SOTAVerified

Cross-modal retrieval with noisy correspondence

Noisy correspondence learning aims to eliminate the negative impact of the mismatched pairs (e.g., false positives/negatives) instead of annotation errors in several tasks.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 20 papers

TitleStatusHype
Cross-Modal Retrieval with Partially Mismatched PairsCode1
Deep Evidential Learning with Noisy Correspondence for Cross-Modal RetrievalCode1
Learning to Rematch Mismatched Pairs for Robust Cross-Modal RetrievalCode1
Integrating Language Guidance Into Image-Text Matching for Correcting False NegativesCode0
NAC: Mitigating Noisy Correspondence in Cross-Modal Matching Via Neighbor Auxiliary Corrector—0
Learning with Noisy Correspondence—0
Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching—0
REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence—0
Learning From Noisy Correspondence With Tri-Partition for Cross-Modal Matching—0
Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.