Learning with Noisy Correspondence for Cross-modal Matching

Benchmark Model Rank Results
cross-modal-retrieval-with-noisy-1NCR#11R-Sum: 355.6Image-to-text R@1: 39.5Image-to-text R@5: 64.5
cross-modal-retrieval-with-noisy-2NCR#9R-Sum: 496.7Image-to-text R@1: 75.0Image-to-text R@5: 93.9
cross-modal-retrieval-with-noisy-3NCR#10R-Sum: 518.5Image-to-text R@1: 77.7Image-to-text R@5: 95.5