Papers with Code · CC BY-SA 4.0

Cross-modal retrieval with noisy correspondence

Image Retrieval with Multi-Modal Query › Cross-Modal Retrieval › Cross-modal retrieval with noisy correspondence 48 평가 기록 3 datasets

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.

논문

Learning with Noisy Correspondence

2024-04-13 이 페이지의 평가 2건
Image-to-text R@1: 39.5Image-to-text R@5: 64.0Image-to-text R@10: 73.1Text-to-image R@1: 40.6