Research map / Vision-language and multimodal / Cross-modal learning
Self-reinforcing Unsupervised Matching
Jiang Lu, Lei Li, Changshui Zhang
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 |
|---|---|---|---|
| use DPW alignment distance instead of naive point-wise distance (ablation) | DPW · toy matching example | distance: 1118 -> 654 | Improved |
| add self-reinforcing outer SWIM iterations (ablation) | SUM · Chinese character and traffic sign matching | match accuracy: 3--20% | Improved |
| add inner SLoMa iterations within each SWIM iteration (ablation) | SUM · Song->Lishu matching | match accuracy | Improved |
| use larger exploration step size alpha (ablation) | SUM SWIM · Song->Lishu matching | final match accuracy | Hurt |
| use one-by-one exploration (alpha=1) instead of alpha=10 (ablation) | SUM SWIM · Song->Lishu matching | stability | Improved |
| use DPW distance matching instead of point-wise KNN matching (ablation) | SUM · Chinese characters | top-1/top-5 accuracy | Improved |
| add local feature adapter learning instead of plain CNN classifier | SUM · Chinese characters and traffic signs | top-1/top-5 accuracy | Improved |
Closest papers by meaning
- It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data (CVPR 2025 · similarity 0.86)
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data (ICLR 2024 · similarity 0.85)
- Noisy Correspondence Rectification via Asymmetric Similarity Learning (AAAI 2025 · similarity 0.85)
- ReconBoost: Boosting Can Achieve Modality Reconcilement (ICML 2024 · similarity 0.85)
- Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation (CVPR 2024 · similarity 0.85)
- Negative Pre-aware for Noisy Cross-Modal Matching (AAAI 2024 · similarity 0.85)
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.
