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
  • [41] Self-supervised Representation Learning on Document Images
    Cosma, Adrian
    Ghidoveanu, Mihai
    Panaitescu-Liess, Michael
    Popescu, Marius
    DOCUMENT ANALYSIS SYSTEMS, 2020, 12116 : 103 - 117
  • [42] Adaptive Self-Supervised Graph Representation Learning
    Gong, Yunchi
    36TH INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN 2022), 2022, : 254 - 259
  • [43] Context Autoencoder for Self-supervised Representation Learning
    Chen, Xiaokang
    Ding, Mingyu
    Wang, Xiaodi
    Xin, Ying
    Mo, Shentong
    Wang, Yunhao
    Han, Shumin
    Luo, Ping
    Zeng, Gang
    Wang, Jingdong
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2023, 132 (1) : 208 - 223
  • [44] SELF-SUPERVISED REPRESENTATION LEARNING FOR ULTRASOUND VIDEO
    Jiao, Jianbo
    Droste, Richard
    Drukker, Lior
    Papageorghiou, Aris T.
    Noble, J. Alison
    2020 IEEE 17TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2020), 2020, : 1847 - 1850
  • [45] Context Autoencoder for Self-supervised Representation Learning
    Xiaokang Chen
    Mingyu Ding
    Xiaodi Wang
    Ying Xin
    Shentong Mo
    Yunhao Wang
    Shumin Han
    Ping Luo
    Gang Zeng
    Jingdong Wang
    International Journal of Computer Vision, 2024, 132 : 208 - 223
  • [46] SelfDoc: Self-Supervised Document Representation Learning
    Li, Peizhao
    Gu, Jiuxiang
    Kuen, Jason
    Morariu, Vlad, I
    Zhao, Handong
    Jain, Rajiv
    Manjunatha, Varun
    Liu, Hongfu
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 5648 - 5656
  • [47] Solving Inefficiency of Self-supervised Representation Learning
    Wang, Guangrun
    Wang, Keze
    Wang, Guangcong
    Torr, Philip H. S.
    Lin, Liang
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 9485 - 9495
  • [48] Self-supervised Representation Learning for Astronomical Images
    Hayat, Md Abul
    Stein, George
    Harrington, Peter
    Lukic, Zarija
    Mustafa, Mustafa
    ASTROPHYSICAL JOURNAL LETTERS, 2021, 911 (02)
  • [49] Self-supervised representation learning for trip recommendation
    Gao, Qiang
    Wang, Wei
    Zhang, Kunpeng
    Yang, Xin
    Miao, Congcong
    Li, Tianrui
    KNOWLEDGE-BASED SYSTEMS, 2022, 247
  • [50] MusicBERT: A Self-supervised Learning of Music Representation
    Zhu, Hongyuan
    Niu, Ye
    Fu, Di
    Wang, Hao
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 3955 - 3963