Learning with Noisy Correspondence

Benchmark Model Rank Results
cross-modal-retrieval-with-noisy-1LNCR-Sum: 355.5Image-to-text R@1: 39.5Image-to-text R@5: 64.0
cross-modal-retrieval-with-noisy-2LNCR-Sum: 498.9Image-to-text R@1: 76.3Image-to-text R@5: 93.7
cross-modal-retrieval-with-noisy-3LNCR-Sum: 519.9Image-to-text R@1: 78.2Image-to-text R@5: 95.8