Learning From Noisy Correspondence With Tri-Partition for Cross-Modal Matching

Benchmark Model Rank Results
cross-modal-retrieval-with-noisy-2CTPR-SGRR-Sum: 508.7Image-to-text R@1: 76.2Image-to-text R@5: 95.8
cross-modal-retrieval-with-noisy-3CTPR-SGRR-Sum: 527Image-to-text R@1: 79.8Image-to-text R@5: 96.6