AI Paper Atlas

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

Boosting Noisy Correspondence Discrimination via Dynamic Neighborhood Semantic Verification

Yu Wang, Fengxia Han, Jianyu Wang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 0 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
add LRP, SGD and SDD components incrementally (ablation)DNS · Flickr30K, 60% noiserSum: 468.3 -> 497.9Improved
use minimum of contrastive and gap indicators rather than maximum or average (ablation)DNS · Flickr30K, 60% noiserSumImproved
set neighborhood size K to 3 instead of smaller or larger (ablation)DNS · Flickr30K and MS-COCO 1K, 60% noiserSumMixed
use DNS instead of ReCon at 60% noiseReCon · Flickr30K, 60% noiserSum: 489.9 -> 497.9Improved
use DNS instead of ReCon on real-world noiseReCon · CC152KrSum: 380.5 -> 384.1Improved
use DNS instead of ReCon at 20% noiseReCon · MS-COCO 1K, 20% noiserSum: 528.6 -> 530.8Improved
fine-tune CLIP-32 on noisy data vs zero-shotCLIP-32 · MS-COCO 5KrSum: 400.4 -> 236.3 (20% noise)Hurt
DNS under 50% noise versus CLIP zero-shot at 0% noiseDNS · MS-COCO 5KrSum: 400.4 -> 434.3Improved

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