ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning

Benchmark Model Rank Results
cross-modal-retrieval-with-noisy-1ReCon#1R-Sum: 380.5Image-to-text R@1: 43.1Image-to-text R@5: 68.7
cross-modal-retrieval-with-noisy-2ReCon#1R-Sum: 511.8Image-to-text R@1: 80.3Image-to-text R@5: 95.3
cross-modal-retrieval-with-noisy-3ReCon#1R-Sum: 528.6Image-to-text R@1: 80.9Image-to-text R@5: 96.6