paper-with-me

홈 › Papers

Weakly Supervised Correspondence Learning

2022-03-02 · Zihan Wang, Zhangjie Cao, Yilun Hao, Dorsa Sadigh

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.

📄 PDF Abstract BibTeX arXiv:2203.00904

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

2021-05-13 · ICCV 2021 10 · Shiyi Lan, Zhiding Yu, Christopher Choy, Subhashree Radhakrishnan 외

We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision. Specifically, we propose a self-ensembling framework where instance segmentat…

Box-supervised Instance SegmentationInstance SegmentationSegmentationSemantic correspondence+1

Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement

2023-01-01 · ICCV 2023 1 · Yiwen Huang, Yixuan Sun, Chenghang Lai, Qing Xu 외

In this paper, we develop a weakly supervised learning algorithm to learn robust semantic correspondences from large-scale datasets with only image-level labels. Following the spirit of multiple instance learning (MI…

Multiple Instance LearningSemantic correspondenceWeakly-supervised Learning

Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels

2022-03-30 · CVPR 2022 1 · Jiwon Kim, Kwangrok Ryoo, Junyoung Seo, Gyuseong Lee 외

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for tr…

Data AugmentationSemantic correspondenceWeakly-supervised Learning

Weakly-Supervised Learning of Dense Functional Correspondences

2025-09-04 · Stefan Stojanov, Linan Zhao, Yunzhi Zhang, Daniel L. K. Yamins 외 arxiv

Establishing dense correspondences across image pairs is essential for tasks such as shape reconstruction and robot manipulation. In the challenging setting of matching across different categories, the function of an obj…

Contrastive LearningRobot Manipulation

A Simple Baseline for Weakly-Supervised Scene Graph Generation

2021-01-01 · ICCV 2021 10 · Jing Shi, Yiwu Zhong, Ning Xu, Yin Li 외

We investigate the weakly-supervised scene graph generation, which is a challenging task since no correspondence of label and object is provided. The previous work regards such correspondence as a latent variable whi…

Contrastive LearningGraph GenerationGraph MatchingScene Graph Generation