SimCS: Simulation for Domain Incremental Online Continual Segmentation

被引:0
|
作者
Alfarra, Motasem [1 ,2 ]
Cai, Zhipeng [1 ]
Bibi, Adel [3 ]
Ghanem, Bernard [2 ]
Mueller, Matthias [1 ]
机构
[1] Intel Labs, Thuwal, Saudi Arabia
[2] King Abdullah Univ Sci & Technol KAUST, Thuwal, Saudi Arabia
[3] Univ Oxford, Oxford, England
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual learning approaches mostly focus on image classification in the class-incremental setup with clear task boundaries and unlimited computational budget. This work explores the problem of Online Domain-Incremental Continual Segmentation (ODICS), where the model is continually trained over batches of densely labeled images from different domains, with limited computation and no information about the task boundaries. ODICS arises in many practical applications. In autonomous driving, this may correspond to the realistic scenario of training a segmentation model over time on a sequence of cities. We analyze several existing continual learning methods and show that they perform poorly in this setting despite working well in class-incremental segmentation. We propose SimCS, a parameter-free method complementary to existing ones that uses simulated data to regularize continual learning. Experiments show that SimCS provides consistent improvements when combined with different CL methods.
引用
收藏
页码:10795 / 10803
页数:9
相关论文
共 50 条
  • [41] Preparing the Future for Continual Semantic Segmentation
    Lin, Zihan
    Wang, Zilei
    Zhang, Yixin
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 11876 - 11886
  • [42] Continual Domain Incremental Learning for Chest X-Ray Classification in Low-Resource Clinical Settings
    Srivastava, Shikhar
    Yaqub, Mohammad
    Nandakumar, Karthik
    Ge, Zongyuan
    Mahapatra, Dwarikanath
    DOMAIN ADAPTATION AND REPRESENTATION TRANSFER, AND AFFORDABLE HEALTHCARE AND AI FOR RESOURCE DIVERSE GLOBAL HEALTH (DART 2021), 2021, 12968 : 226 - 238
  • [43] Continual Learning for Fundus Image Segmentation
    Liu, Yufan
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT XIV, 2025, 15044 : 314 - 328
  • [44] CBA: Improving Online Continual Learning via Continual Bias Adaptor
    Wang, Quanziang
    Wang, Renzhen
    Wu, Yichen
    Jia, Xixi
    Meng, Deyu
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 19036 - 19046
  • [45] Segmentation with Incremental Classifiers
    Bernard, Guillaume
    Verleysen, Michel
    Lee, John A.
    IMAGE ANALYSIS AND PROCESSING (ICIAP 2013), PT II, 2013, 8157 : 81 - 90
  • [46] INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation
    Liu, Leyao
    Zheng, Tian
    Lin, Yun-Jou
    Ni, Kai
    Fang, Lu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 18953 - 18962
  • [47] Live and Learn: Continual Action Clustering with Incremental Views
    Yan, Xiaoqiang
    Gan, Yingtao
    Mao, Yiqiao
    Ye, Yangdong
    Yu, Hui
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 15, 2024, : 16264 - 16271
  • [48] Incremental Multiview Clustering With Continual Information Bottleneck Method
    Yan, Xiaoqiang
    Mao, Yiqiao
    Ye, Yangdong
    Yu, Hui
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2025, 55 (01): : 295 - 306
  • [49] Detecting Morphing Attacks via Continual Incremental Training
    Pellegrini, Lorenzo
    Borghi, Guido
    Franco, Annalisa
    Maltoni, Davide
    2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB, 2023,
  • [50] ONLINE CONTINUAL LEARNING FOR EMBEDDED DEVICES
    Hayes, Tyler L.
    Kanan, Christopher
    CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 199, 2022, 199