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
来源
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020 | 2020年 / 33卷
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
  • [21] Whitening for Self-Supervised Representation Learning
    Ermolov, Aleksandr
    Siarohin, Aliaksandr
    Sangineto, Enver
    Sebe, Nicu
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [22] Self-Supervised Representation Learning for CAD
    Jones, Benjamin T.
    Hu, Michael
    Kodnongbua, Milin
    Kim, Vladimir G.
    Schulz, Adriana
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 21327 - 21336
  • [23] Enhancing motion visual cues for self-supervised video representation learning
    Nie, Mu
    Quan, Zhibin
    Ding, Weiping
    Yang, Wankou
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [24] MULTI-AUGMENTATION FOR EFFICIENT SELF-SUPERVISED VISUAL REPRESENTATION LEARNING
    Tran, Van Nhiem
    Huang, Chi-En
    Liu, Shen-Hsuan
    Yang, Kai-Lin
    Ko, Timothy
    Li, Yung-Hui
    2022 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (IEEE ICMEW 2022), 2022,
  • [25] Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
    Wei, Longhui
    Xie, Lingxi
    He, Jianzhong
    Zhang, Xiaopeng
    Tian, Qi
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 2642 - 2650
  • [26] Self-supervised Visual Learning from Interactions with Objects
    Aubret, Arthur
    Teuliere, Celine
    Triesch, Jochen
    COMPUTER VISION - ECCV 2024, PT LXXV, 2025, 15133 : 54 - 71
  • [27] Evolved Hierarchical Masking for Self-Supervised Learning
    Feng, Zhanzhou
    Zhang, Shiliang
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 47 (02) : 1013 - 1027
  • [28] Self-Distilled Self-supervised Representation Learning
    Jang, Jiho
    Kim, Seonhoon
    Yoo, Kiyoon
    Kong, Chaerin
    Kim, Jangho
    Kwak, Nojun
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 2828 - 2838
  • [29] Towards Latent Masked Image Modeling for Self-supervised Visual Representation Learning
    Wei, Yibing
    Gupta, Abhinav
    Morgado, Pedro
    COMPUTER VISION - ECCV 2024, PT XXXIX, 2025, 15097 : 1 - 17
  • [30] solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
    Turrisi da Costa, Victor G.
    Fini, Enrico
    Nabi, Moin
    Sebe, Nicu
    Ricci, Elisa
    Journal of Machine Learning Research, 2022, 23