基于主动学习的图像分类技术：现状与未来

刘颖; 庞羽良; 张伟东; 李大湘; 许志杰

doi:10.12263/DZXB.20230397

您当前的位置：

首页 >

文章列表页 >

基于主动学习的图像分类技术：现状与未来

综述评论 | 更新时间：2025-12-08

- 基于主动学习的图像分类技术：现状与未来
- Active Learning-Based Image Classification Technology: Status and Future
- 电子学报 2023年51卷第10期页码：2960-2984
- 作者机构：
  
  1.西安邮电大学图像与信息处理研究所，陕西西安 710121
  2.无线通信与信息处理技术国际联合研究中心，陕西西安 710121
  3.英国哈德斯菲尔德大学，西约克郡 HD13DH
- 作者简介：
  
  [ "刘颖女，2007年获得澳大利亚莫纳什大学博士学位．现为西安邮电大学教授、硕士生导师、图像与信息处理研究所成员、无线通信与信息处理技术国际联合研究中心成员.主要研究方向为图像理解与识别.中国电子学会会员编号：E190091672M." ]
  [ "庞羽良（通讯作者）男，2021年西安邮电大学通信与信息工程学院硕士研究生.主要研究方向为主动学习图像分类.E-mail: yuliangpang0315@163.com" ]
  [ "张伟东男，生物医学工程专业博士，副教授，硕士生导师.现为西安邮电大学图像与信息处理研究所成员、无线通信与信息处理技术国际联合研究中心成员.主要研究方向为室内场景理解.E-mail: chluzhre@126.com" ]
  [ "李大湘男，副教授，硕士生导师.现为西安邮电大学图像与信息处理研究所成员、无线通信与信息处理技术国际联合研究中心成员.主要研究方向为图像分类识别.E-mail: www.ldx@163.com" ]
  [ "许志杰男，现任英国哈德斯菲尔德大学（University of Huddersfield）工程与计算机学院教授，视觉计算与虚拟技术研究中心主任，无线通信与信息处理技术国际联合研究中心成员.主要研究方向为图形图像处理.E-mail: z.xu@hud.ac.uk" ]
- 基金信息：
  
  国家自然科学基金青年项目(62106195)
- DOI：10.12263/DZXB.20230397
  中图分类号： TP751;TP391
- 收稿：2023-05-04，
  
  修回：2023-08-23，
  
  纸质出版：2023-10-25
- 稿件说明：
移动端阅览
刘颖,庞羽良,张伟东等.基于主动学习的图像分类技术：现状与未来[J].电子学报,2023,51(10):2960-2984.

LIU Ying,PANG Yu-liang,ZHANG Wei-dong,et al.Active Learning-Based Image Classification Technology: Status and Future[J].ACTA ELECTRONICA SINICA,2023,51(10):2960-2984.
刘颖,庞羽良,张伟东等.基于主动学习的图像分类技术：现状与未来[J].电子学报,2023,51(10):2960-2984. DOI： 10.12263/DZXB.20230397.

LIU Ying,PANG Yu-liang,ZHANG Wei-dong,et al.Active Learning-Based Image Classification Technology: Status and Future[J].ACTA ELECTRONICA SINICA,2023,51(10):2960-2984. DOI： 10.12263/DZXB.20230397.

摘要

图像分类作为计算机视觉领域中的重要研究方向之一，应用领域非常广泛.基于深度学习的图像分类技术取得的成功，依赖大量的已标注数据，然而数据的标注成本往往是昂贵的.主动学习作为一种机器学习方法，旨在以尽可能少的高质量标注数据达到期望的模型性能，缓解监督学习任务中存在的标注成本高、标注信息难以大量获取的问题.主动学习图像分类算法根据样本选择策略，从未标记样本数据集合中选择出信息量丰富，对分类模型训练贡献更高的样本进行标注，以更新已标注训练数据池，如此循环直至满足给定的停止条件或模型标注预算耗尽.本文对近年来提出的主动学习图像分类算法进行了详细综述，并根据所用样本数据处理及模型优化方案，将现有算法分为三类：基于数据增强的算法，包括利用图像增广来扩充训练数据，或者根据图像特征插值后的差异性来选择高质量的训练数据；基于数据分布信息的算法，根据数据分布的特点来优化样本选择策略；优化模型预测的算法，包括优化获取和利用深度模型预测信息的方法、基于生成对抗网络和强化学习来优化预测模型的结构，以及基于Transformer结构提升模型预测性能，以确保模型预测结果的可靠性.此外，本文还对各类主动学习图像分类算法下的重要学术工作进行了实验对比，并对各算法在不同规模数据集上的性能和适应性进行了分析.另外，本文探讨了主动学习图像分类技术所面临的挑战，并指出了未来研究的方向.

Abstract

As one of the important research directions in the field of computer vision

image classification has a wide range of applications. The success of deep learning-based image classification techniques depends on a large amount of annotated data. However

the cost of data annotation is often expensive. Active learning is a machine learning method that aims to achieve the expected model performance with as few high-quality annotated data as possible

and it can alleviate the problem of high annotation costs and difficulty in obtaining a large amount of annotation information in supervised learning tasks. Based on a sample selection strategy

active learning for image classification selects samples from the unlabeled dataset which are informative and thus contribute more to the training of the classification model

in order to update the annotated training data pool. This process is repeated until a given stopping condition is met or the model annotation budget is exhausted. This paper provides a comprehensive survey of the active learning image classification algorithms published in recent years. According the strategies applied in sample data processing and model structure optimization

existing algorithms are classified into three categories: algorithms based on data augmentation

including those using image augmentation to expand the scale of training data or using the differences in image feature interpolation to select high-quality training data; algorithms based on data distribution information

which optimize sample selection strategies based on the characteristics of data distribution; algorithms for optimizing model predictions

including methods for optimizing the acquisition and utilization of deep model prediction information

improving the predictive model structure through the use of generative adversarial networks and reinforcement learning

as well as enhancing model prediction performance based on the Transformer architecture to ensure the reliability of model predictions. In addition

this paper also conducts experimental comparisons on important academic work under various types of active learning image classification algorithms

and analyzes the performance and adaptability of each algorithm on datasets of different scales. Furthermore

this paper discusses the challenges faced by active learning image classification technology and points out future research directions.

关键词

Keywords

references

LECUN Y , BENGIO Y , HINTON G . Deep learning [J]. Nature , 2015 , 521 ( 7553 ): 436 - 444 .

GU J X , WANG Z H , KUEN J , et al . Recent advances in convolutional neural networks [J]. Pattern Recognition , 2018 , 77 : 354 - 377 .

EL-SAWY A , EL-BAKRY H , LOEY M . CNN for handwritten Arabic digits recognition based on LeNet-5 [C]// International Conference on Advanced Intelligent Systems and Informatics . Cham : Springer , 2017 : 566 - 575 .

BALLESTER P , ARAUJO R M . On the performance of GoogLeNet and AlexNet applied to sketches [C]// Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence . New York : ACM , 2016 : 1124 - 1128 .

KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL]. ( 2014-09-04 )[ 2023-05-04 ]. https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .

KOTHAWADE S , SAVARKAR A , IYER V , et al . CLINICAL: Targeted active learning for imbalanced medical image classification [C]// Workshop on Medical Image Learning with Limited and Noisy Data . Cham : Springer , 2022 : 119 - 129 .

TUIA D , VOLPI M , COPA L , et al . A survey of active learning algorithms for supervised remote sensing image classification [J]. IEEE Journal of Selected Topics in Signal Processing , 2011 , 5 ( 3 ): 606 - 617 .

SETTLES B . Active learning literature survey [EB/OL]. ( 2010-01-26 )[ 2023-05-04 ]. http://digital.library.wisc.edu/1793/60660 http://digital.library.wisc.edu/1793/60660 .

BELUCH W H , GENEWEIN T , NURNBERGER A , et al . The power of ensembles for active learning in image classification [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 9368 - 9377 .

MACKOWIAK R , LENZ P , GHORI O , et al . CEREALS - cost-effective REgion-based active learning for semantic segmentation [EB/OL]. ( 2018-10-23 )[ 2023-05-04 ]. https://arxiv.org/abs/1810.09726 https://arxiv.org/abs/1810.09726 .

BRUST C A , KÄDING C , DENZLER J . Active learning for deep object detection [EB/OL]. ( 2018-09-26 )[ 2023-05-04 ]. https://arxiv.org/abs/1809.09875 https://arxiv.org/abs/1809.09875 .

SENER O , SAVARESE S . Active learning for convolutional neural networks: A core-set approach [EB/OL]. ( 2017-08-01 )[ 2023-05-04 ]. https://arxiv.org/abs/1708.00489 https://arxiv.org/abs/1708.00489 .

GAL Y , ISLAM R , GHAHRAMANI Z . Deep Bayesian active learning with image data [C]// Proceedings of the 34th International Conference on Machine Learning . New York : ACM , 2017 : 1183 - 1192 .

SUN L , GONG Y H . Active learning for image classification: A deep reinforcement learning approach [C]// 2019 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI) . Piscataway : IEEE , 2019 : 71 - 76 .

ZHU J J , BENTO J . Generative adversarial active learning [EB/OL]. ( 2017-02-25 )[ 2023-05-04 ]. https://arxiv.org/abs/1702.07956 https://arxiv.org/abs/1702.07956 .

MAHAPATRA D , BOZORGTABAR B , THIRAN J P , et al . Efficient active learning for image classification and segmentation using a sample selection and conditional generative adversarial network [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham : Springer , 2018 : 580 - 588 .

BENGAR J Z , VAN DE WEIJER J , FUENTES L L , et al . Class-balanced active learning for image classification [C]// 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) . Piscataway : IEEE , 2022 : 3707 - 3716 .

LIU P , WANG L Z , RANJAN R , et al . A survey on active deep learning: From model driven to data driven [J]. ACM Computing Surveys , 54 ( 10 s): 221.

REN P Z , XIAO Y , CHANG X J , et al . A survey of deep active learning [J]. ACM Computing Surveys , 54 ( 9 ): 180 .

ZHAN X Y , WANG Q Z , HUANG K H , et al . A comparative survey of deep active learning [EB/OL]. ( 2022-03-25 )[ 2023-05-04 ]. https://arxiv.org/abs/2203.13450 https://arxiv.org/abs/2203.13450 .

WANG M , MIN F , ZHANG Z H , et al . Active learning through density clustering [J]. Expert Systems With Applications , 2017 , 85 : 305 - 317 .

GORRIZ M , CARLIER A , FAURE E , et al . Cost-effective active learning for melanoma segmentation [EB/OL]. ( 2017-11-24 )[ 2023-05-04 ]. https://arxiv.org/abs/1711.09168 https://arxiv.org/abs/1711.09168 .

ZHDANOV F . Diverse mini-batch active learning [EB/OL]. ( 2019-01-17 )[ 2023-05-04 ]. https://arxiv.org/abs/1901.05954 https://arxiv.org/abs/1901.05954 .

NGUYEN H T , SMEULDERS A . Active learning using pre-clustering [C]// Proceedings of the Twenty-First International Conference on Machine Learning . New York : ACM , 2004 , DOI: 10.1145/1015330.1015349 http://dx.doi.org/10.1145/1015330.1015349 .

YANG L , ZHANG Y Z , CHEN J X , et al . Suggestive annotation: A deep active learning framework for biomedical image segmentation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham : Springer , 2017 : 399 - 407 .

NÚÑEZ J A , CINCOTTA P M , WACHLIN F C . Information entropy [C]// Chaos in Gravitational N-Body Systems . Dordrecht : Springer , 1996 : 43 - 53 .

FENG Y , SHI Q K , GAO X Y , et al . DeepGini: Prioritizing massive tests to enhance the robustness of deep neural networks [C]// Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis . New York : ACM , 2020 : 177 - 188 .

ZHANG X C , CHEN F L , LU C T , et al . Mitigating uncertainty in document classification [EB/OL]. ( 2019-07-17 )[ 2023-05-04 ]. https://arxiv.org/abs/1907.07590 https://arxiv.org/abs/1907.07590 .

JAIN P , KAPOOR A . Active learning for large multi-class problems [C]// 2009 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2009 : 762 - 769 .

ZHOU J , SUN S L . Improved margin sampling for active learning [C]// Chinese Conference on Pattern Recognition . Berlin : Springer , 2014 : 120 - 129 .

SHEN W J , LI Y H , CHEN L , et al . Multiple-boundary clustering and prioritization to promote neural network retraining [C]// Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering . New York : ACM , 2020 : 410 - 422 .

YOU X G , WANG R X , TAO D C . Diverse expected gradient active learning for relative attributes [J]. IEEE Transactions on Image Processing , 2014 , 23 ( 7 ): 3203 - 3217 .

GUO H S , WANG W J . An active learning-based SVM multi-class classification model [J]. Pattern Recognition , 2015 , 48 ( 5 ): 1577 - 1597 .

LENG Y , QI G H , XU X Y , et al . A new SVM active learning algorithm based on KNN [J]. Advanced Materials Research , 2014 , 926 / 927 / 928 / 929 / 930 : 2906 - 2909 .

YAN L , XU X Y , SUN C L , et al . A SVM active learning method based on confidence, KNN and diversity [C]// 2015 IEEE International Conference on Multimedia and Expo (ICME) . Piscataway : IEEE , 2015 : 1 - 6 .

YE C , WU J , SHENG V S , et al . Multi-label active learning with label correlation for image classification [C]// 2015 IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2015 : 3437 - 3441 .

FENG C , LIU M Y , KAO C C , et al . Deep active learning for civil infrastructure defect detection and classification [C]// Computing in Civil Engineering 2017 . Reston : American Society of Civil Engineers , 2017 : 298 - 306 .

AHMED M U , WOO K J , HYEON K Y , et al . Wild facial expression recognition based on incremental active learning [J]. Cognitive Systems Research , 2018 , 52 : 212 - 222 .

HAUT J M , PAOLETTI M E , PLAZA J , et al . Active learning with convolutional neural networks for hyperspectral image classification using a new Bayesian approach [J]. IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 11 ): 6440 - 6461 .

SAYANTAN G , KIEN P T , KADAMBARI K V . Classification of ECG beats using deep belief network and active learning [J]. Medical & Biological Engineering & Computing , 2018 , 56 ( 10 ): 1887 - 1898 .

SHORTEN C , KHOSHGOFTAAR T M . A survey on image data augmentation for deep learning [J]. Journal of Big Data , 2019 , 6 ( 1 ): 1 - 48 .

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J]. Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 .

TRAN T , DO T T , REID I , et al . Bayesian generative active deep learning [C]// Proceedings of the 36th International Conference on Machine Learning . Long Beach : ICML , 2019 : 6295 - 6304 .

PU Y C , GAN Z , HENAO R , et al . Variational autoencoder for deep learning of images, labels and captions [C]// Proceedings of the 30th International Conference on Neural Information Processing Systems . New York : Curran Associates Inc. , 2016 : 2360 - 2368 .

SINHA S , EBRAHIMI S , DARRELL T . Variational adversarial active learning [C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2020 : 5971 - 5980 .

MOTTAGHI A , YEUNG S . Adversarial representation active learning [EB/OL]. ( 2019-12-20 )[ 2023-05-04 ]. https://arxiv.org/abs/1912.09720 https://arxiv.org/abs/1912.09720 .

KIM Y-Y , SONG K , JANG J , I-C MOON . Lada: Look-ahead data acquisition via augmentation for deep active learning [C]// Advances in Neural Information Processing Systems , Virtual Conference : NIPS Fundation , 2021 : 22919 - 22930 .

GONG C Y , WANG D L , LI M , et al . KeepAugment: A simple information-preserving data augmentation approach [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 1055 - 1064 .

DIPU KABIR H M , ABDAR M , KHOSRAVI A , et al . SpinalNet: Deep neural network with gradual input [J]. IEEE Transactions on Artificial Intelligence , 2022 . DOI: 10.1109/TAI.2022.3185179 http://dx.doi.org/10.1109/TAI.2022.3185179 .

QIAN Y M , HU H , TAN T . Data augmentation using generative adversarial networks for robust speech recognition [J]. Speech Communication , 2019 , 114 : 1 - 9 .

ZHANG H Y , CISSE M , DAUPHIN Y N , et al . Mixup: Beyond empirical risk minimization [EB/OL]. ( 2017-10-25 )[ 2023-05-04 ]. https://arxiv.org/abs/1710.09412 https://arxiv.org/abs/1710.09412 .

VENKATARAMANAN S , KIJAK E , AMSALEG L , et al . AlignMixup: Improving representations by interpolating aligned features [C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 19152 - 19161 .

MA Y , LU S X , XU E Y , et al . Combining active learning and data augmentation for image classification [C]// Proceedings of the 3rd International Conference on Big Data Technologies . New York : ACM , 2020 : 58 - 62 .

WANG D D , LI Y D , WANG L Q , et al . Neural networks are more productive teachers than human raters: Active mixup for data-efficient knowledge distillation from a blackbox model [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 1495 - 1504 .

PARVANEH A , ABBASNEJAD E , TENEY D , et al . Active learning by feature mixing [C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 12227 - 12236 .

KIM J H , CHOO W , JEONG H , et al . Co-mixup: Saliency guided joint mixup with supermodular diversity [EB/OL]. ( 2021-02-05 )[ 2023-05-04 ]. https://arxiv.org/abs/2102.03065 https://arxiv.org/abs/2102.03065 .

LI X , GUO Y H . Adaptive active learning for image classification [C]// 2013 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2013 : 859 - 866 .

LIU P , ZHANG H , EOM K B . Active deep learning for classification of hyperspectral images [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2017 , 10 ( 2 ): 712 - 724 .

YANG Y Z , LOOG M . Single shot active learning using pseudo annotators [J]. Pattern Recognition , 2019 , 89 : 22 - 31 .

GISSIN D , SHALEV-SHWARTZ S . Discriminative active learning [EB/OL]. ( 2019-07-15 )[ 2023-05-04 ]. https://arxiv.org/abs/1907.06347 https://arxiv.org/abs/1907.06347 .

CARAMALAU R , BHATTARAI B , KIM T K . Sequential graph convolutional network for active learning [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 9578 - 9587 .

ZHANG S , TONG H H , XU J J , et al . Graph convolutional networks: A comprehensive review [J]. Computational Social Networks , 2019 , 6 ( 1 ): 1 - 23 .

AGARWAL S , ARORA H , ANAND S , et al . Contextual diversity for active learning [C]// European Conference on Computer Vision . Cham : Springer , 2020 : 137 - 153 .

WANG X , WANG S , LIANG X X , et al . Deep reinforcement learning: A survey [J]. IEEE Transactions on Neural Networks and Learning Systems , 2022 , DOI: 10.1109/TNNLS.2022.3207346 http://dx.doi.org/10.1109/TNNLS.2022.3207346 .

WAN F , YUAN T N , FU M Y , et al . Nearest neighbor classifier embedded network for active learning [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 11 ): 10041 - 10048 .

FROSST N , PAPERNOT N , HINTON G . Analyzing and improving representations with the soft nearest neighbor loss [C]// Proceedings of the 36 th International Conference on Machine Learning . Long Beach : ICML , 2019 : 2012 - 2020 .

OUYANG W L , WANG X G , ZHANG C , et al . Factors in finetuning deep model for object detection with long-tail distribution [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 864 - 873 .

CHOI J , YI K M , KIM J , et al . VaB-AL: Incorporating class imbalance and difficulty with variational Bayes for active learning [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 6745 - 6754 .

OVADIA Y , FERTIG E , REN J J , et al . Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift [C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems . New York : Curran Associates Inc. , 2019 : 14003 - 14014 .

GUO Y J , HU Q , CORDY M , et al . Robust active learning: Sample-efficient training of robust deep learning models [C]// Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI . New York : ACM , 2022 : 41 - 42 .

WANG K Z , ZHANG D Y , LI Y , et al . Cost-effective active learning for deep image classification [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2017 , 27 ( 12 ): 2591 - 2600 .

YOO D , KWEON I S . Learning loss for active learning [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 93 - 102 .

HUANG S Y , WANG T Y , XIONG H Y , et al . Semi-supervised active learning with temporal output discrepancy [C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2022 : 3427 - 3436 .

MEHTA R , SHUI C J , NICHYPORUK B , et al . Information gain sampling for active learning in medical image classification [C]// International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging . Cham : Springer , 2022 : 135 - 145 .

HEMMER P , KÜHL N , SCHÖFFER J . DEAL: Deep evidential active learning for image classification [M]// Deep Learning Applications , Volume 3 . Singapore : Springer , 2022: 171 - 192 .

TEH Y W . Dirichlet process [M]// Encyclopedia of Machine Learning . New York : Springer , 2010 : 280 - 287 .

WU Z H , PAN S R , CHEN F W , et al . A comprehensive survey on graph neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems , 2021 , 32 ( 1 ): 4 - 24 .

KALUZA P , VINGRON M , MIKHAILOV A S . Self-correcting networks: Function, robustness, and motif distributions in biological signal processing [J]. Chaos , 2008 , 18 ( 2 ): 026113 .

ILIĆ V , TADIĆ J . Active learning using a self-correcting neural network (ALSCN) [J]. Applied Intelligence , 2022 , 52 ( 2 ): 1956 - 1968 .

BERNARD S , BAS P , KLEIN J , et al . Explicit optimization of min max steganographic game [J]. IEEE Transactions on Information Forensics and Security , 2021 , 16 : 812 - 823 .

KIM K , PARK D , KIM K I , et al . Task-aware variational adversarial active learning [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 8162 - 8171 .

ZHANG B C , LI L , YANG S J , et al . State-relabeling adversarial active learning [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 8753 - 8762 .

WANG S , LI Y X , MA K , et al . Dual adversarial network for deep active learning [C]// European Conference on Computer Vision . Cham : Springer , 2020 : 680 - 696 .

MAYER C , TIMOFTE R . Adversarial sampling for active learning [C]// 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) . Piscataway : IEEE , 2020 : 3060 - 3068 .

MIYATO T , KATAOKA T , KOYAMA M , et al . Spectral normalization for generative adversarial networks [EB/OL]. ( 2018-02-16 )[ 2023-05-04 ]. https://arxiv.org/abs/1802.05957 https://arxiv.org/abs/1802.05957 .

FANG M , LI Y , COHN T . Learning how to active learn: A deep reinforcement learning approach [EB/OL]. ( 2017-08-08 )[ 2023-05-04 ]. https://arxiv.org/abs/1708.02383 https://arxiv.org/abs/1708.02383 .

HAUSSMANN M , HAMPRECHT F A , KANDEMIR M . Deep active learning with adaptive acquisition [EB/OL]. ( 2019-06-27 )[ 2023-05-04 ]. https://arxiv.org/abs/1906.11471 https://arxiv.org/abs/1906.11471 .

LIU Z M , WANG J Y , GONG S G , et al . Deep reinforcement active learning for human-in-the-loop person re-identification [C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2020 : 6121 - 6130 .

WANG J W , YAN Y G , ZHANG Y B , et al . Deep reinforcement active learning for medical image classification [C]// Medical Image Computing and Computer Assisted Intervention - MICCAI 2020 . Cham : Springer , 2020 : 33 - 42 .

CUI Y L , HIREMATH S K , PLOETZ T . Reinforcement learning based online active learning for human activity recognition [C]// Proceedings of the 2022 ACM International Symposium on Wearable Computers . New York : ACM , 2022 : 23 - 27 .

ZHANG Y H , TONG H H , XIA Y L , et al . Batch active learning with graph neural networks via multi-agent deep reinforcement learning [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 8 ): 9118 - 9126 .

CHEN S Y , WANG R , LU J . A meta-framework for multi-label active learning based on deep reinforcement learning [J]. Neural Networks , 2023 , 162 : 258 - 270 .

TOUVRON H , CORD M , DOUZE M , et al . Training data-efficient image transformers & distillation through attention [EB/OL]. ( 2020-12-23 )[ 2023-05-04 ]. https://arxiv.org/abs/2012.12877 https://arxiv.org/abs/2012.12877 .

CHEN C F R , FAN Q F , PANDA R . CrossViT: cross-attention multi-scale vision transformer for image classification [C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2022 : 347 - 356 .

XIE Y C , TOMIZUKA M , ZHAN W . Towards general and efficient active learning [EB/OL]. ( 2021-10-15 )[ 2023-05-04 ]. https://arxiv.org/abs/2112.07963 https://arxiv.org/abs/2112.07963 .

CARAMALAU R , BHATTARAI B , KIM T K . Visual transformer for task-aware active learning [EB/OL]. ( 2021-06-07 )[ 2023-05-04 ]. https://arxiv.org/abs/2106.03801 https://arxiv.org/abs/2106.03801 .

KHAN A , HAQ I U , HUSSAIN T , et al . Pmal: A proxy model active learning approach for vision based industrial applications [J]. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) , 2022 , 18 ( 2 s): 123.

TANG S G , YU X Y , CHEANG C F , et al . Transformer-based multi-task learning for classification and segmentation of gastrointestinal tract endoscopic images [J]. Computers in Biology and Medicine , 2023 , 157 : 106723 .

XIAO H , RASUL K , VOLLGRAF R . Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms [EB/OL]. ( 2017-08-25 )[ 2023-05-04 ]. https://arxiv.org/abs/1708.07747 https://arxiv.org/abs/1708.07747 .

DOON R , KUMAR RAWAT T , GAUTAM S . Cifar-10 classification using deep convolutional neural network [C]// 2018 IEEE Punecon . Piscataway : IEEE , 2019 : 1 - 5 .

KRIZHEVSKY A . Learning Multiple Layers of Features From Tiny Images [D]. Toronto : University of Toronto , 2009 .

NETZER Y , WANG T , COATES A , et al . The Street View House Numbers (SVHN) Dataset [D/OL]. [ 2023-05-04 ]. http://ufldl.stanford.edu/housenumbers/ http://ufldl.stanford.edu/housenumbers/ .

FOLMSBEE J , LIU X L , BRANDWEIN-WEBER M , et al . Active deep learning: Improved training efficiency of convolutional neural networks for tissue classification in oral cavity cancer [C]// 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) . Piscataway : IEEE , 2018 : 770 - 773 .

ALAHMARI S S , GOLDGOF D , HALL L O , et al . Automatic cell counting using active deep learning and unbiased stereology [C]// 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC) . Piscataway : IEEE , 2019 : 1708 - 1713 .

SPANHOL F A , OLIVEIRA L S , PETITJEAN C , et al . A dataset for breast cancer histopathological image classification [J]. IEEE Transactions on Biomedical Engineering , 2016 , 63 ( 7 ): 1455 - 1462 .

DENG C , XUE Y M , LIU X L , et al . Active transfer learning network: A unified deep joint spectral-spatial feature learning model for hyperspectral image classification [J]. IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 3 ): 1741 - 1754 .

LIN J Z , ZHAO L , LI S Y , et al . Active-learning-incorporated deep transfer learning for hyperspectral image classification [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2018 , 11 ( 11 ): 4048 - 4062 .

LIU Y , LEI Y B , RASHID S F . Graph convolution network with node feature optimization using cross attention for few-shot learning [C]// Proceedings of the 2nd ACM International Conference on Multimedia in Asia . New York : ACM , 2021 : 1 - 7 .

DENG X Y , LIU Q , DENG Y , et al . An improved method to construct basic probability assignment based on the confusion matrix for classification problem [J]. Information Sciences , 2016 , 340/341 : 250 - 261 .

DASGUPTA S , HSU D J , MONTELEONI C . A general agnostic active learning algorithm [C]// Proceedings of the 20th International Conference on Neural Information Processing Systems . New York : Curran Associates Inc. , 2007 : 353 - 360 .

COHN D A , GHAHRAMANI Z , JORDAN M I . Active learning with mixture models [M]// Multiple Model Approaches to Modelling and Control . Boca Raton : CRC Press , 1997 : 167 - 183 .

DALMAZ O , YURT M , ÇUKUR T . ResViT: Residual vision transformers for multi-modal medical image synthesis [EB/OL]. ( 2021-06-30 )[ 2023-05-04 ]. https://arxiv.org/abs/2106.16031 https://arxiv.org/abs/2106.16031 .

MEINHARDT T , KIRILLOV A , LEAL-TAIXÉ L , et al . TrackFormer: Multi-object tracking with transformers [C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 8834 - 8844 .

CARION N , MASSA F , SYNNAEVE G , et al . End-to-end object detection with transformers [C]// European Conference on Computer Vision . Cham : Springer , 2020 : 213 - 229 .

DEY D , CHATTERJEE B , CHAKRAVORTI S , et al . Rough-granular approach for impulse fault classification of transformers using cross-wavelet transform [J]. IEEE Transactions on Dielectrics and Electrical Insulation , 2008 , 15 ( 5 ): 1297 - 1304 .

ZHENG S X , LU J C , ZHAO H S , et al . Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 6877 - 6886 .

LI M , LIU J , ZHENG C , et al . Exploiting multi-view part-wise correlation via an efficient transformer for vehicle re-identification [J]. IEEE Transactions on Multimedia , 2023 , 25 : 919 - 929 .

DOSOVITSKIY A , BEYER L , KOLESNIKOV A , et al . An image is worth 16 x 16 words: Transformers for image recognition at scale[EB/OL]. ( 2020-10-22 )[ 2023-05-04 ]. https://arxiv.org/abs/2010.11929 https://arxiv.org/abs/2010.11929 .

SRINIVAS A , LIN T Y , PARMAR N , et al . Bottleneck transformers for visual recognition [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 16514 - 16524 .

LIU Z , LIN Y T , CAO Y , et al . Swin transformer: Hierarchical vision transformer using shifted windows [C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2022 : 9992 - 10002 .

FINN C , ABBEEL P , LEVINE S . Model-agnostic meta-learning for fast adaptation of deep networks [C]// Proceedings of the 34th International Conference on Machine Learning - Volume 70 . New York : ACM , 2017 : 1126 - 1135 .

VELIČKOVIĆ P , CUCURULL G , CASANOVA A , et al . Graph attention networks [EB/OL]. ( 2017-10-30 )[ 2023-05-04 ]. https://arxiv.org/abs/1710.10903 https://arxiv.org/abs/1710.10903 .

ZHOU J , CUI G Q , HU S D , et al . Graph neural networks: A review of methods and applications [J]. AI Open , 2020 , 1 : 57 - 81 .

WU Y , CHEN Y P , WANG L J , et al . Large scale incremental learning [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 374 - 382 .

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

背景感知机制的图像分类网络

基于坐标重要性池化和解耦类别对齐蒸馏的图像分类算法

基于特征异常检测与伪标签回归的无监督对抗域适应

基于图表征知识蒸馏的图像分类方法

基于联邦学习的主动半监督短文本分类方法