Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation

被引:3
|
作者
Bruggemann, David [1 ]
Sakaridis, Christos [1 ]
Brodermann, Tim [1 ]
Van Gool, Luc [1 ]
机构
[1] Swiss Fed Inst Technol, Zurich, Switzerland
来源
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023) | 2023年
关键词
D O I
10.1109/ICCV51070.2023.01045
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Standard unsupervised domain adaptation methods adapt models from a source to a target domain using labeled source data and unlabeled target data jointly. In model adaptation, on the other hand, access to the labeled source data is prohibited, i.e., only the source-trained model and unlabeled target data are available. We investigate normal-to-adverse condition model adaptation for semantic segmentation, whereby image-level correspondences are available in the target domain. The target set consists of unlabeled pairs of adverse- and normalcondition street images taken at GNSS-matched locations. Our method-CMA-leverages such image pairs to learn condition-invariant features via contrastive learning. In particular, CMA encourages features in the embedding space to be grouped according to their condition-invariant semantic content and not according to the condition under which respective inputs are captured. To obtain accurate cross-domain semantic correspondences, we warp the normal image to the viewpoint of the adverse image and leverage warp-confidence scores to create robust, aggregated features. With this approach, we achieve state-of-the-art semantic segmentation performance for model adaptation on several normal-to-adverse adaptation benchmarks, such as ACDC and Dark Zurich. We also evaluate CMA on a newly procured adverse-condition generalization benchmark and report favorable results compared to standard unsupervised domain adaptation methods, despite the comparative handicap of CMA due to source data inaccessibility. Code is available at https://github.com/brdav/cma.
引用
收藏
页码:11344 / 11353
页数:10
相关论文
共 50 条
  • [41] Partial Domain Adaptation on Semantic Segmentation
    Tian, Yingjie
    Zhu, Siyu
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (06) : 3798 - 3809
  • [42] Benchmarking domain adaptation for semantic segmentation
    Ahmed, Masud
    Hasan, Zahid
    Khan, Naima
    Roy, Nirmalya
    Purushotham, Sanjay
    Gangopadhyay, Aryya
    You, Suya
    UNMANNED SYSTEMS TECHNOLOGY XXIV, 2022, 12124
  • [43] Domain Adaptation in Nuclei Semantic Segmentation
    Li, Dawei
    Shi, Zongxuan
    Zhang, Hao
    Zhang, Renhao
    INTERNATIONAL CONFERENCE ON COMPUTER VISION, APPLICATION, AND DESIGN (CVAD 2021), 2021, 12155
  • [44] Knowledge Adaptation for Efficient Semantic Segmentation
    He, Tong
    Shen, Chunhua
    Tian, Zhi
    Gong, Dong
    Sun, Changming
    Yan, Youliang
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 578 - 587
  • [45] ADVERSARIAL CONTRASTIVE FOURIER DOMAIN ADAPTATION FOR POLYP SEGMENTATION
    Huy, Ta Duc
    Huyen, Hoang Cao
    Nguyen, Chanh D. T.
    Duong, Soan T. M.
    Bui, Trung
    Truong, Steven Q. H.
    2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022), 2022,
  • [46] CTDA: Contrastive Temporal Domain Adaptation for Action Segmentation
    Han, Hongfeng
    Lu, Zhiwu
    Wen, Ji-Rong
    MULTIMEDIA MODELING, MMM 2023, PT II, 2023, 13834 : 562 - 574
  • [47] Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation
    Gomariz, Alvaro
    Lu, Huanxiang
    Li, Yun Yvonna
    Albrecht, Thomas
    Maunz, Andreas
    Benmansour, Fethallah
    Valcarcel, Alessandra M.
    Luu, Jennifer
    Ferrara, Daniela
    Goksel, Orcun
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VIII, 2022, 13438 : 351 - 361
  • [48] A Cross-Condition Fault Disentangling Matching Network for Industrial Early Fault Enhancement
    Ren, Yifu
    Zheng, Dayong
    Yang, Yanyong
    Qu, Jianzhen
    Liu, Jinhai
    Zhang, Pinjia
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2024,
  • [49] Contrastive Adapters for Foundation Model Group Robustness
    Zhang, Michael
    Re, Christopher
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [50] Recursive prototypical network with coordinate attention: A model for few-shot cross-condition bearing fault diagnosis
    Jiang, Yonghua
    Qiu, Zengjie
    Zheng, Linjie
    Dong, Zhilin
    Jiao, Weidong
    Tang, Chao
    Sun, Jianfeng
    Xuan, Zhongyi
    APPLIED ACOUSTICS, 2025, 231