AI Paper Atlas

Research map / Video / Video segmentation and tracking

Mining Better Samples for Contrastive Learning of Temporal Correspondence

Sangryul Jeon, Dongbo Min, Seungryong Kim, Kwanghoon Sohn

CVPR 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 25 citations (OpenAlex)

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the proposed confidence-based positive mining and dynamic semi-hard negative miningpixel-level video correspondence learning · DAVIS-2017 validationJ&Fmean: 67.6 -> 70.3Improved
Use the full proposed methodpixel-level video correspondence learning · YouTube-VOS validationOverall: 64.2 -> 67.3Improved
Add temporal coherence to the positive-match confidence pipeline (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 68.7 -> 70.3Improved
Add optimal transport refinement to matching confidence (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 65.1 -> 70.3Improved
Add forward-backward consistency to matching confidence (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 63.7 -> 70.3Improved
Add negative samples to positive-only training (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 64.6 -> 70.3Improved
Select semi-hard negatives rather than all possible negatives (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 66.4 -> 70.3Improved
Adapt the negative-sample hardness threshold with a dynamic curriculum (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 67.6 -> 70.3Improved
Use a dynamic rather than linear negative-mining curriculum (ablation)the proposed method · DAVIS-2017 validationJ&Fmean: 68.9 -> 70.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy