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
  • [21] Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation
    Saporta, Antoine
    Douillard, Arthur
    Vu, Tuan-Hung
    Perez, Patrick
    Cord, Matthieu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 3750 - 3759
  • [22] PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning
    Lin, Huiwei
    Zhang, Baoquan
    Feng, Shanshan
    Li, Xutao
    Ye, Yunming
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 24246 - 24255
  • [23] CeCR: Cross-entropy contrastive replay for online class-incremental continual learning
    Sun, Guanglu
    Ji, Baolun
    Liang, Lili
    Chen, Minghui
    NEURAL NETWORKS, 2024, 173
  • [24] Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
    Churamani, Nikhil
    Kara, Ozgur
    Gunes, Hatice
    IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 14 (04) : 3191 - 3206
  • [25] Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer
    Marsden, Robert A.
    Wiewel, Felix
    Doebler, Mario
    Yang, Yang
    Yang, Bin
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [26] Domain consistency learning for continual test-time adaptation in image semantic segmentation
    Ye, Yanyu
    Wei, Wei
    Zhang, Lei
    Ding, Chen
    Zhang, Yanning
    PATTERN RECOGNITION, 2025, 165
  • [27] Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency
    Gu, Yanan
    Yang, Xu
    Wei, Kun
    Deng, Cheng
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 7432 - 7441
  • [28] Continual Hippocampus Segmentation with Transformers
    Ranem, Amin
    Gonzalez, Camila
    Mukhopadhyay, Anirban
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 3710 - 3719
  • [29] Towards Unsupervised Online Domain Adaptation for Semantic Segmentation
    Kuznietsov, Yevhen
    Proesmans, Marc
    Van Gool, Luc
    2022 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2022), 2022, : 261 - 271
  • [30] Domain knowledge based segmentation of online banking customers
    Seret, Alex
    Bejinaru, Andreea
    Baesens, Bart
    INTELLIGENT DATA ANALYSIS, 2015, 19 : S163 - S184