Research map / Vision-language and multimodal / Cross-modal learning
Learning with Noisy Correspondence for Cross-modal Matching
Zhenyu Huang, Guocheng Niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, hua wu, Xi Peng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply NCR (co-divide, co-rectify, soft-margin loss) on top of SGR | SGR · Flickr30K 50% noise Image->Text | R@1: 36.9 -> 72.9 | Improved |
| apply NCR instead of training SGR on clean data only (SGR-C) | SGR · Flickr30K 50% noise Image->Text | R@1: 69.8 -> 72.9 | Improved |
| apply NCR to SGR on noise-free data | SGR · Flickr30K 0% noise Image->Text | R@1: 75.2 -> 77.3 | Improved |
| apply NCR on real noisy correspondence | SGR* · CC152K Image->Text | R@1: 35.0 -> 39.5 | Improved |
| pre-train SGR with vanilla triplet loss without hard negatives (SGR*) | SGR · CC152K Image->Text | R@1: 11.3 -> 35.0 | Improved |
| use NCR instead of fine-tuning CLIP ViT-B/32 on noisy MS-COCO | CLIP ViT-B/32 · MS-COCO 5K 50% noise Image->Text | R@1: 10.9 -> 53.1 | Improved |
| extend SCAN with NCR (NCR-SCAN) | SCAN · Flickr30K varying noise 0-60% | avg(R@1,R@5,R@10) | Improved |
Closest papers by meaning
- Noisy Correspondence Rectification via Asymmetric Similarity Learning (AAAI 2025 · similarity 0.93)
- Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation (AAAI 2024 · similarity 0.91)
- Robust Noisy Correspondence Learning with Equivariant Similarity Consistency (CVPR 2024 · similarity 0.91)
- Negative Pre-aware for Noisy Cross-Modal Matching (AAAI 2024 · similarity 0.90)
- Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning (CVPR 2024 · similarity 0.89)
- Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
