Learning From Noisy Correspondence With Tri-Partition for Cross-Modal Matching
Open paper
Benchmark
Model
Rank
Results
cross-modal-retrieval-with-noisy-2
CTPR-SGR
–
R-Sum: 508.7
Image-to-text R@1: 76.2
Image-to-text R@5: 95.8
…
cross-modal-retrieval-with-noisy-3
CTPR-SGR
–
R-Sum: 527
Image-to-text R@1: 79.8
Image-to-text R@5: 96.6
…
Rank counts only results with a code link.