Noisy Correspondence Learning with Meta Similarity Correction

Benchmark Model Rank Results
cross-modal-retrieval-with-noisy-1MSCN#8R-Sum: 366.7Image-to-text R@1: 40.1Image-to-text R@5: 65.7
cross-modal-retrieval-with-noisy-2MSCN#8R-Sum: 501.9Image-to-text R@1: 77.4Image-to-text R@5: 94.9
cross-modal-retrieval-with-noisy-3MSCN#7R-Sum: 524.6Image-to-text R@1: 78.1Image-to-text R@5: 97.2