AI Paper Atlas

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

Learning with Noisy Correspondence for Cross-modal Matching

Zhenyu Huang, Guocheng Niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, hua wu, Xi Peng

NeurIPS 2021 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 61 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
apply NCR (co-divide, co-rectify, soft-margin loss) on top of SGRSGR · Flickr30K 50% noise Image->TextR@1: 36.9 -> 72.9Improved
apply NCR instead of training SGR on clean data only (SGR-C)SGR · Flickr30K 50% noise Image->TextR@1: 69.8 -> 72.9Improved
apply NCR to SGR on noise-free dataSGR · Flickr30K 0% noise Image->TextR@1: 75.2 -> 77.3Improved
apply NCR on real noisy correspondenceSGR* · CC152K Image->TextR@1: 35.0 -> 39.5Improved
pre-train SGR with vanilla triplet loss without hard negatives (SGR*)SGR · CC152K Image->TextR@1: 11.3 -> 35.0Improved
use NCR instead of fine-tuning CLIP ViT-B/32 on noisy MS-COCOCLIP ViT-B/32 · MS-COCO 5K 50% noise Image->TextR@1: 10.9 -> 53.1Improved
extend SCAN with NCR (NCR-SCAN)SCAN · Flickr30K varying noise 0-60%avg(R@1,R@5,R@10)Improved

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