Image-to-text R@1: 78.8Image-to-text R@5: 96.1Image-to-text R@10: 98.6Text-to-image R@1: 63.7
Papers with Code · CC BY-SA 4.0
Cross-modal retrieval with noisy correspondence
Noisy correspondence learning aims to eliminate the negative impact of the mismatched pairs (e.g., false positives/negatives) instead of annotation errors in several tasks.
논문
Image-to-text R@1: 79.6Image-to-text R@5: 96.1Image-to-text R@10: 98.7Text-to-image R@1: 64.7
Image-to-text R@1: 78.9Image-to-text R@5: 96.3Image-to-text R@10: 98.6Text-to-image R@1: 63.3
Image-to-text R@1: 77.0Image-to-text R@5: 95.5Image-to-text R@10: 98.1Text-to-image R@1: 61.3
Image-to-text R@1: 77.5Image-to-text R@5: 95.9Image-to-text R@10: 98.4Text-to-image R@1: 61.7
Image-to-text R@1: 80.2Image-to-text R@5: 96.3Image-to-text R@10: 98.5Text-to-image R@1: 64.2
Image-to-text R@1: 79.5Image-to-text R@5: 96.4Image-to-text R@10: 98.9Text-to-image R@1: 64.4
Image-to-text R@1: 80.3Image-to-text R@5: 96.2Image-to-text R@10: 98.5Text-to-image R@1: 63.2
Image-to-text R@1: 78.1Image-to-text R@5: 97.2Image-to-text R@10: 98.8Text-to-image R@1: 64.3
Image-to-text R@1: 78.5Image-to-text R@5: 96.8Image-to-text R@10: 98.8Text-to-image R@1: 63.8
Image-to-text R@1: 80.9Image-to-text R@5: 96.6Image-to-text R@10: 98.8Text-to-image R@1: 65.2
Image-to-text R@1: 78.3Image-to-text R@5: 96.8Image-to-text R@10: 98.3Text-to-image R@1: 62.5
Image-to-text R@1: 79.5Image-to-text R@5: 97.2Image-to-text R@10: 99.0Text-to-image R@1: 63.7
Image-to-text R@1: 79.6Image-to-text R@5: 96.5Image-to-text R@10: 98.5Text-to-image R@1: 64.4
Image-to-text R@1: 79.8Image-to-text R@5: 96.6Image-to-text R@10: 98.9Text-to-image R@1: 63.8
Image-to-text R@1: 78.2Image-to-text R@5: 95.8Image-to-text R@10: 98.5Text-to-image R@1: 62.6
Image-to-text R@1: 77.7Image-to-text R@5: 95.5Image-to-text R@10: 98.2Text-to-image R@1: 62.5