SDDA：无监督的风格和分布域适应夜间语义分割方法

雷晓春; 吴炜林; 江泽涛; 朱文才; 刘颖健; 陈冬梅; 吴思琦

doi:10.12263/DZXB.20251221

您当前的位置：

首页 >

文章列表页 >

SDDA：无监督的风格和分布域适应夜间语义分割方法

学术论文 | 更新时间：2026-06-22

- SDDA：无监督的风格和分布域适应夜间语义分割方法
- SDDA: Unsupervised Style and Distribution Domain Adaptation Method for Nighttime Semantic Segmentation
- 电子学报 2026年54卷第1期页码：433-450
- 作者机构：
  
  1.桂林电子科技大学计算机与信息安全学院，广西桂林 541004
  2.广西图像图形与智能处理重点实验室，广西桂林 541004
  3.西北工业大学计算机学院，陕西西安 710072
- 作者简介：
  
  雷晓春女，1981年2月出生于广西壮族自治区南宁市。现为桂林电子科技大学计算机与信息安全学院博士、高级实验师。主要研究方向为图像处理、计算机视觉、人工智能。E-mail: glleixiaochun@qq.com
  吴炜林男，2000年9月出生于广西壮族自治区北海市。现为桂林电子科技大学计算机与信息安全学院硕士研究生。主要研究方向为图像处理、计算机视觉。E-mail: 23032303013@mails.guet.edu.cn
  江泽涛男，1961年3月出生于江西省九江市。现为桂林电子科技大学计算机与信息安全学院博士、教授。主要研究方向为图像处理、计算机视觉、人工智能。E-mail: zetaojiang@126.com
  朱文才男，1999年11月出生于河北省沧州市。现为西北工业大学计算机学院博士研究生。主要研究方向为图像处理、计算机视觉。E-mail: zwc33@mail.nwpu.edu.cn
  刘颖健男，2000年3月出生于江西省宜春市。现为桂林电子科技大学计算机与信息安全学院硕士研究生。主要研究方向为图像处理、计算机视觉。E-mail: 2547051960@qq.com
  陈冬梅女，2000年5月出生于广西壮族自治区钦州市。现为桂林电子科技大学计算机与信息安全学院硕士研究生。主要研究方向为图像处理、计算机视觉。E-mail: 23032303002@mails.guet.edu.cn
  吴思琦男，2004年3月出生于湖北省孝感市。现为桂林电子科技大学计算机与信息安全学院本科生。主要研究方向为计算机视觉与计算生物学。E-mail: 2201610118@mails.guet.edu.cn
- 基金信息：
  
  国家自然科学基金(62473105);广西自然科学基金面上项目(2025JJA170088);广西图像图形智能处理重点实验项目(GIIP2305);桂林电子科技大学研究生教育创新计划项目(2025YCXS051;2024YCXS035)
- DOI：10.12263/DZXB.20251221
  中图分类号： TP391;
- 收稿：2026-01-12，
  
  录用：2026-01-19，
  
  纸质出版：2026-01-25
- 稿件说明：
移动端阅览
雷晓春, 吴炜林, 江泽涛, 等. SDDA：无监督的风格和分布域适应夜间语义分割方法[J]. 电子学报, 2026, 54(01): 433-450.

LEI Xiaochun, WU Weilin, JIANG Zetao, et al. SDDA: Unsupervised Style and Distribution Domain Adaptation Method for Nighttime Semantic Segmentation[J]. Acta Electronica Sinica, 2026, 54(01): 433-450.
雷晓春, 吴炜林, 江泽涛, 等. SDDA：无监督的风格和分布域适应夜间语义分割方法[J]. 电子学报, 2026, 54(01): 433-450. DOI：10.12263/DZXB.20251221

LEI Xiaochun, WU Weilin, JIANG Zetao, et al. SDDA: Unsupervised Style and Distribution Domain Adaptation Method for Nighttime Semantic Segmentation[J]. Acta Electronica Sinica, 2026, 54(01): 433-450. DOI：10.12263/DZXB.20251221

摘要

语义分割在自动驾驶、医工交叉和安防监控等多种实际应用中发挥着重要作用，但夜间语义分割仍然是未解决的一道难题。由于夜间光照不足，获取的图像细节模糊不清，导致数据集标注困难，因而人们首选探索无监督域适应夜间语义分割方法。虽然取得了一些进展，但仍然存在数据集跨域幅度太大难以直接进行域适应的问题，导致夜间场景的语义分割效果不理想。针对这个问题，本文提出了一种风格和分布域适应（Style and Distribution Domain Adaptation，SDDA）的无监督夜间语义分割方法，将夜间语义分割任务的域适应分为风格域适应和分布域适应，以此降低夜间分割任务的难度。将性能更优秀的Mamba架构模型引入无监督域适应夜间语义分割任务中，探索该架构模型在夜间语义分割任务的优势，以提升夜间分割任务的精度。提出了一个语义对齐图像翻译（Semantic Pairing GAN，SPG）模块，通过语义信息将非配对翻译和粗配对翻译相结合，以此将分割任务与SPG翻译模块进行语义关联，促进翻译内容更加适合分割任务，且不独立于分割任务。SPG模块先将源域白天图像翻译成夜间图像，然后分割模型用翻译后的图像进行训练，这样分割模型就能学习到风格域信息以减少风格域差异。提出了一种语义域混合（Semantic Domain Mixing，SDM）策略，利用语义信息将SPG翻译的动态物体提取并移动到目标域夜间静态物体图像的合理位置，重新组合成新的图像。分割模型利用这种风格域差异小的图像进行训练，可以更容易从分布域角度进行域适应，从而缩小分布域差距。通过风格域适应和分布域适应相结合，使模型从两种不同角度分别缩小域差异，整体上实现夜间分割任务的域适应，从而缓解现有数据集跨域幅度太大，难以直接域适应的问题。实验结果表明，本文的方法在Dark Zurich、ACDC Night和Nighttime Driving三个数据集上的mIoU指标分别取得60.0%、59.8%、59.1%，比现有最好的方法分别提高0.9%，0.4%和1.6%，对夜间复杂实际场景图像目标能进行精准的分割预测。

Abstract

Semantic segmentation plays an important role in a variety of practical applications such as autonomous driving

doctor-worker intersection

and security monitoring. However

nighttime semantic segmentation is still an unsolved problem. Due to insufficient illumination at night

the details of the acquired image are unclear

which leads to the difficulty of dataset annotation. Therefore

unsupervised domain adaptation methods for nighttime semantic segmentation are preferred. As a result

the semantic segmentation effect of nighttime scenes is not ideal. To solve this problem

this paper proposes an unsupervised SDDA (Style and Distribution Domain Adaptation) method for nighttime semantic segmentation. The domain adaptation of nighttime semantic segmentation task is divided into style domain adaptation and distribution domain adaptation. In this way

the difficulty of the nighttime segmentation task is reduced. The Mamba architecture model with better performance is introduced into the unsupervised domain to adapt to the nighttime semantic segmentation task

and the advantages of this architecture model in the nighttime semantic segmentation task are explored to improve the accuracy of the nighttime segmentation task. This paper proposes a SPG (Semantic Pairing GAN) module

which combines the unpaired translation and rough paired translation through semantic information

so as to semantically associate the segmentation task with the SPG translation module

so as to promote the translation content to be more suitable for the segmentation task and not independent of the segmentation task. The SPG module translates the day images of the source domain into night images

and then the segmentation model is trained with the translated images

so that the segmentation model can learn the style domain information to reduce the style domain differences. This paper proposes a SDM (Semantic Domain Mixing) strategy

which uses semantic information to extract and move the dynamic objects translated by SPG to the reasonable position of the static object image at night in the target domain

and recombines them into a new image. The segmentation model is trained by using the images with small style domain differences

which makes it easier to perform domain adaptation from the perspective of distribution domain

so as to narrow the distribution domain gap. Through the combination of style domain adaptation and distribution domain adaptation

the model reduces the domain differences from two different perspectives

and realizes the domain adaptation of night segmentation tasks as a whole

so as to alleviate the problem that the existing data sets have too large cross-domain range and are difficult to directly adapt to the domain. The experimental results show that the mIoU index of the proposed method on Dark Zurich

ACDC Night and Nighttime Driving datasets achieves 60.0%

59.8% and 59.1%

respectively

which is 0.9%

0.4% and 1.6% higher than the best existing method. It can accurately segment and predict the image target of complex actual scene at night.

关键词

Keywords

references

Fu Y X , Lou M , Yu Y Z . SegMAN: Omni-scale context modeling with state space models and local attention for semantic segmentation [C ] // 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2025 : 19077 - 19087 . DOI: 10.1109/cvpr52734.2025.01777 http://dx.doi.org/10.1109/cvpr52734.2025.01777

Chen L W , Fu Y , Gu L , et al . Spatial frequency modulation for semantic segmentation [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 47 ( 11 ): 9767 - 9784 . DOI: 10.1109/tpami.2025.3592621 http://dx.doi.org/10.1109/tpami.2025.3592621

Xu Z Z , Wu D Y , Yu C Q , et al . SCTNet: Single-branch CNN with transformer semantic information for real-time segmentation [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 6 ): 6378 - 6386 . DOI: 10.1609/aaai.v38i6.28457 http://dx.doi.org/10.1609/aaai.v38i6.28457

Zhao Z , Long S F , Pi J M , et al . Instance-specific and model-adaptive supervision for semi-supervised semantic segmentation [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 23705 - 23714 . DOI: 10.1109/cvpr52729.2023.02270 http://dx.doi.org/10.1109/cvpr52729.2023.02270

杨维静 , 徐瑞 , 顾浩文 , 等 . 基于伪标签去噪和SAM优化的大规模无监督语义分割 [J ] . 电子学报 , 2025 , 53 ( 3 ): 716 - 727 .

Yang Weijing , Xu Rui , Gu Haowen , et al . Pseudo-label denoising and SAM optimization for large-scale unsupervised semantic segmentation [J ] . Acta Electronica Sinica , 2025 , 53 ( 3 ): 716 - 727 . (in Chinese)

Sun L , Wang K W , Yang K L , et al . See clearer at night: Towards robust nighttime semantic segmentation through day-night image conversion [C ] // Artificial Intelligence and Machine Learning in Defense Applications . SPIE , 2019 : 2532477 . DOI: 10.1117/12.2532477 http://dx.doi.org/10.1117/12.2532477

Shen Z Q , Huang M Y , Shi J P , et al . Towards instance-level image-to-image translation [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 3678 - 3687 . DOI: 10.1109/cvpr.2019.00380 http://dx.doi.org/10.1109/cvpr.2019.00380

江泽涛 , 廖培期 , 黄钦阳 , 等 . 基于向量符号架构-域适应网络的低照度图像语义分割方法 [J ] . 计算机辅助设计与图形学学报 , 2025 , 37 ( 8 ): 1371 - 1382 . DOI: 10.3724/sp.j.1089.2023-00555 http://dx.doi.org/10.3724/sp.j.1089.2023-00555

Jiang Z T , Liao P Q , Huang Q Y , et al . Low-light image semantic segmentation method based on vector symbolic architecture-domain adaptation network [J ] . Journal of Computer-Aided Design & Computer Graphics , 2025 , 37 ( 8 ): 1371 - 1382 . (in Chinese) . DOI: 10.3724/sp.j.1089.2023-00555 http://dx.doi.org/10.3724/sp.j.1089.2023-00555

江泽涛 , 朱文才 , 金鑫 , 等 . 一种基于双重语义协作网络的图像描述方法 [J ] . 计算机研究与发展 , 2024 , 61 ( 11 ): 2897 - 2908 .

Jiang Zetao , Zhu Wencai , Jin Xin , et al . An image captioning method based on DSC-net [J ] . Journal of Computer Research and Development , 2024 , 61 ( 11 ): 2897 - 2908 . (in Chinese)

江泽涛 , 翟丰硕 , 钱艺 , 等 . 结合特征增强和多尺度感受野的低照度目标检测 [J ] . 计算机研究与发展 , 2023 , 60 ( 4 ): 903 - 915 . DOI: 10.7544/issn1000-1239.202111092 http://dx.doi.org/10.7544/issn1000-1239.202111092

Jiang Zetao , Zhai Fengshuo , Qian Yi , et al . Low illumination object detection combined with feature enhancement and MultiScale receptive field [J ] . Journal of Computer Research and Development , 2023 , 60 ( 4 ): 903 - 915 . (in Chinese) . DOI: 10.7544/issn1000-1239.202111092 http://dx.doi.org/10.7544/issn1000-1239.202111092

Yang G L , Zhong Z , Tang H , et al . Bi-mix: Bidirectional mixing for domain adaptive nighttime semantic segmentation [PP/OL ] . V1.arXiv ( 2021-11-19 )[ 2026-01-25 ] . https://doi.org/10.48550/arXiv.2111.10339 https://doi.org/10.48550/arXiv.2111.10339 .

Luo X Y , Zhang J M , Yang K L , et al . Towards robust semantic segmentation of accident scenes via multi-source mixed sampling and meta-learning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2022 : 4428 - 4438 . DOI: 10.1109/cvprw56347.2022.00489 http://dx.doi.org/10.1109/cvprw56347.2022.00489

Pan J Y , Li S H , Chen Y C , et al . Towards dynamic and small objects refinement for unsupervised domain adaptative nighttime semantic segmentation [C ] // 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems . Piscataway : IEEE , 2024 : 2720 - 2727 . DOI: 10.1109/iros58592.2024.10801389 http://dx.doi.org/10.1109/iros58592.2024.10801389

Sankaranarayanan S , Balaji Y , Jain A , et al . Learning from synthetic data: Addressing domain shift for semantic segmentation [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3752 - 3761 . DOI: 10.1109/cvpr.2018.00395 http://dx.doi.org/10.1109/cvpr.2018.00395

Zhang Y H , Qiu Z F , Yao T , et al . Fully convolutional adaptation networks for semantic segmentation [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 6810 - 6818 . DOI: 10.1109/cvpr.2018.00712 http://dx.doi.org/10.1109/cvpr.2018.00712

Gao H , Guo J C , Wang G L , et al . Cross-domain correlation distillation for unsupervised domain adaptation in nighttime semantic segmentation [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9903 - 9913 . DOI: 10.1109/cvpr52688.2022.00968 http://dx.doi.org/10.1109/cvpr52688.2022.00968

Wu X Y , Wu Z Y , Guo H , et al . DANNet: A one-stage domain adaptation network for unsupervised nighttime semantic segmentation [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 15764 - 15773 . DOI: 10.1109/cvpr46437.2021.01551 http://dx.doi.org/10.1109/cvpr46437.2021.01551

Liu W Y , Li W T , Zhu J K , et al . Improving nighttime driving-scene segmentation via dual image-adaptive learnable filters [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2023 , 33 ( 10 ): 5855 - 5867 . DOI: 10.1109/tcsvt.2023.3260240 http://dx.doi.org/10.1109/tcsvt.2023.3260240

Hoyer L , Dai D X , Van Gool L . DAFormer: Improving network architectures and training strategies for domain-adaptive semantic segmentation [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 9914 - 9925 . DOI: 10.1109/cvpr52688.2022.00969 http://dx.doi.org/10.1109/cvpr52688.2022.00969

Xie E Z , Wang W H , Yu Z D , et al . SegFormer: Simple and efficient design for semantic segmentation with transformers [C/OL ] // The 35th Conference on Neural Information Processing Systems (NeurIPS 2021). 2021 : 12077 - 12090 . https://proceedings.neurips.cc/paper_files/paper/2021/file/64f1f27bf1b4ec22924fd0acb550c235-Paper.pdf https://proceedings.neurips.cc/paper_files/paper/2021/file/64f1f27bf1b4ec22924fd0acb550c235-Paper.pdf .

Huang F D , Yao Z H , Zhou W H . DTBS: Dual-teacher bi-directional self-training for domain adaptation in nighttime semantic segmentation [PP/OL ] . V1.arXiv ( 2024-01-02 )[ 2026-01-25 ] . https://doi.org/10.48550/arXiv.2401.01066 https://doi.org/10.48550/arXiv.2401.01066 .

Hoyer L , Dai D X , Wang H R , et al . MIC: Masked image consistency for context-enhanced domain adaptation [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 11721 - 11732 . DOI: 10.1109/cvpr52729.2023.01128 http://dx.doi.org/10.1109/cvpr52729.2023.01128

Long J , Shelhamer E , Darrell T . Fully convolutional networks for semantic segmentation [C ] // 2015 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2015 : 3431 - 3440 . DOI: 10.1109/cvpr.2015.7298965 http://dx.doi.org/10.1109/cvpr.2015.7298965

Ronneberger O , Fischer P , Brox T . U-Net: Convolutional networks for biomedical image segmentation [M ] // Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015 . Cham : Springer International Publishing , 2015 : 234 - 241 . DOI: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28

Lin G S , Milan A , Shen C H , et al . RefineNet: Multi-path refinement networks for high-resolution semantic segmentation [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 5168 - 5177 . DOI: 10.1109/cvpr.2017.549 http://dx.doi.org/10.1109/cvpr.2017.549

Chen L C , Papandreou G , Kokkinos I , et al . DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 , 40 ( 4 ): 834 - 848 . DOI: 10.1109/tpami.2017.2699184 http://dx.doi.org/10.1109/tpami.2017.2699184

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 . Piscataway : IEEE , 2021 : 6877 - 6886 . DOI: 10.1109/cvpr46437.2021.00681 http://dx.doi.org/10.1109/cvpr46437.2021.00681

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 . Piscataway : IEEE , 2021 : 9992 - 10002 . DOI: 10.1109/iccv48922.2021.00986 http://dx.doi.org/10.1109/iccv48922.2021.00986

Yu W H , Wang X C . MambaOut: Do we really need mamba for vision [C ] // 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2025 : 4484 - 4496 . DOI: 10.1109/cvpr52734.2025.00423 http://dx.doi.org/10.1109/cvpr52734.2025.00423

Dai D X , Van Gool L . Dark model adaptation: Semantic image segmentation from daytime to nighttime [C ] // 2018 21st International Conference on Intelligent Transportation Systems . Piscataway : IEEE , 2018 : 3819 - 3824 . DOI: 10.1109/itsc.2018.8569387 http://dx.doi.org/10.1109/itsc.2018.8569387

Sakaridis C , Dai D X , Van Gool L . Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 7373 - 7382 . DOI: 10.1109/iccv.2019.00747 http://dx.doi.org/10.1109/iccv.2019.00747

Sakaridis C , Dai D X , Van Gool L . Map-guided curriculum domain adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 6 ): 3139 - 3153 . DOI: 10.1109/tpami.2020.3045882 http://dx.doi.org/10.1109/tpami.2020.3045882

Wu X , Lai Z H , Yu S Q , et al . Coarse-to-fine low-light image enhancement with light restoration and color refinement [J ] . IEEE Transactions on Emerging Topics in Computational Intelligence , 2024 , 8 ( 1 ): 591 - 603 . DOI: 10.1109/tetci.2023.3314436 http://dx.doi.org/10.1109/tetci.2023.3314436

Wu X , Lai Z H , Zhou J , et al . Light-aware contrastive learning for low-light image enhancement [J ] . ACM Transactions on Multimedia Computing, Communications, and Applications , 2024 , 20 ( 9 ): 1 - 24 . DOI: 10.1145/3665498 http://dx.doi.org/10.1145/3665498

Wu X , Hou X X , Lai Z H , et al . A codebook-driven approach for low-light image enhancement [J ] . Engineering Applications of Artificial Intelligence , 2025 , 156 : 111115 . DOI: 10.1016/j.engappai.2025.111115 http://dx.doi.org/10.1016/j.engappai.2025.111115

秦嘉奇 , 江泽涛 , 雷晓春 . 基于ICFIE-YOLO的低照度图像目标检测方法 [J ] . 电子学报 , 2025 , 53 ( 2 ): 514 - 526 .

Qin Jiaqi , Jiang Zetao , Lei Xiaochun . Low illumination image object detection method based on ICFIE-YOLO [J ] . Acta Electronica Sinica , 2025 , 53 ( 2 ): 514 - 526 . (in Chinese)

Wei Z X , Chen L , Tu T , et al . Disentangle then parse: Night-time semantic segmentation with illumination disentanglement [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 21536 - 21546 . DOI: 10.1109/iccv51070.2023.01974 http://dx.doi.org/10.1109/iccv51070.2023.01974

Tan X , Xu K , Cao Y , et al . Night-time scene parsing with a large real dataset [J ] . IEEE Transactions on Image Processing , 2021 , 30 : 9085 - 9098 . DOI: 10.1109/tip.2021.3122004 http://dx.doi.org/10.1109/tip.2021.3122004

Deng X Q , Wang P , Lian X C , et al . NightLab: A dual-level architecture with hardness detection for segmentation at night [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 16917 - 16927 . DOI: 10.1109/cvpr52688.2022.01643 http://dx.doi.org/10.1109/cvpr52688.2022.01643

Xie Z F , Wang S , Xu K , et al . Boosting night-time scene parsing with learnable frequency [J ] . IEEE Transactions on Image Processing , 2023 , 32 : 2386 - 2398 . DOI: 10.1109/tip.2023.3267044 http://dx.doi.org/10.1109/tip.2023.3267044

Nag S , Adak S , Das S . What’s there in the dark [C ] // 2019 IEEE International Conference on Image Processing . Piscataway : IEEE , 2019 : 2996 - 3000 . DOI: 10.1109/icip.2019.8803299 http://dx.doi.org/10.1109/icip.2019.8803299

Luo R D , Wang W J , Yang W H , et al . Similarity Min-max: Zero-shot day-night domain adaptation [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 8070 - 8080 . DOI: 10.1109/iccv51070.2023.00744 http://dx.doi.org/10.1109/iccv51070.2023.00744

Liang D , Li L , Wei M Q , et al . Semantically contrastive learning for low-light image enhancement [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 2 ): 1555 - 1563 . DOI: 10.1609/aaai.v36i2.20046 http://dx.doi.org/10.1609/aaai.v36i2.20046

Yun S , Han D , Chun S , et al . CutMix: Regularization strategy to train strong classifiers with localizable features [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 6022 - 6031 . DOI: 10.1109/iccv.2019.00612 http://dx.doi.org/10.1109/iccv.2019.00612

Olsson V , Tranheden W , Pinto J , et al . ClassMix: Segmentation-based data augmentation for semi-supervised learning [C ] // 2021 IEEE Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2021 : 1368 - 1377 . DOI: 10.1109/wacv48630.2021.00141 http://dx.doi.org/10.1109/wacv48630.2021.00141

Walawalkar D , Shen Z Q , Liu Z C , et al . Attentive cutmix: An enhanced data augmentation approach for deep learning based image classification [C ] // ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2020 : 3642 - 3646 . DOI: 10.1109/icassp40776.2020.9053994 http://dx.doi.org/10.1109/icassp40776.2020.9053994

Tranheden W , Olsson V , Pinto J , et al . DACS: Domain adaptation via cross-domain mixed sampling [C ] // 2021 IEEE Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2021 : 1378 - 1388 . DOI: 10.1109/wacv48630.2021.00142 http://dx.doi.org/10.1109/wacv48630.2021.00142

Zhou Q Y , Feng Z Y , Gu Q Q , et al . Context-aware mixup for domain adaptive semantic segmentation [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2023 , 33 ( 2 ): 804 - 817 . DOI: 10.1109/tcsvt.2022.3206476 http://dx.doi.org/10.1109/tcsvt.2022.3206476

Chen S J , Jia X , He J Z , et al . Semi-supervised domain adaptation based on dual-level domain mixing for semantic segmentation [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 11013 - 11022 . DOI: 10.1109/cvpr46437.2021.01087 http://dx.doi.org/10.1109/cvpr46437.2021.01087

Jiao J B , Liu Y , Liu Y F , et al . VMamba: Visual state space model [C ] // Advances in Neural Information Processing Systems 37 . Neural Information Processing Systems Foundation, Inc. (NeurIPS) , 2024 : 103031 - 103063 . DOI: 10.52202/079017-3273 http://dx.doi.org/10.52202/079017-3273

Zhu J Y , Park T , Isola P , et al . Unpaired image-to-image translation using cycle-consistent adversarial networks [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 2242 - 2251 . DOI: 10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244

Ho J , Jain A , Abbeel P . Denoising diffusion probabilistic models [C/OL ] // The 34th International Conference on Neural Information Processing Systems . 2020 : 6840 - 6851 . https://proceedings.neurips.cc/paper_files/paper/2020/file/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf https://proceedings.neurips.cc/paper_files/paper/2020/file/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf .

Shen Z Y , Mao M Y , Fan P F . A primary comparison of diffusion models and generative adversarial networks for image synthesis [C ] // Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI) . New York : ACM , 2024 : 225 - 234 . DOI: 10.1145/3696271.3696307 http://dx.doi.org/10.1145/3696271.3696307

Sakaridis C , Dai D X , Van Gool L . ACDC: The adverse conditions dataset with correspondences for semantic driving scene understanding [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 10745 - 10755 . DOI: 10.1109/iccv48922.2021.01059 http://dx.doi.org/10.1109/iccv48922.2021.01059

Lyu S W , Chang M C , Du D W , et al . UA-DETRAC 2017: Report of AVSS2017 & IWT4S challenge on advanced traffic monitoring [C ] // 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance . Piscataway : IEEE , 2017 : 8078560 . DOI: 10.1109/avss.2017.8078560 http://dx.doi.org/10.1109/avss.2017.8078560

Cordts M , Omran M , Ramos S , et al . The cityscapes dataset for semantic urban scene understanding [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 3213 - 3223 . DOI: 10.1109/cvpr.2016.350 http://dx.doi.org/10.1109/cvpr.2016.350

MMSEGMENTATION C . MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark [EB/OL ] . ( 2020-07-09 )[ 2026-01-25 ] . https://github.com/open-mmlab/mmsegmentation https://github.com/open-mmlab/mmsegmentation .

Loshchilov I , Hutter F . Decoupled weight decay regularization [PP/OL ] . V3.arXiv ( 2019-01-04 )[ 2026-01-25 ] . https://doi.org/10.48550/arXiv.1711.05101 https://doi.org/10.48550/arXiv.1711.05101 .

Hoyer L , Dai D X , Van Gool L . HRDA: Context-aware high-resolution domain-adaptive semantic segmentation [M ] // Computer Vision-ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 372 - 391 . DOI: 10.48550/arXiv.2204.13132 http://dx.doi.org/10.48550/arXiv.2204.13132

Xie Z F , Qiu R , Wang S , et al . PIG: Prompt images guidance for night-time scene parsing [J ] . IEEE Transactions on Image Processing , 2024 , 33 : 3921 - 3934 . DOI: 10.1109/tip.2024.3415963 http://dx.doi.org/10.1109/tip.2024.3415963

Xie B H , Li S , Li M J , et al . SePiCo: Semantic-guided pixel contrast for domain adaptive semantic segmentation [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 7 ): 9004 - 9021 . DOI: 10.1109/tpami.2023.3237740 http://dx.doi.org/10.1109/tpami.2023.3237740

Lu Y W , Lang J C , Ding M R . Dual-path consistency unsupervised domain adaptation for nighttime semantic segmentation [C ] // ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2025 : 10887918 . DOI: 10.1109/icassp49660.2025.10887918 http://dx.doi.org/10.1109/icassp49660.2025.10887918

Sakaridis C , Bruggemann D , Yu F , et al . Condition-invariant semantic segmentation [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 47 ( 4 ): 3111 - 3125 . DOI: 10.1109/tpami.2025.3529350 http://dx.doi.org/10.1109/tpami.2025.3529350

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

基于深度学习的图像实例分割技术研究进展

基于长程依赖与局部动态感知的加密流量预训练模型构建

面向边缘物联网的双教师蒸馏式轻量化入侵检测

基于异构图的Tor网络关键节点识别方法

分布偏移场景下图神经网络测试时自适应方法