Weakly Supervised Correspondence Learning

被引:0
|
作者
Wang, Zihan [1 ]
Cao, Zhangjie [1 ]
Hao, Yilun [1 ]
Sadigh, Dorsa [1 ]
机构
[1] Stanford Univ, Dept Comp Sci, Stanford, CA 94305 USA
关键词
SIMULATION; OTHERS;
D O I
10.1109/ICRA.46639.2022.9811729
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, current correspondence learning methods either leverage strictly paired data-which are often difficult to collect-or learn in an unsupervised fashion from unpaired data using regularization techniques such as cycle-consistency-which suffer from severe misalignment issues. We propose a weakly supervised correspondence learning approach that trades off between strong supervision over strictly paired data and unsupervised learning with a regularizer over unpaired data. Our idea is to leverage two types of weak supervision: i) temporal ordering of states and actions to reduce the compounding error, and ii) paired abstractions, instead of paired data, to alleviate the misalignment problem and learn a more accurate correspondence. The two types of weak supervision are easy to access in real-world applications, which simultaneously reduces the high cost of annotating strictly paired data and improves the quality of the learned correspondence. We show the videos of the experiments on our website.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement
    Huang, Yiwen
    Sun, Yixuan
    Lai, Chenghang
    Xu, Qing
    Wang, Xiaomei
    Shen, Xuli
    Ge, Weifeng
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 16208 - 16217
  • [2] Weakly Supervised Manifold Learning for Dense Semantic Object Correspondence
    Gaur, Utkarsh
    Manjunath, B. S.
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 1744 - 1752
  • [3] Weakly supervised foreground learning for weakly supervised localization and detection
    Zhang, Chen -Lin
    Li, Yin
    Wu, Jianxin
    [J]. PATTERN RECOGNITION, 2023, 137
  • [4] Safe Weakly Supervised Learning
    Li, Yu-Feng
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4951 - 4955
  • [5] Weakly Supervised Dictionary Learning
    You, Zeyu
    Raich, Raviv
    Fern, Xiaoli Z.
    Kim, Jinsub
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, 66 (10) : 2527 - 2541
  • [6] Weakly supervised machine learning
    Ren, Zeyu
    Wang, Shuihua
    Zhang, Yudong
    [J]. CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2023, 8 (03) : 549 - 580
  • [7] Weakly Supervised Contrastive Learning
    Zheng, Mingkai
    Wang, Fei
    You, Shan
    Qian, Chen
    Zhang, Changshui
    Wang, Xiaogang
    Xu, Chang
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 10022 - 10031
  • [8] Local Correspondence Network for Weakly Supervised Temporal Sentence Grounding
    Yang, Wenfei
    Zhang, Tianzhu
    Zhang, Yongdong
    Wu, Feng
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 3252 - 3262
  • [9] Weakly Supervised Deep Learning in Radiology
    Misera, Leo
    Mueller-Franzes, Gustav
    Truhn, Daniel
    Kather, Jakob Nikolas
    [J]. RADIOLOGY, 2024, 312 (01)
  • [10] Special issue on weakly supervised learning
    Zhang, Luming
    Ji, Rongrong
    Yi, Zhen
    Lin, Weisi
    Snoek, Cees
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 37 : 1 - 2