连续学习方法与其在视觉任务中的应用

方岩; 魏云超; 丛润民; 左旺孟; 赵耀

doi:10.12263/DZXB.20240750

您当前的位置：

首页 >

文章列表页 >

连续学习方法与其在视觉任务中的应用

大模型与互联网 | 更新时间：2025-10-16

- 连续学习方法与其在视觉任务中的应用
- Continual Learning Methods and Applications in Computer Vision
- 电子学报 2025年53卷第6期页码：1713-1740
- 作者机构：
  
  1.北京交通大学计算机科学与技术学院，北京 100044
  2.山东大学控制科学与工程学院，山东济南 250100
  3.哈尔滨工业大学计算机学院，黑龙江哈尔滨 150001
- 作者简介：
  
  [ "方岩男，2000年8月出生于安徽省宣城市.现为北京交通大学信息科学研究所电子科技博士生.主要研究方向包括计算机视觉与深度学习基础模型.E-mail: yanfang@bjtu.edu.cn" ]
  [ "魏云超男，1987年8月出生于河北省邢台市.2016年毕业于北京交通大学，获工学博士学位.现为北京交通大学计算机科学与技术学院教授、博士生导师.主要研究方向包括面向非完美数据的视觉认知、图像/视频的分割和物体检测、多模态数据建模、生成式人工智能等.中国电子学会会员编号：E190130784M. E-mail: yunchao.wei@bjtu.edu.cn" ]
  [ "丛润民男，1989年9月出生于山东省潍坊市.2019年毕业于天津大学信息与通信工程专业，获工学博士学位.现为山东大学控制科学与工程学院教授、博士生导师.主要研究方向包括计算机视觉、人工智能、多媒体信息处理、视觉显著性计算、遥感影像解译、水下环境感知、智慧医疗、深度学习等.中国电子学会会员编号：E190025265S.E-mail: rmcong@sdu.edu.cn" ]
  [ "左旺孟男，1977年6月出生于河南省新乡市.2007年毕业于哈尔滨工业大学，获工学博士学位.现为哈尔滨工业大学计算机学院长聘教授、博士生导师.主要研究方向包括元学习、迁移学习和生成式对抗网络模型方法及其在底层视觉、图像生成、视觉跟踪、物体检测和图像分类等领域的应用. E-mail: cswmzuo@gmail.com" ]
  [ "赵耀男，1967年12月出生于江苏省徐州市.1996年获北京交通大学工学博士学位.现为北京交通大学计算机科学与技术学院教授、博士生导师.主要研究方向包括数字媒体信息处理与智能分析、人工智能、计算机视觉、AIGC、AI视频编码.中国电子学会会员编号：E190004729S.E-mail: yzhao@bjtu.edu.cn" ]
- 基金信息：
  
  科技创新2030-新一代人工智能重大专项(2021ZD0112100)
- DOI：10.12263/DZXB.20240750
  中图分类号： TP18;
- 收稿：2024-08-13，
  
  修回：2025-05-26，
  
  纸质出版：2025-06-25
- 稿件说明：
移动端阅览
方岩, 魏云超, 丛润民, 等. 连续学习方法与其在视觉任务中的应用[J]. 电子学报, 2025, 53(06): 1713-1740.

FANG Yan, Wei Yun-chao, Cong Run-min, et al. Continual Learning Methods and Applications in Computer Vision[J]. Acta Electronica Sinica, 2025, 53(06): 1713-1740.
方岩, 魏云超, 丛润民, 等. 连续学习方法与其在视觉任务中的应用[J]. 电子学报, 2025, 53(06): 1713-1740. DOI：10.12263/DZXB.20240750

FANG Yan, Wei Yun-chao, Cong Run-min, et al. Continual Learning Methods and Applications in Computer Vision[J]. Acta Electronica Sinica, 2025, 53(06): 1713-1740. DOI：10.12263/DZXB.20240750

摘要

连续学习广义上指智能算法与智能体学习和适应动态变化世界的能力，这使得智能算法能够在部署周期中不断获取、更新、积累和利用知识.连续学习技术赋予了智能系统自适应发展的前景和能力.在深度学习中，连续学习具体指的是能够从非平稳数据流中学习和适应不断变化的训练目标，这一任务通常面临着灾难性遗忘的挑战，即学习新任务通常会导致旧任务性能的大幅下降.近年来，随着深度学习在语言、视觉等诸多领域的迅速发展，涌现了诸多进展，有效拓展了对连续学习的理解和应用.本工作对现有连续学习工作进行了较为广泛而深入的调研，并从连续学习基础定义、代表性方法、在视觉领域的应用等多角度分析.最后，本文也对连续学习当前的前沿发展和未来研究趋势进行探讨.基于对连续学习领域相关工作的探讨，期待本文这一综述可以有效促进该领域和后续研究工作的进一步发展和探索.

Abstract

Continual learning generally refers to the ability of intelligent algorithms and agents to learn and adapt to a dynamic and changing world

enabling these algorithms to continually acquire

update

accumulate

and utilize knowledge throughout their deployment cycle. Continual learning technologies endow intelligent systems with the prospects and capabilities of adaptive development. In the context of deep learning

continual learning specifically refers to the ability to learn from non-stationary data streams and adapt to changing training objectives. This task often faces the challenge of catastrophic forgetting

where learning new tasks typically results in a significant decline in performance on previously learned tasks. In recent years

with the rapid development of deep learning in various fields such as language and vision

numerous advancements have emerged

effectively extending the understanding and application of continual learning. This work conducts a relatively extensive and comprehensive survey of existing continual learning research

analyzing it from multiple perspectives including fundamental definition

representative methods

applications in the visual domain. Finally

this paper also discusses the current cutting-edge developments and future research trends in continual learning. Based on the discussion of relevant work in the field of continual learning

we hope this review can effectively promote the development and exploration of this field and subsequent research endeavors.

关键词

Keywords

references

朱飞 , 张煦尧 , 刘成林 . 类别增量学习研究进展和性能评价 [J ] . 自动化学报 , 2023 , 49 ( 3 ): 635 - 660 .

ZHU F , ZHANG X Y , LIU C L . Class incremental learning: A review and performance evaluation [J ] . Acta Automatica Sinica , 2023 , 49 ( 3 ): 635 - 660 . (in Chinese)

张东阳 , 陆子轩 , 刘军民 , 等 . 深度模型的持续学习综述: 理论、方法和应用 [J ] . 电子与信息学报 , 2024 , 46 ( 10 ): 3849 - 3878 .

ZHANG D Y , LU Z X , LIU J M , et al . A survey of continual learning with deep networks: Theory, method and application [J ] . Journal of Electronics Information Technology , 2024 , 46 ( 10 ): 3849 - 3878 . (in Chinese)

杨静 , 李斌 , 李少波 , 等 . 脑启发式持续学习方法: 技术、应用与发展 [J ] . 电子与信息学报 , 2022 , 44 ( 5 ): 1865 - 1878 .

YANG J , LI B , LI S B , et al . Brain-inspired continuous learning: Technology, application and future [J ] . Journal of Electronics Information Technology , 2022 , 44 ( 5 ): 1865 - 1878 . (in Chinese)

常一帆 . 人脑学习与记忆机制启发的卷积神经网络持续学习方法 [D ] . 合肥 : 中国科学技术大学 , 2023 .

CHANG Y F . Research on Continual Learning of Convolutional Neural Networks Inspired [D ] . Hefei : University of Science and Technology of China , 2023 . (in Chinese)

张亮 . 针对视觉数据的连续学习方法研究 [D ] . 成都 : 电子科技大学 , 2024 .

ZHANG L . Research on Continual Learning Methods for Visual Data [D ] . Chengdu : University of Electronic Science and Technology of China , 2024 . (in Chinese)

SOUTIF-CORMERAIS A , CARTA A , COSSU A , et al . A comprehensive empirical evaluation on online continual learning [C ] // 2023 IEEE/CVF International Conference on Computer Vision Workshops . Piscataway : IEEE , 2023 : 3510 - 3520 .

MASANA M , LIU X , TWARDOWSKI B , et al . Class-incremental learning: Survey and performance evaluation on image classification [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 45 ( 5 ): 5513 - 5533 .

ZHOU D W , WANG Q W , QI Z H , et al . Class-incremental learning: A survey [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 ( 12 ): 9851 - 9873 .

WANG Z Y , YANG E N , SHEN L , et al . A comprehensive survey of forgetting in deep learning beyond continual learning [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 47 ( 3 ): 1464 - 1483 .

GHOSH S . Dynamic VAEs with generative replay for continual zero-shot learning [EB/OL ] . ( 2021-04-26 )[ 2024-05-30 ] . https://arxiv.org/abs/2104.12468 https://arxiv.org/abs/2104.12468 .

SINGH P , MAZUMDER P , RAI P , et al . Rectification-based knowledge retention for continual learning [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 15277 - 15286 .

TAO X Y , HONG X P , CHANG X Y , et al . Few-shot class-incremental learning [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 12180 - 12189 .

WANG L Y , YANG K , LI C X , et al . ORDisCo: Effective and efficient usage of incremental unlabeled data for semi-supervised continual learning [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 5379 - 5388 .

JOSEPH K J , KHAN S , KHAN F S , et al . Towards open world object detection [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 5826 - 5836 .

WANG Q F , GENG X , LIN S X , et al . Learngene: From open-world to your learning task [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 8 ): 8557 - 8565 .

HU D P , YAN S P , LU Q , et al . How well does self-supervised pre-training perform with streaming data [EB/OL ] . ( 2021-07-21 )[ 2024-05-30 ] . https://arxiv.org/abs/2104.12081 https://arxiv.org/abs/2104.12081

RAO D , VISIN F , RUSU A A , et al . Continual unsupervised representation learning [EB/OL ] . ( 2019-10-31 )[ 2024-05-30 ] . https://arXiv.org/abs/1910.14481 https://arXiv.org/abs/1910.14481 .

KIM C D , JEONG J , KIM G . Imbalanced continual learning with partitioning reservoir sampling [EB/OL ] . ( 2020-09-08 )[ 2024-05-30 ] . https://arXiv.org/abs/2009.03632 https://arXiv.org/abs/2009.03632 .

BANG J , KOH H , PARK S , et al . Online continual learning on a contaminated data stream with blurry task boundaries [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9265 - 9274 .

LIN H B , ZHANG Y F , QIU Z , et al . Prototype-guided continual adaptation for class-incremental unsupervised domain adaptation [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 351 - 368 .

SIMON C , FARAKI M , TSAI Y H , et al . On generalizing beyond domains in cross-domain continual learning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9255 - 9264 .

KOH H , KIM D , HA J W , et al . Online continual learning on class incremental blurry task configuration with anytime inference [EB/OL ] . ( 2021-10-19 )[ 2024-05-30 ] . https://arXiv.org/abs/2110.10031 https://arXiv.org/abs/2110.10031 .

JOSEPH K J , PAUL S , AGGARWAL G , et al . Novel class discovery without forgetting [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 570 - 586 .

SRINIVASAN T , CHANG T Y , ALVA L L P , et al . CLiMB: A continual learning benchmark for vision-and-language tasks [EB/OL ] . ( 2022-06-18 )[ 2024-05-30 ] . https://arXiv.org/abs/2206.09059. https://arXiv.org/abs/2206.09059. .

KIRKPATRICK J , PASCANU R , RABINOWITZ N , et al . Overcoming catastrophic forgetting in neural networks [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2017 , 114 ( 13 ): 3521 - 3526 .

ZENKE F , POOLE B , GANGULI S . Continual learning through synaptic intelligence [C ] // Proceedings of the 34th International Conference on Machine Learning - Volume 70 . New York : ACM , 2017 : 3987 - 3995 .

ALJUNDI R , BABILONI F , ELHOSEINY M , et al . Memory aware synapses: Learning what (not) to forget [M ] // Computer Vision - ECCV 2018 . Cham : Springer International Publishing , 2018 : 144 - 161 .

CHAUDHRY A , DOKANIA P K , AJANTHAN T , et al . Riemannian walk for incremental learning: Understanding forgetting and intransigence [M ] // Computer Vision - ECCV 2018 . Cham : Springer International Publishing , 2018 : 556 - 572 .

LIU X L , MASANA M , HERRANZ L , et al . Rotate your networks: Better weight consolidation and less catastrophic forgetting [C ] // 2018 the 24th International Conference on Pattern Recognition . Piscataway : IEEE , 2018 : 2262 - 2268 .

LEE J , HONG H G , JOO D , et al . Continual learning with extended kronecker-factored approximate curvature [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 8998 - 9007 .

PARK D , HONG S , HAN B , et al . Continual learning by asymmetric loss approximation with single-side overestimation [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 3334 - 3343 .

LEE S W , KIM J H , JUN J , et al . Overcoming catastrophic forgetting by incremental moment matching [EB/OL ] . ( 2017-03-24 )[ 2024-05-30 ] . https://arXiv.org/abs/1703.08475 https://arXiv.org/abs/1703.08475 .

LEE J , JOO D , HONG H G , et al . Residual continual learning [EB/OL ] . ( 2020-02-17 )[ 2024-05-30 ] . https://arXiv.org/abs/2002.06774 https://arXiv.org/abs/2002.06774 .

SCHWARZ J , CZARNECKI W , LUKETINA J , et al . Progress Compress: A scalable framework for continual learning [EB/OL ] . ( 2018-05-16 )[ 2024-05-30 ] . https://arxiv.org/abs/1805.06370 https://arxiv.org/abs/1805.06370 .

WANG L Y , ZHANG M T , JIA Z F , et al . AFEC: Active forgetting of negative transfer in continual learning [EB/OL ] . ( 2021-11-04 )[ 2024-05-30 ] . https://arXiv.org/abs/2110.12187 https://arXiv.org/abs/2110.12187 .

SWAROOP S , NGUYEN C V , BUI T D , et al . Improving and understanding variational continual learning [EB/OL ] . ( 2019-05-06 )[ 2024-05-30 ] . https://arXiv.org/abs/1905.02099 https://arXiv.org/abs/1905.02099 .

NGUYEN C V , LI Y Z , BUI T D , et al . Variational continual learning [EB/OL ] . ( 2018-05-20 )[ 2024-05-30 ] . https://arXiv.org/abs/1710.10628 https://arXiv.org/abs/1710.10628 .

TSERAN H , KHAN M E , HARADA T , et al . Natural Variational Continual Learning [EB/OL ] . ( 2018-01-01 )[ 2024-05-30 ] . https://marcpickett.com/cl2018/CL-2018_paper_51.pdf https://marcpickett.com/cl2018/CL-2018_paper_51.pdf .

ADEL T , ZHAO H , TURNER R E . Continual learning with adaptive weights (CLAW) [EB/OL ] . ( 2020-06-16 )[ 2024-05-30 ] . https://arXiv.org/abs/1911.09514 https://arXiv.org/abs/1911.09514 .

LOO N , SWAROOP S , TURNER R E . Generalized variational continual learning [EB/OL ] . ( 2020-11-24 )[ 2024-05-30 ] . https://arXiv.org/abs/2011.12328 https://arXiv.org/abs/2011.12328 .

DERAKHSHANI M M , ZHEN X , SHAO L , et al . Kernel continual learning [C ] // Proceedings of the 38th International Conference on Machine Learning . Cambridge : PMLR , 2021 : 2621 - 2631 .

KAPOOR S , KARALETSOS T , BUI T D . Variational auto-regressive Gaussian processes for continual learning [EB/OL ] . ( 2021-06-12 )[ 2024-05-30 ] . https://arXiv.org/abs/2006.05468 https://arXiv.org/abs/2006.05468 .

PAIK I , OH S , KWAK T , et al . Overcoming catastrophic forgetting by neuron-level plasticity control [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 4 ): 5339 - 5346 .

AHN H , CHA S , LEE D , et al . Uncertainty-based continual learning with adaptive regularization [EB/OL ] . ( 2019-11-14 )[ 2024-05-30 ] . https://arXiv.org/abs/1905.11614 https://arXiv.org/abs/1905.11614 .

JUNG S , AHN H , CHA S , et al . Continual learning with node-importance based adaptive group sparse regularization [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 3647 - 3658 .

LI Z Z , HOIEM D . Learning without forgetting [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 , 40 ( 12 ): 2935 - 2947 .

DHAR P , SINGH R V , PENG K C , et al . Learning without memorizing [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 5133 - 5141 .

LEE K , LEE K , SHIN J , et al . Overcoming catastrophic forgetting with unlabeled data in the wild [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 312 - 321 .

CASTRO F M , MARÍN-JIMÉNEZ M J , GUIL N , et al . End-to-end incremental learning [M ] // Computer Vision - ECCV 2018 . Cham : Springer International Publishing , 2018 : 241 - 257 .

HOU S H , PAN X Y , LOY C C , et al . Learning a unified classifier incrementally via rebalancing [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 831 - 839 .

DOUILLARD A , CORD M , OLLION C , et al . PODNet: Pooled outputs distillation for small-tasks incremental learning [C ] // Computer Vision - ECCV 2020 . Cham : Springer Nature Switzerland , 2020 : 86 - 102 .

BUZZEGA P , BOSCHINI M , PORRELLO A , et al . Dark experience for general continual learning: A strong, simple baseline [EB/OL ] . ( 2020-10-22 )[ 2024-05-30 ] . https://arXiv.org/abs/2004.07211 https://arXiv.org/abs/2004.07211 .

TITSIAS M K , SCHWARZ J , DE G MATTHEWS A G , et al . Functional regularisation for continual learning with Gaussian processes [EB/OL ] . ( 2022-02-11 )[ 2024-05-30 ] . https://arXiv.org/abs/1901.11356 https://arXiv.org/abs/1901.11356 .

PAN P B , SWAROOP S , IMMER A , et al . Continual deep learning by functional regularisation of memorable past [EB/OL ] . ( 2020-01-08 )[ 2024-05-30 ] . https://arXiv.org/abs/2004.14070 https://arXiv.org/abs/2004.14070 .

RUDNER T G J , SMITH F B , FENG Q X , et al . Continual learning via sequential function-space variational inference [EB/OL ] . ( 2023-12-28 )[ 2024-05-30 ] . https://arXiv.org/abs/2312.17210 https://arXiv.org/abs/2312.17210 .

REBUFFI S A , KOLESNIKOV A , SPERL G , et al . iCaRL: Incremental classifier and representation learning [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 5533 - 5542 .

ALJUNDI R , LIN M , GOUJAUD B , et al . Gradient based sample selection for online continual learning [EB/OL ] . ( 2019-10-31 )[ 2024-05-30 ] . https://arXiv.org/abs/1903.08671 https://arXiv.org/abs/1903.08671 .

BORSOS Z , MUTNY M , KRAUSE A . Coresets via bilevel optimization for continual learning and Streaming [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 14879 - 14890 .

YOON J , MADAAN D , YANG E , et al . Online coreset selection for rehearsal-based continual learning [EB/OL ] . ( 2022-03-18 )[ 2024-05-30 ] . https://arXiv.org/abs/2106.01085 https://arXiv.org/abs/2106.01085 .

SHIM D , MAI Z D , JEONG J , et al . Online class-incremental continual learning with adversarial shapley value [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 11 ): 9630 - 9638 .

BANG J , KIM H , YOO Y , et al . Rainbow memory: Continual learning with a memory of diverse samples [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 8214 - 8223 .

CACCIA L , BELILOVSKY E , CACCIA M , et al . Online learned continual compression with adaptive quantization modules [C ] // Proceedings of the 37th International Conference on Machine Learning . New York : ACM , 2020 : 1240 - 1250 .

WANG L Y , ZHANG X X , YANG K , et al . Memory replay with data compression for continual learning [EB/OL ] . ( 2022-03-09 )[ 2024-05-30 ] . https://arXiv.org/abs/2202.06592 https://arXiv.org/abs/2202.06592 .

KUMARI L , WANG S , ZHOU T , et al . Retrospective adversarial replay for continual Learning [C ] // Advances in Neural Information Processing Systems 35 . San Diego : NeurIPS , 2022 : 28530 - 28544 .

SHIN H , LEE J K , KIM J , et al . Continual learning with deep generative replay [EB/OL ] . ( 2017-12-12 )[ 2024-05-30 ] . https://arXiv.org/abs/1705.08690 https://arXiv.org/abs/1705.08690 .

WU C , HERRANZ L , LIU X , et al . Memory replay GANs: Learning to generate new categories without forgetting [C ] // Advances in Neural Information Processing Systems 31 . San Diego : NeurIPS , 2018 : 31 .

LIU X L , WU C S , MENTA M , et al . Generative feature replay for class-incremental learning [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2020 : 915 - 924 .

ISCEN A , ZHANG J , LAZEBNIK S , et al . Memory-efficient incremental learning through feature adaptation [M ] // Computer Vision - ECCV 2020 . Cham : Springer International Publishing , 2020 : 699 - 715 .

ZHU K , ZHAI W , CAO Y , et al . Self-sustaining representation expansion for non-exemplar class-incremental learning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9286 - 9295 .

BELOUADAH E , POPESCU A . IL2 M: Class incremental learning with dual memory[C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 583 - 592 .

GONG Z , ZHOU K , ZHAO X , et al . Continual pre-training of language models for math problem understanding with syntax-aware memory network [C ] // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics . Stroudsburg : ACL , 2022 : 5923 - 5933 .

TOLDO M , OZAY M . Bring evanescent representations to life in lifelong class incremental learning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 16711 - 16720 .

HAYES T L , KAFLE K , SHRESTHA R , et al . REMIND your neural network to prevent catastrophic forgetting [M ] // Computer Vision - ECCV 2020 . Cham : Springer International Publishing , 2020 : 466 - 483 .

WANG K , HERRANZ L , VAN DE WEIJER J . ACAE-REMIND for online continual learning with compressed feature replay [EB/OL ] . ( 2021-07-08 )[ 2024-05-30 ] . https://arXiv.org/abs/2105.08595 https://arXiv.org/abs/2105.08595 .

PETIT G , POPESCU A , SCHINDLER H , et al . FeTrIL: Feature translation for exemplar-free class-incremental learning [C ] // 2023 IEEE/CVF Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2023 : 3900 - 3909 .

ZENG G X , CHEN Y , CUI B , et al . Continual learning of context-dependent processing in neural networks [J ] . Nature Machine Intelligence , 2019 , 1 ( 8 ): 364 - 372 .

GUO Y D , HU W P , ZHAO D Y , et al . Adaptive orthogonal projection for batch and online continual learning [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 6 ): 6783 - 6791 .

FARAJTABAR M , AZIZAN N , MOTT A , et al . Orthogonal gradient descent for continual learning [C ] // Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics . Cambridge : PMLR , 2020 : 3762 - 3773 .

SAHA G , GARG I , ROY K . Gradient projection memory for continual learning [EB/OL ] . ( 2021-03-17 )[ 2024-05-30 ] . https://arXiv.org/abs/2103.09762 https://arXiv.org/abs/2103.09762 .

CHEN C , ZHANG J , SONG J K , et al . Class gradient projection for continual learning [C ] // Proceedings of the 30th ACM International Conference on Multimedia . New York : ACM , 2022 : 5575 - 5583 .

DENG D R , CHEN G Y , HAO J Y , et al . Flattening sharpness for dynamic gradient projection memory benefits continual learning [EB/OL ] . ( 2021-10-09 )[ 2024-05-30 ] . https://arXiv.org/abs/2110.04593 https://arXiv.org/abs/2110.04593 .

LIN S , YANG L , FAN D L , et al . Beyond not-forgetting: Continual learning with backward knowledge transfer [EB/OL ] . ( 2022-11-01 )[ 2024-05-30 ] . https://arXiv.org/abs/2211.00789 https://arXiv.org/abs/2211.00789 .

LIN S , YANG L , FAN D L , et al . TRGP: Trust region gradient projection for continual learning [EB/OL ] . ( 2022-02-07 )[ 2024-05-30 ] . https://arXiv.org/abs/2202.02931 https://arXiv.org/abs/2202.02931 .

WANG S P , LI X R , SUN J , et al . Training networks in null space of feature covariance for continual learning [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 184 - 193 .

KONG Y J , LIU L , WANG Z , et al . Balancing stability and plasticity through advanced null space in continual learning [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 219 - 236 .

KAO T C , JENSEN K T , VAN DE VEN G M , et al . Natural continual learning: Success is a journey, not (just) a destination [EB/OL ] . ( 2021-12-15 )[ 2024-05-30 ] . https://arXiv.org/abs/2106.08085 https://arXiv.org/abs/2106.08085 .

LIU H , LIU H P . Continual learning with recursive gradient optimization [EB/OL ] . ( 2022-01-29 )[ 2024-05-30 ] . https://arXiv.org/abs/2201.12522 https://arXiv.org/abs/2201.12522 .

JAVED K , WHITE M . Meta-learning representations for continual learning [EB/OL ] . ( 2019-10-30 )[ 2024-05-30 ] . https://arXiv.org/abs/1905.12588 https://arXiv.org/abs/1905.12588 .

SHAWN B , LAPO F , THOMAS M , et al . Learning to continually learn [EB/OL ] . ( 2020-03-04 )[ 2024-05-30 ] . https://arxiv.org/abs/2002.09571 https://arxiv.org/abs/2002.09571 .

LEE E , HUANG C H , LEE C Y . Few-shot and continual learning with attentive independent mechanisms [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 9435 - 9444 .

RIEMER M , CASES I , AJEMIAN R , et al . Learning to learn without forgetting by maximizing transfer and minimizing interference [EB/OL ] . ( 2019-03-03 )[ 2024-05-30 ] . https://arxiv.org/abs/1810.11910 https://arxiv.org/abs/1810.11910 .

RAJASEGARAN J , KHAN S , HAYAT M , et al . iTAML: An incremental task-agnostic meta-learning approach [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 13585 - 13594 .

GUPTA G , YADAV K , PAULL L . Look-ahead meta learning for continual learning [C ] // Advances in Neural Information Processing Systems 33 . San Diego : NeurIPS , 2020 : 11588 - 11598 .

CACCIA M , RODR I P . Online fast adaptation and knowledge accumulation (OSAKA): A new approach to continual learning [C ] // NIPS’20: Proceedings of the 34th International Conference on Neural Information Processing Systems New York: ACM , 2020 : 16532 - 16545 .

JOSEPH K J , BALASUBRAMANIAN V N . Meta-consolidation for continual learning [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 14374 - 14386 .

HENNING C , CERVERA M R , D’ANGELO F , et al . Posterior meta-replay for continual learning [EB/OL ] . ( 2021-10-21 )[ 2024-05-30 ] . https://arXiv.org/abs/2103.01133 https://arXiv.org/abs/2103.01133 .

HURTADO J , RAYMOND-S A A . Optimizing reusable knowledge for continual learning via metalearning [C ] // Proceedings of the 35th Conference on Neural Information Processing Systems . New York : ACM , 2021 : 1 - 13 .

WANG R Q , BAO Y X , ZHANG B C , et al . Anti-retroactive interference forLifelong learning [C ] // Computer Vision - ECCV 2022 . Cham : Springer , 2022 : 163 - 178 .

MIRZADEH S I , FARAJTABAR M , PASCANU R , et al . Understanding the role of training regimes in continual learning [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 7308 - 7320 .

MIRZADEH S I , FARAJTABAR M , GORUR D , et al . Linear mode connectivity in multitask and continual learning [EB/OL ] . ( 2020-10-09 )[ 2024-05-30 ] . https://arXiv.org/abs/2010.04495 https://arXiv.org/abs/2010.04495 .

LIN G L , CHU H L , LAI H J . Towards better plasticity-stability trade-off in incremental learning: A simple linear connector [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 89 - 98 .

MADAAN D , YOON J , LI Y C , et al . Representational continuity for unsupervised continual learning [EB/OL ] . ( 2022-04-05 )[ 2024-05-30 ] . https://arXiv.org/abs/2110.06976 https://arXiv.org/abs/2110.06976 .

PURUSHWALKAM S , MORGADO P , GUPTA A . The challenges of Continuous self-supervised learning [C ] // Computer Vision - ECCV 2022 . Cham : Springer , 2022 : 702 - 721 .

FINI E , COSTA V G T DA , ALAMEDA-PINEDA X , et al . Self-supervised models are continual learners [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9611 - 9620 .

CHA H , LEE J , SHIN J . Co2 L: Contrastive continual learning[C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 9496 - 9505 .

PHAM Q , LIU C , HOI S . DualNet: Continual learning, fast and slow [C ] // Advances in Neural Information Processing Systems 34 . San Diego : NeurIPS , 2021 : 16131 - 16144 .

ZHANG J O , SAX A , ZAMIR A , et al . Side-tuning: A baseline for network adaptation via additive side networks [M ] // Computer Vision - ECCV 2020 . Cham : Springer International Publishing , 2020 : 698 - 714 .

SHON H , LEE J , KIM S H , et al . DLCFT: Deep linear continual fine-tuning for general incremental learning [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 513 - 529 .

BOSCHINI M , BONICELLI L , PORRELLO A , et al . Transfer without forgetting [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 692 - 709 .

CONG Y , ZHAO M , LI J , et al . GAN memory with no forgetting [C ] // Advances in Neural Information Processing Systems 33 . San Diego : NeurIPS , 2020 : 16481 - 16494 .

PEREZ E , STRUB F , DE VRIES H , et al . FiLM: Visual reasoning with a general conditioning layer [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2018 , 32 ( 1 ): 3942 - 3951 .

ZHAO M Y , CONG Y L , CARIN L . On leveraging pretrained GANs for generation with limited data [EB/OL ] . ( 2020-08-08 )[ 2024-05-31 ] . https://arxiv.org/abs/2002.11810 https://arxiv.org/abs/2002.11810 .

WANG Z F , ZHANG Z Z , LEE C Y , et al . Learning to prompt for continual learning [EB/OL ] . ( 2022-03-21 )[ 2024-05-30 ] . https://arXiv.org/abs/2112.08654 https://arXiv.org/abs/2112.08654 .

SMITH J S , KARLINSKY L , GUTTA V , et al . CODA-prompt: COntinual decomposed attention-based prompting for rehearsal-free continual learning [EB/OL ] . ( 2023-03-30 )[ 2024-05-30 ] . https://arXiv.org/abs/2211.13218 https://arXiv.org/abs/2211.13218 .

WANG Z F , ZHANG Z Z , EBRAHIMI S , et al . DualPrompt: Complementary prompting for rehearsal-free continual learning [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 631 - 648 .

WANG Y B , HUANG Z W , HONG X P . S-prompts learning with pre-trained transformers: An Occam’s razor for domain incremental learning [EB/OL ] . ( 2023-03-18 )[ 2024-05-31 ] . https://arXiv.org/abs/2207.12819 https://arXiv.org/abs/2207.12819 .

WANG L Y , XIE J Y , ZHANG X X , et al . Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality [C ] // Proceedings of the 37th International Conference on Neural Information Processing Systems . New York : ACM , 2023 : 69054 - 69076 .

RAZDAIBIEDINA A , MAO Y N , HOU R , et al . Progressive prompts: Continual learning for language models [EB/OL ] . ( 2023-01-29 )[ 2024-05-30 ] . https://arXiv.org/abs/2301.12314 https://arXiv.org/abs/2301.12314 .

SHI Y J , ZHOU K Q , LIANG J , et al . Mimicking the oracle: An initial phase decorrelation approach for class incremental learning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 16701 - 16710 .

SHI G , CHEN J , ZHANG W , et al . Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima [C ] // Advances in Neural Information Processing Systems 34 , San Diego : NeurIPS , 2024 : 6747 - 6761 .

MEHTA S V , PATIL D , CHANDAR S , et al . An empirical investigation of the role of pre-training in lifelong learning [J ] . Journal of Machine Learning Research , 2023 , 24 ( 1 ): 10185 - 10234 .

FORET P , KLEINER A , MOBAHI H , et al . Sharpness-aware minimization for efficiently improving generalization [EB/OL ] . ( 2021-04-29 )[ 2024-05-30 ] . https://arXiv.org/abs/2010.01412 https://arXiv.org/abs/2010.01412 .

YAN S P , HONG L Q , XU H , et al . Generative negative text replay for continual vision-language pretraining [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 22 - 38 .

HAN R J , REN X , PENG N Y . ECONET: Effective continual pretraining of language models for event temporal reasoning [C ] // Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing . Stroudsburg : ACL , 2021 : 5367 - 5380 .

LIU Q , MAJUMDER O , ACHILLE A , et al . Incremental few-shot meta-learning via indirect discriminant alignment [M ] // Computer Vision - ECCV 2020 . Cham : Springer International Publishing , 2020 : 685 - 701 .

WANG Z Y , SHEN L , FANG L , et al . Meta-learning with less forgetting on large-scale non-stationary task distributions [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 221 - 238 .

ZHU H G , WEI Y C , LIANG X D , et al . CTP: Towards vision-language continual pretraining via compatible momentum contrast and topology preservation [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 22200 - 22210 .

KE Z X , SHAO Y J , LIN H W , et al . Continual pre-training of language models [EB/OL ] . ( 2023-04-12 )[ 2024-05-30 ] . https://arXiv.org/abs/2302.03241 https://arXiv.org/abs/2302.03241 .

CHAUDHRY A , ROHRBACH M , ELHOSEINY M , et al . On tiny episodic memories in continual learning [EB/OL ] . ( 2019-06-04 )[ 2024-05-30 ] . https://arXiv.org/abs/1902.10486 https://arXiv.org/abs/1902.10486 .

RICE J R , VITTER J S . Random sampling with a reservoir [J ] . ACM Transactions on Mathematical Software , 1985 , 11 ( 1 ): 37 - 57 .

LOPEZ-PAZ D , RANZATO M . Gradient episodic memory for continual learning [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 6470 - 6479 .

VAN DEN OORD A , VINYALS O , KAVUKCUOGLU KORAY . Neural discrete representation learning [C ] // Advances in Neural Information Processing Systems 30 . San Diego : NeurIPS , 2017 : 1 - 10 .

KULESZA A . Determinantal point processes for machine learning [J ] . Foundations and Trends in Machine Learning , 2012 , 5 ( 2/3 ): 123 - 286 .

KIM J , CHO H , KIM J , et al . SDDGR: Stable diffusion-based deep generative replay for class incremental object detection [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 28772 - 28781 .

DOAN K , TRAN Q , TRAN T L , et al . Class-prototype conditional diffusion model with gradient projection for continual learning [EB/OL ] . ( 2024-03-21 )[ 2024-05-30 ] . https://arXiv.org/abs/2312.06710 https://arXiv.org/abs/2312.06710 .

CYWIŃSKI B , DEJA K , TRZCIŃSKI T , et al . GUIDE: Guidance-based incremental learning with diffusion models [EB/OL ] . ( 2024-03-31 )[ 2024-05-30 ] . https://arXiv.org/abs/2403.03938 https://arXiv.org/abs/2403.03938 .

GOU J P , YU B S , MAYBANK S J , et al . Knowledge distillation: A survey [J ] . International Journal of Computer Vision , 2021 , 129 ( 6 ): 1789 - 1819 .

DHAR P , SINGH R V , PENG K C , et al . Learning without memorizing [C ] // IEEE/CVF Conference on Computer Vision and Pattern Recognition , Piscataway : IEEE , 2019 , 5138 - 5146 .

TRIKI A R , ALJUNDI R , BLASCHKO M B , et al . Encoder based lifelong learning [EB/OL ] . ( 2017-04-06 )[ 2024-05-30 ] . https://arXiv.org/abs/1704.01920 https://arXiv.org/abs/1704.01920 .

ZHAI M Y , CHEN L , TUNG F , et al . Lifelong GAN: Continual learning for conditional image generation [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 2759 - 2768 .

WANG Z , LIU L , DUAN Y Q , et al . Continual learning through retrieval and imagination [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 8 ): 8594 - 8602 .

CHAUDHRY A , RANZATO M , ROHRBACH M , et al . Efficient lifelong learning with A-GEM [EB/OL ] . ( 2019-01-09 )[ 2024-05-30 ] . https://arXiv.org/abs/1812.00420 https://arXiv.org/abs/1812.00420 .

TANG S X , CHEN D P , ZHU J G , et al . Layerwise optimization by gradient decomposition for continual learning [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 9629 - 9638 .

CHAUDHRY A , KHAN N , DOKANIA P K , et al . Continual learning in low-rank orthogonal subspaces [EB/OL ] . ( 2020-12-08 )[ 2024-05-30 ] . https://arXiv.org/abs/2010.11635 https://arXiv.org/abs/2010.11635 .

HADSELL R , RAO D , RUSU A A , et al . Embracing change: Continual learning in deep neural networks [J ] . Trends in Cognitive Sciences , 2020 , 24 ( 12 ): 1028 - 1040 .

CHEN X L , XIE S N , HE K M . An empirical study of training self-supervised vision transformers [EB/OL ] . ( 2021-08-16 )[ 2024-05-30 ] . https://arXiv.org/abs/2104.02057 https://arXiv.org/abs/2104.02057 .

ERICSSON L , GOUK H , HOSPEDALES T M . How well do self-supervised models transfer? [EB/OL ] . ( 2021-03-29 )[ 2024-05-30 ] . https://arXiv.org/abs/2011.13377 https://arXiv.org/abs/2011.13377 .

DAVARI M , ASADI N , MUDUR S , et al . Probing representation forgetting in supervised and unsupervised continual learning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 16691 - 16700 .

RAMASESH V V , LEWKOWYCZ A , DYER E . Effect of scale on catastrophic forgetting in neural networks [C ] // International Conference on Learning Representations . Appleton : ICLR . 2021 : 1 - 33 .

WU T Y , SWAMINATHAN G , LI Z Z , et al . Class-incremental learning with strong pre-trained models [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9591 - 9600 .

HAO Y R , DONG L , WEI F R , et al . Visualizing and understanding the effectiveness of BERT [C ] // Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing . Stroudsburg : ACL , 2019 : 4141 - 4150 .

NEYSHABUR B , SEDGHI H , ZHANG C Y . What is being transferred in transfer learning? [EB/OL ] . ( 2021-01-14 )[ 2024-05-30 ] . https://arXiv.org/abs/2008.11687 https://arXiv.org/abs/2008.11687 .

GALLARDO J , HAYES T L , KANAN C . Self-supervised training enhances online continual learning [EB/OL ] . ( 2021-10-22 )[ 2024-05-30 ] . https://arXiv.org/abs/2103.14010 https://arXiv.org/abs/2103.14010 .

OSTAPENKO O , TIMOTH{\'E . Continual learning with foundation models: An empirical study of latent replay [C ] // Proceedings of the 1st Conference on Lifelong Learning Agents . Cambridge : PMLR , 2022 : 60 - 91 .

PELOSIN F . Simpler is better: Off-the-shelf continual learning through pretrained backbones [EB/OL ] . ( 2022-05-03 )[ 2024-05-30 ] . https://arXiv.org/abs/2205.01586 https://arXiv.org/abs/2205.01586 .

JANSON P , ZHANG W X , ALJUNDI R , et al . A simple baseline that questions the use of pretrained-models in continual learning [EB/OL ] . ( 2023-03-29 )[ 2024-05-30 ] . https://arXiv.org/abs/2210.04428 https://arXiv.org/abs/2210.04428 .

HUANG W C , CHEN C F , HSU H . OVOR: OnePrompt with virtual outlier regularization for rehearsal-free class-incremental learning [EB/OL ] . ( 2024-02-26 )[ 2024-05-30 ] . https://arXiv.org/abs/2402.04129 https://arXiv.org/abs/2402.04129 .

ROY A , MOULICK R , VERMA V K , et al . Convolutional prompting meets language models for continual learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23616 - 23626 .

GAO Z X , CEN J , CHANG X B . Consistent prompting for rehearsal-free continual learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 28463 - 28473 .

ZHANG G W , WANG L Y , KANG G L , et al . SLCA: Slow learner with classifier alignment for continual learning on a pre-trained model [EB/OL ] . ( 2023-10-09 )[ 2024-05-30 ] . https://arXiv.org/abs/2303.05118 https://arXiv.org/abs/2303.05118 .

MCDONNELL M D , GONG D , PARVENEH A , et al . RanPAC: Random projections and pre-trained models for continual learning [EB/OL ] . ( 2024-01-16 )[ 2024-05-30 ] . https://arXiv.org/abs/2307.02251 https://arXiv.org/abs/2307.02251 .

CAO X S , LU H R , HUANG L L , et al . Generative multi-modal models are good class-incremental learners [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 28706 - 28717 .

ZHOU D W , SUN H L , YE H J , et al . Expandable subspace ensemble for pre-trained model-based class-incremental learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23554 - 23564 .

TAN Y W , ZHOU Q H , XIANG X , et al . Semantically-shifted incremental adapter-tuning is a continual ViTransformer [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23252 - 23262 .

LIANG Y S , LI W J . InfLoRA: Interference-free low-rank adaptation for continual learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23638 - 23647 .

COSSU A , TUYTELAARS T , CARTA A , et al . Continual pre-training mitigates forgetting in language and vision [EB/OL ] . ( 2022-03-09 )[ 2024-05-30 ] . https://arXiv.org/abs/2205.09357 https://arXiv.org/abs/2205.09357 .

RADFORD A , KIM J W , HALLACY C , et al . Learning transferable visual models from natural language supervision [C ] // Proceedings of the 38th International Conference on Machine Learning . Cambridge : PMLR , 2021 : 8748 - 8763 .

SHMELKOV K , SCHMID C , ALAHARI K . Incremental learning of object detectors without catastrophic forgetting [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 3420 - 3429 .

GIRSHICK R . Fast R-CNN [C ] // 2015 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2015 : 1440 - 1448 .

RAMAKRISHNAN K , PANDA R , FAN Q F , et al . Relationship matters: Relation guided knowledge transfer for incremental learning of object detectors [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2020 : 1009 - 1018 .

ZHOU X , WANG D , KRÄHENBÜHL P . Objects as Points [EB/OL ] . ( 2019-04-25 )[ 2024-05-30 ] . https://arxiv.org/abs/1904.07850 https://arxiv.org/abs/1904.07850 .

PENG C , ZHAO K , MAKSOUD S , et al . SID: Incremental learning for anchor-free object detection via selective and inter-related distillation [J ] . Computer Vision and Image Understanding , 2021 , 210 : 103229 .

LIN T Y , GOYAL P , GIRSHICK R , et al . Focal loss for dense object detection [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 , 42 ( 2 ): 318 - 327 .

LI D W , TASCI S , GHOSH S , et al . RILOD: Near real-time incremental learning for object detection at the edge [C ] // Proceedings of the 4th ACM/IEEE Symposium on Edge Computing . New York : ACM , 2019 : 113 - 126 .

LI X , WANG W H , WU L J , et al . Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 21002 - 21012 .

FENG T , WANG M , YUAN H J . Overcoming catastrophic forgetting in incremental object detection via elastic response distillation [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9417 - 9426 .

REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: Towards real-time object detection with region proposal networks [C ] // IEEE Transactions on Pattern Analysis and Machine Intelligence . Piscataway : IEEE , 2017 : 1137 - 1149 .

HAO Y , FU Y W , JIANG Y G , et al . An end-to-end architecture for class-incremental object detection with knowledge distillation [C ] // 2019 IEEE International Conference on Multimedia and Expo . Piscataway : IEEE , 2019 : 1 - 6 .

PENG C , ZHAO K , LOVELL B C . Faster ILOD: Incremental learning for object detectors based on faster RCNN [EB/OL ] . ( 2020-10-07 )[ 2024-05-30 ] . https://arXiv.org/abs/2003.03901 https://arXiv.org/abs/2003.03901 .

ZHANG J T , ZHANG J , GHOSH S , et al . Class-incremental learning via deep model consolidation [C ] // 2020 IEEE Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2020 : 1120 - 1129 .

DONG N , ZHANG Y , DING M , et al . Bridging non co-occurrence with unlabeled in-the-wild data for incremental object detection [C ] // Proceedings of the 35th International Conference on Neural Information Processing Systems . New York : ACM , 2021 : 30492 - 30503 .

JOSEPH K J , RAJASEGARAN J , KHAN S , et al . Incremental object detection via meta-learning [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 12 ): 9209 - 9216 .

ZHAO N , LEE G H . Static-dynamic co-teaching for class-incremental 3D object detection [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 3 ): 3436 - 3445 .

WANG J R , WANG X , SHANG-GUAN Y , et al . Wanderlust: Online continual object detection in the real world [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 10809 - 10818 .

PEREZ-RUA J M , ZHU X T , HOSPEDALES T M , et al . Incremental few-shot object detection [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 13843 - 13852 .

MICHIELI U , ZANUTTIGH P . Incremental learning techniques for semantic segmentation [C ] // 2019 IEEE/CVF International Conference on Computer Vision Workshop . Piscataway : IEEE , 2019 : 3205 - 3212 .

MICHIELI U , ZANUTTIGH P . Knowledge distillation for incremental learning in semantic segmentation [EB/OL ] . ( 2021-01-20 )[ 2024-05-30 ] . https://arXiv.org/abs/1911.03462 https://arXiv.org/abs/1911.03462 .

CERMELLI F , MANCINI M , ROTA BULÒ S , et al . Modeling the background for incremental learning in semantic segmentation [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 9230 - 9239 .

OH Y , BAEK D , HAM B . ALIFE: Adaptive logit regularizer and feature replay for incremental semantic segmentation [J ] . Advances in Neural Information Processing Systems 35. San Diego: NeurIPS , 2022 : 14516 - 14528 .

ZHANG C B , XIAO J W , LIU X L , et al . Representation compensation networks for continual semantic segmentation [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 7043 - 7054 .

MICHIELI U , ZANUTTIGH P . Continual semantic segmentation via repulsion-attraction of sparse and disentangled latent representations [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 1114 - 1124 .

YANG G L , FINI E , XU D , et al . Uncertainty-aware contrastive distillation for incremental semantic segmentation [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 2 ): 2567 - 2581 .

DOUILLARD A , CHEN Y F , DAPOGNY A , et al . PLOP: Learning without forgetting for continual semantic segmentation [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 4039 - 4049 .

MARACANI A , MICHIELI U , TOLDO M , et al . RECALL: Replay-based continual learning in semantic segmentation [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 7006 - 7015 .

CHA S , KIM B , YOO Y , et al . SSUL: Semantic segmentation with unknown label for exemplar-based class-incremental learning [EB/OL ] . ( 2021-11-19 )[ 2024-05-30 ] . https://arXiv.org/abs/2106.11562 https://arXiv.org/abs/2106.11562 .

YAN S P , ZHOU J L , XIE J W , et al . An EM framework for online incremental learning of semantic segmentation [C ] // Proceedings of the 29th ACM International Conference on Multimedia . New York : ACM , 2021 : 3052 - 3060 .

YU L , LIU X L , VAN DE WEIJER J . Self-training for class-incremental semantic segmentation [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2023 , 34 ( 11 ): 9116 - 9127 .

CERMELLI F , FONTANEL D , TAVERA A , et al . Incremental learning in semantic segmentation from image labels [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 4361 - 4371 .

Fortin M P , Chaib-draa B . Continual semantic segmentation leveraging image-level labels and rehearsal [C ] // Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence . California : IJCAI , 2022 : 1268 - 1275 .

ZHANG Z K , GAO G Y , FANG Z Y , et al . Mining unseen classes via regional objectness: A simple baseline for incremental segmentation [EB/OL ] . ( 2023-01-07 )[ 2024-05-30 ] . https://arXiv.org/abs/2211.06866 https://arXiv.org/abs/2211.06866 .

ZHANG Z K , GAO G Y , JIAO J B , et al . CoinSeg: Contrast inter- and intra- class representations for incremental segmentation [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 843 - 853 .

THANH-TUNG H , TRAN T . Catastrophic forgetting and mode collapse in GANs [C ] // 2020 International Joint Conference on Neural Networks . Piscataway : IEEE , 2020 : 1 - 10 .

LIANG K J , LI C Y , WANG G Y , et al . Generative adversarial network training is a continual learning problem [EB/OL ] . ( 2018-11-27 )[ 2024-05-30 ] . https://arXiv.org/abs/1811.11083 https://arXiv.org/abs/1811.11083 .

吴美君 , 杨新 , 潘超凡 , 等 . 自编码器结合持续学习: 现状、挑战与展望 [J ] . 计算机学报 , 2025 , 48 ( 2 ): 317 - 357 .

WU M J , YANG X , PAN C F , et al . Autoencoders combined with continual learning: Development, challenges, and prospects [J ] . Chinese Journal of Computers , 2025 , 48 ( 2 ): 317 - 357 . (in Chinese)

CHEN H T , WANG Y H , XU C , et al . Data-free learning of student networks [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 3513 - 3521 .

BINICI K , TRUNG PHAM N , MITRA T , et al . Preventing catastrophic forgetting and distribution mismatch in knowledge distillation via synthetic data [C ] // 2022 IEEE/CVF Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2022 : 3625 - 3633 .

BINICI K , AGGARWAL S , PHAM N T , et al . Robust and resource-efficient data-free knowledge distillation by generative pseudo replay [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 6 ): 6089 - 6096 .

DO K , LE H , NGUYEN D , et al . Momentum adversarial distillation: Handling large distribution shifts in data-free knowledge distillation [EB/OL ] . ( 2022-09-21 )[ 2024-05-30 ] . https://arXiv.org/abs/2209.10359 https://arXiv.org/abs/2209.10359 .

PATEL G , MOPURI K R , QIU Q . Learning to retain while acquiring: Combating distribution-shift in adversarial data-free knowledge distillation [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 7786 - 7794 .

SEFF A , BEATSON A , SUO D , et al . Continual learning in generative adversarial nets [EB/OL ] . ( 2017-05-23 )[ 2024-05-30 ] . https://arXiv.org/abs/1705.08395 https://arXiv.org/abs/1705.08395 .

YE F , BORS A G . Learning latent representations across multiple data domains using lifelong VAEGAN [C ] // Computer Vision - ECCV 2020 . Cham : Springer , 2020 : 777 - 795 .

ZHAI M Y , CHEN L , MORI G . Hyper-LifelongGAN: Scalable lifelong learning for image conditioned generation [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 2246 - 2255 .

CHEN P , ZHANG Y K , LI Z J , et al . Few-shot incremental learning for label-to-image translation [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 3687 - 3697 .

ACHILLE A , ECCLES T , MATTHEY L , et al . Life-long disentangled representation learning with cross-domain latent homologies [C ] // Proceedings of the 32nd International Conference on Neural Information Processing Systems . New York : ACM , 2018 : 9895 - 9905 .

EGOROV E , KUZINA A , BURNAEV E , et al . Boosting approach for continual learning of VAE [C ] // Advances in Neural Information Processing Systems 34 . San Diego : NeurIPS , 2021 : 17889 - 17901 .

QIU Z H , XU Y , MENG F M , et al . Dual-consistency model inversion for non-exemplar class incremental learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 24025 - 24035 .

ROMBACH R , BLATTMANN A , LORENZ D , et al . High-resolution image synthesis with latent diffusion models [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 10674 - 10685 .

SMITH J S , HSU Y C , ZHANG L Y , et al . Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA [EB/OL ] . ( 2024-05-02 )[ 2024-05-30 ] . https://arXiv.org/abs/2304.06027 https://arXiv.org/abs/2304.06027 .

ALJUNDI R , KELCHTERMANS K , TUYTELAARS T . Task-free continual learning [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 11246 - 11255 .

DE LANGE M , ALJUNDI R , MASANA M , et al . A continual learning survey: Defying forgetting in classification tasks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 7 ): 3366 - 3385 .

LEE S , HA J , ZHANG D S , et al . A neural dirichlet process mixture model for task-free continual learning [EB/OL ] . ( 2020-01-14 )[ 2024-05-30 ] . https://arXiv.org/abs/2001.00689 https://arXiv.org/abs/2001.00689 .

JERFEL G , GRANT E , GRIFFITHS T L , et al . Reconciling meta-learning and continual learning with online mixtures of tasks [EB/OL ] . ( 2019-06-19 )[ 2024-05-30 ] . https://arXiv.org/abs/1812.06080 https://arXiv.org/abs/1812.06080 .

ARDYWIBOWO R , HUO Z , WANG Z , et al . VariGrow: Variational architecture growing for task-agnostic continual learning based on Bayesian novelty [C ] // Proceedings of the 39th International Conference on Machine Learning . Cambridge : PMLR , 2022 : 865 - 877 .

YE F , BORS A G . Task-free continual learning via online discrepancy distance learning [EB/OL ] . ( 2022-10-12 )[ 2024-05-30 ] . https://arXiv.org/abs/2210.06579 https://arXiv.org/abs/2210.06579 .

CHEN H J , CHENG A C , JUAN D C , et al . Mitigating forgetting in online continual learning via instance-aware parameterization [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 17466 - 17477 .

SUN S Y , CALANDRIELLO D , HU H Y , et al . Information-theoretic online memory selection for continual learning [EB/OL ] . ( 2022-04-10 )[ 2024-05-30 ] . https://arXiv.org/abs/2204.04763 https://arXiv.org/abs/2204.04763 .

CHRYSAKIS A , MOENS M F . Online continual learning from imbalanced data [C ] // Proceedings of the 37th International Conference on Machine Learning . New York : ACM , 2020 : 1952 - 1961 .

PRABHU A , TORR P H S , DOKANIA P K . GDumb: A simple approach that questions our progress in continual learning [M ] // Computer Vision - ECCV 2020 . Cham : Springer International Publishing , 2020 : 524 - 540 .

DE LANGE M , TUYTELAARS T . Continual prototype evolution: Learning online from non-stationary data streams [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 8230 - 8239 .

JIN X S , SADHU A , DU J Y , et al . Gradient-based editing of memory examples for online task-free continual learning [EB/OL ] . ( 2021-12-07 )[ 2024-05-30 ] . https://arXiv.org/abs/2006.15294 https://arXiv.org/abs/2006.15294 .

WANG Z Y , SHEN L , FANG L , et al . Improving task-free continual learning by distributionally robust memory evolution [C ] // International Conference on Machine Learning . Cambridge : PMLR , 2022 : 22985 - 22998 .

ALJUNDI R , BELILOVSKY E , TUYTELAARS T , et al . Online continual learning with maximal interfered retrieval [C ] // Advances in Neural Information Processing Systems 32 . San Diego : NeurIPS , 2019 : 1 - 12 .

GU Y N , YANG X , WEI K , et al . Not just selection, but exploration: Online class-incremental continual learning via dual view consistency [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 7432 - 7441 .

YAN H W , WANG L Y , MA K S , et al . Orchestrate latent expertise: Advancing online continual learning with multi-level supervision and reverse self-distillation [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23670 - 23680 .

HAN Y N , LIU J W . Adaptive instance similarity embedding for online continual learning [J ] . Pattern Recognition , 2024 , 149 : 110238 .

KIM B , SEO M , CHOI J . Online continual learning for interactive instruction following agents [EB/OL ] . ( 2024-03-13 )[ 2024-05-30 ] . https://arxiv.org/abs/2403.07548 https://arxiv.org/abs/2403.07548 .

WANG M R , MICHEL N , XIAO L , et al . Improving plasticity in online continual learning via collaborative learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23460 - 23469 .

SEO M , KOH H , JEUNG W , et al . Learning equi-angular representations for online continual learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23933 - 23942 .

HE Y H , CHEN Y J , JIN Y H , et al . DYSON: Dynamic feature space self-organization for online task-free class incremental learning [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23741 - 23751 .

OPENAI , ACHIAM J , ADLER S , et al . GPT-4 technical report [EB/OL ] . ( 2024-03-04 )[ 2024-05-30 ] . https://arxiv.org/abs/2303.08774 https://arxiv.org/abs/2303.08774 .

KIRILLOV A , MINTUN E , RAVI N , et al . Segment anything [EB/OL ] . ( 2023-04-05 )[ 2024-05-30 ] . https://arXiv.org/abs/2304.02643 https://arXiv.org/abs/2304.02643 .

OQUAB M , DARCET T , MOUTAKANNI T , et al . DINOv2: Learning robust visual features without supervision [EB/OL ] . ( 2024-02-02 )[ 2024-05-30 ] . https://arXiv.org/abs/2304.07193 https://arXiv.org/abs/2304.07193 .

HO J , JAIN A , ABBEEL P . Denoising diffusion probabilistic models [EB/OL ] . ( 2020-12-16 )[ 2024-05-30 ] . https://arxiv.org/abs/2006.11239 https://arxiv.org/abs/2006.11239 .

SONG J M , MENG C L , ERMON S . Denoising diffusion implicit models [EB/OL ] . ( 2022-10-05 )[ 2024-05-30 ] . https://arXiv.org/abs/2010.02502 https://arXiv.org/abs/2010.02502 .

CHEN Z , WU J N , WANG W H , et al . Intern VL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 24185 - 24198 .

LIU H , LI C , WU Q , et al . Visual instruction tuning [EB/OL ] . ( 2023-12-11 )[ 2024-05-30 ] . https://arxiv.org/abs/2304.08485 https://arxiv.org/abs/2304.08485 .

HU E J , SHEN Y L , WALLIS P , et al . LoRA: Low-rank adaptation of large language models [EB/OL ] . ( 2021-10-16 )[ 2024-07-02 ] . https://arXiv.org/abs/2106.09685 https://arXiv.org/abs/2106.09685 .

HOULSBY N , GIURGIU A , JASTRZEBSKI S , et al . Parameter-efficient transfer learning for NLP [C ] // Proceedings of the 36th International Conference on Machine Learning . Cambridge : PMLR , 2019 : 2790 - 2799 .

LESTER B , AL-RFOU R , CONSTANT N . The power of scale for parameter-efficient prompt tuning [C ] // Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing . Stroudsburg : ACL , 2021 : 3045 - 3059 .

SMITH J S , KARLINSKY L , GUTTA V , et al . CODA-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 11909 - 11919 .

WISTUBA M , SIVAPRASAD P T , BALLES L , et al . Continual learning with low rank adaptation [EB/OL ] . ( 2023-11-29 )[ 2024-07-02 ] . https://arXiv.org/abs/2311.17601 https://arXiv.org/abs/2311.17601 .

GAO Q K , ZHAO C , SUN Y F , et al . A unified continual learning framework with general parameter-efficient tuning [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 11449 - 11459 .

BÜYÜKAKYÜZ K . OLoRA: Orthonormal low-rank adaptation of large language models [EB/OL ] . ( 2024-11-25 )[ 2025-05-02 ] . https://arXiv.org/abs/2406.01775 https://arXiv.org/abs/2406.01775 .

CHITALE R , VAIDYA A , KANE A , et al . Task arithmetic with LoRA for continual learning [EB/OL ] . ( 2023-11-04 )[ 2024-05-30 ] . https://arxiv.org/abs/2311.02428 https://arxiv.org/abs/2311.02428 .

YU J Z , ZHUGE Y Z , ZHANG L , et al . Boosting continual learning of vision-language models via mixture-of-experts adapters [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 23219 - 23230 .

ZHANG H , LEI Y , GUI L , et al . CPPO: Continual learning for reinforcement learning with human feedback [EB/OL ] . ( 2024-12-21 )[ 2024-06-30 ] . https://arxiv.org/abs/2402.14228 https://arxiv.org/abs/2402.14228 .

PENG B H , TIAN Z T , LIU S , et al . Scalable language model with generalized continual learning [EB/OL ] . ( 2024-04-11 )[ 2024-05-30 ] . https://arXiv.org/abs/2404.07470 https://arXiv.org/abs/2404.07470 .

WANG G Z , XIE Y Q , JIANG Y F , et al . Voyager: An open-ended embodied agent with large language models [EB/OL ] . ( 2023-10-19 )[ 2024-05-30 ] . https://arXiv.org/abs/2305.16291 https://arXiv.org/abs/2305.16291 .

TZIAFAS G , KASAEI H . Lifelong robot library learning: Bootstrapping composable and generalizable skills for embodied control with language models [C ] // 2024 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2024 : 515 - 522 .

MENDEZ-MENDEZ J , KAELBLING L P , LOZANO-PÉREZ T . Embodied lifelong learning for task and motion planning [EB/OL ] . ( 2023-11-06 )[ 2024-05-30 ] . https://arXiv.org/abs/2307.06870 https://arXiv.org/abs/2307.06870 .

于达 . 克服灾难性遗忘的连续学习方法研究 [D ] . 哈尔滨 : 哈尔滨工业大学 , 2024 .

YU D . Research on Continual Learning Method for Overcoming Catastrophic Forgetting [D ] . Harbin : Harbin Institute of Technology , 2024 . (in Chinese)

MU Y , CHEN T X , PENG S J , et al . RoboTwin: Dual-arm robot benchmark with generative digital twins (early version) [EB/OL ] . ( 2024-09-04 )[ 2024-09-30 ] . https://arXiv.org/abs/2409.02920 https://arXiv.org/abs/2409.02920 .

LIU S M , WU L X , LI B G , et al . RDT-1B: A diffusion foundation model for bimanual manipulation [EB/OL ] . ( 2025-03-01 )[ 2025-05-02 ] . https://arXiv.org/abs/2410.07864 https://arXiv.org/abs/2410.07864 .

KIM M J , PERTSCH K , KARAMCHETI S , et al . OpenVLA: An open-source vision-language-action model [EB/OL ] . ( 2024-09-05 )[ 2024-09-30 ] . https://arXiv.org/abs/2406.09246 https://arXiv.org/abs/2406.09246 .

TEAM O M , GHOSH D , WALKE H , et al . Octo: An open-source generalist robot policy [EB/OL ] . ( 2024-05-26 )[ 2024-05-30 ] . https://arXiv.org/abs/2405.12213 https://arXiv.org/abs/2405.12213 .

BROHAN A , BROWN N , CARBAJAL J , et al . RT-1: Robotics transformer for real-world control at scale [EB/OL ] . ( 2023-08-11 )[ 2024-05-30 ] . https://arXiv.org/abs/2212.06817 https://arXiv.org/abs/2212.06817 .

LICĂ M , SHIREKAR O , COLLE B , et al . MindForge: Empowering embodied agents with theory of mind for lifelong cultural learning [EB/OL ] . ( 2024-11-20 )[ 2024-11-30 ] . https://arXiv.org/abs/2411.12977 https://arXiv.org/abs/2411.12977 .

ZHAO Z H , CHAI W H , WANG X , et al . See and think: Embodied agent in virtual environment [M ] // Computer Vision - ECCV 2024 . Cham : Springer Nature Switzerland , 2024 : 187 - 204 .

HE C Y , CHENG S X , QIU Z H , et al . Continual egocentric activity recognition with foreseeable-generalized visual-IMU representations [J ] . IEEE Sensors Journal , 2024 , 24 ( 8 ): 12934 - 12945 .

GRAUMAN K , WESTBURY A , BYRNE E , et al . Ego 4 D: Around the world in 3 000 hours of egocentric video[EB/OL ] . ( 2022-03-11 )[ 2024-05-30 ] . https://arxiv.org/abs/2110.07058 https://arxiv.org/abs/2110.07058 .

SAPOVAL N , AGHAZADEH A , NUTE M G , et al . Current progress and open challenges for applying deep learning across the biosciences [J ] . Nature Communications , 2022 , 13 : 1728 .

WEBB S . Deep Learning for Biology [M ] . California : O’Reilly Media, Inc. , 2018 .

ZENI C , PINSLER R , ZÜGNER D , et al . MatterGen: A generative model for inorganic materials design [EB/OL ] . ( 2024-01-29 )[ 2024-05-30 ] . https://arXiv.org/abs/2312.03687 https://arXiv.org/abs/2312.03687 .

MERCHANT A , BATZNER S , SCHOENHOLZ S S , et al . Scaling deep learning for materials discovery [J ] . Nature , 2023 , 624 ( 7990 ): 80 - 85 .

BI K F , XIE L X , ZHANG H H , et al . Accurate medium-range global weather forecasting with 3D neural networks [J ] . Nature , 2023 , 619 ( 7970 ): 533 - 538 .

JUMPER J , EVANS R , PRITZEL A , et al . Highly accurate protein structure prediction with AlphaFold [J ] . Nature , 2021 , 596 ( 7873 ): 583 - 589 .

SINGH V , SHRIVASTAVA S , SINGH S K , et al . Multi-scale temporal convolutional networks and continual learning based in silico discovery of alternative antibiotics to combat multi-drug resistance [J ] . Expert Systems with Applications , 2023 , 215 : 119295 .

ZHANG Y X , LI X Y , CHEN H M , et al . Continual learning forAbdominal multi-organ andTumor segmentation [C ] // Medical Image Computing and Computer Assisted Intervention - MICCAI 2023 . Cham : Springer , 2023 : 35 - 45 .

BRINGAS S , DUQUE R , LAGE C , et al . CLADSI: Deep continual learning for Alzheimer’s disease stage identification using accelerometer data [J ] . IEEE Journal of Biomedical and Health Informatics , 2024 , 28 ( 6 ): 3401 - 3410 .

QAZI M A , ALMAKKY I , HASHMI A U R , et al . DynaMMo: Dynamic model merging for efficient class incremental learning for medical images [M ] // Medical Image Understanding and Analysis . Cham : Springer Nature Switzerland , 2024 : 245 - 257 .

KUMARI P , CHAUHAN J , BOZORGPOUR A , et al . Continual learning in medical image analysis: A comprehensive review of recent advancements and future prospects [EB/OL ] . ( 2023-12-28 )[ 2024-05-30 ] . https://arXiv.org/abs/2312.17004 https://arXiv.org/abs/2312.17004 .

WEI B Q , CHEN J J , TSENG Y C , et al . Representative data selection for efficient medical incremental learning [J ] . Annual International Conference of the IEEE Engineering in Medicine and Biology Society , 2023 : 1 - 4 .

LI C H , JHA N K . DOCTOR: A multi-disease detection continual learning framework based on wearable medical sensors [J ] . ACM Transactions on Embedded Computing Systems , 2024 , 23 ( 5 ): 1 - 33 .

ZHU X Y , JIANG Z G , WU K , et al . Lifelong histopathology whole slide image retrieval via distance consistency rehearsal [M ] // Medical Image Computing and Computer Assisted Intervention - MICCAI 2024 . Cham : Springer Nature Switzerland , 2024 : 274 - 284 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于神经网络的图像风格迁移算法综述

DRHA-UIE：基于双重残差混合注意力模块的水下图像增强方法

基于无标签视频数据的深度预测学习方法综述

基于深度学习的通用目标检测研究综述