Research map / Label-efficient and robust learning / Recognition and long-tail
Bootstrapping Multi-view Learning for Test-time Noisy Correspondence
Changhao He, Di Xue, Shuxian Li, Yanji Hao, Xi Peng, Peng Hu
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 |
|---|---|---|---|
| add reveal-supervised loss Lw with bootstrapped noise supervision (ablation) | BML · 7 datasets avg, 50% TNC | accuracy: 71.77 -> 79.38 | Improved |
| add inter-view prediction discrepancy J as estimator input (ablation) | BML · 7 datasets avg, 50% TNC | accuracy: 78.35 -> 79.38 | Improved |
| add intra-view predictive uncertainty Q as estimator input (ablation) | BML · 7 datasets avg, 50% TNC | accuracy: 79.14 -> 79.38 | Improved |
| resample noise-augmented set on the fly each epoch (ablation) | BML · 7 datasets avg, 50% TNC | accuracy: 74.25 -> 79.38 | Improved |
| apply estimated view reliabilities in fusion (ablation) | BML · Fashion, TNC | accuracy: 90.75 -> 94.15 | Improved |
| add Q on top of full model on Leaves (ablation) | BML · Leaves, 50% TNC | accuracy: 96.06 -> 96.16 | No clear effect |
| add Q on top of full model on HW (ablation) | BML · HW, 50% TNC | accuracy: 97.17 -> 97.28 | No clear effect |
| use BML on clean test data (0% TNC) | BML · Caltech/Leaves/HW/LandUse/Scene avg | accuracy: 89.38 (FUML) -> 92.45 | Improved |
| use BML under 100% TNC vs best baseline | BML · five feature datasets avg | accuracy: 78.11 (FUML) -> 85.39 | Improved |
Closest papers by meaning
- Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation (AAAI 2026 · similarity 0.86)
- Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping (ICLR 2025 · similarity 0.86)
- BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception (ICML 2026 · similarity 0.85)
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising (CVPR 2024 · similarity 0.85)
- MVVBench: Benchmarking 4D Reasoning in Vision-Language Models (NeurIPS 2026 · similarity 0.85)
- Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models (AAAI 2025 · 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.
