Self-Supervised Visual Representation Learning from Hierarchical Grouping

被引:0
|
作者
Zhang, Xiao [1 ]
Maire, Michael [1 ]
机构
[1] Univ Chicago, Chicago, IL 60637 USA
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
We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partitions an image into regions, followed by merging of those regions into a tree hierarchy. A small supervised dataset suffices for training this grouping primitive. Across a large unlabeled dataset, we apply this learned primitive to automatically predict hierarchical region structure. These predictions serve as guidance for self-supervised contrastive feature learning: we task a deep network with producing per-pixel embeddings whose pairwise distances respect the region hierarchy. Experiments demonstrate that our approach can serve as state-of-the-art generic pre-training, benefiting downstream tasks. We additionally explore applications to semantic region search and video-based object instance tracking.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Self-Supervised Visual Representation Learning with Semantic Grouping
    Wen, Xin
    Zhao, Bingchen
    Zheng, Anlin
    Zhang, Xiangyu
    Qi, Xiaojuan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [2] Revisiting Self-Supervised Visual Representation Learning
    Kolesnikov, Alexander
    Zhai, Xiaohua
    Beyer, Lucas
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 1920 - 1929
  • [3] Self-Supervised Dense Visual Representation Learning
    Ozcelik, Timoteos Onur
    Gokberk, Berk
    Akarun, Lale
    32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024,
  • [4] Hierarchical Self-supervised Representation Learning for Movie Understanding
    Xiao, Fanyi
    Kundu, Kaustav
    Tighe, Joseph
    Modolo, Davide
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 9717 - 9726
  • [5] SHERLock: Self-Supervised Hierarchical Event Representation Learning
    Roychowdhury, S.
    Sontakke, S. A.
    Itti, L.
    Sarkar, M.
    Aggarwal, M.
    Badjatiya, P.
    Puri, N.
    Krishnamurthy, B.
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 2672 - 2678
  • [6] Mixed Autoencoder for Self-supervised Visual Representation Learning
    Chen, Kai
    Liu, Zhili
    Hong, Lanqing
    Xu, Hang
    Li, Zhenguo
    Yeung, Dit-Yan
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 22742 - 22751
  • [7] A survey on self-supervised methods for visual representation learning
    Uelwer, Tobias
    Robine, Jan
    Wagner, Stefan Sylvius
    Hoeftmann, Marc
    Upschulte, Eric
    Konietzny, Sebastian
    Behrendt, Maike
    Harmeling, Stefan
    MACHINE LEARNING, 2025, 114 (04)
  • [8] Scaling and Benchmarking Self-Supervised Visual Representation Learning
    Goyal, Priya
    Mahajan, Dhruv
    Gupta, Abhinav
    Misra, Ishan
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6400 - 6409
  • [9] Transitive Invariance for Self-supervised Visual Representation Learning
    Wang, Xiaolong
    He, Kaiming
    Gupta, Abhinav
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 1338 - 1347
  • [10] Self-supervised Visual Representation Learning for Histopathological Images
    Yang, Pengshuai
    Hong, Zhiwei
    Yin, Xiaoxu
    Zhu, Chengzhan
    Jiang, Rui
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT II, 2021, 12902 : 47 - 57