AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

Shuo Yang, Zhaopan Xu, Kai Wang, Yang You, Hongxun Yao, Tongliang Liu, Min Xu

CVPR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 41 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 BiCro soft correspondence labels instead of binary labels (ablation)SGRAF · Flickr30K 40% noiseImage-to-text R@1: 72.0 -> 74.6Improved
Use BiCro soft correspondence labels instead of binary labels (ablation)SGRAF · Flickr30K 40% noiseText-to-image R@1: 53.3 -> 55.5Improved
Replace GMM with BMM for modeling per-sample losses (ablation)BiCro · Flickr30K 40% noiseImage-to-text R@1: 72.0 -> 74.6Improved
Remove co-teaching (ablation)BiCro · Flickr30K 40% noiseImage-to-text R@1: 74.6 -> 69.9Hurt
Remove warmup (ablation)BiCro · Flickr30K 40% noiseImage-to-text R@1: 74.6 -> 54.3Hurt
Set soft correspondence labels below a mismatch threshold to zeroBiCro · Flickr30K 40% noiseSumImproved
Use BiCro rather than DECLSGRAF · Flickr30K 60% noiseSum: 450.6 -> 465.7Improved
Use BiCro rather than DECLSGRAF · MS-COCO 1K 60% noiseSum: 502.5 -> 505.8Improved
Use BiCro rather than DECLSGRAF · CC152KSum: 364.3 -> 368.9Improved

Later papers that compared with this method

4 later accepted papers report BiCro as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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