Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization
Lin Zhu, Xinbing Wang, Chenghu Zhou, Nanyang Ye
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 Bayes-CAL cross-modal alignment learning | CLIP ResNet-50 · NICO | accuracy: 96.75 -> 98.33 | Improved |
| add Bayes-CAL cross-modal alignment learning | CLIP ResNet-50 · ColoredCatsDogs | accuracy: 65.00 -> 69.00 | Improved |
| add Bayes-CAL cross-modal alignment learning | CLIP ResNet-50 · PACS | accuracy: 91.81 -> 91.82 | No clear effect |
| add Bayes-CAL cross-modal alignment learning | CLIP ResNet-50 · VLCS | accuracy: 77.14 -> 78.06 | Improved |
| add LE (ablation) | Bayes-CAL · NICO | accuracy: 96.58 -> 98.33 | Improved |
| add LIRM (ablation) | Bayes-CAL · NICO | accuracy: 98.00 -> 98.33 | Improved |
| add Lorth (ablation) | Bayes-CAL · NICO | accuracy: 98.25 -> 98.33 | No clear effect |
| add LE (ablation) | Bayes-CAL · CCD | accuracy: 68.67 -> 69.00 | No clear effect |
| add LIRM (ablation) | Bayes-CAL · CCD | accuracy: 61.33 -> 69.00 | Improved |
| add Lorth (ablation) | Bayes-CAL · CCD | accuracy: 64.33 -> 69.00 | Improved |
| add LE (ablation) | Bayes-CAL · PACS | accuracy: 91.56 -> 91.82 | No clear effect |
| add LIRM (ablation) | Bayes-CAL · PACS | accuracy: 91.77 -> 91.82 | No clear effect |
Closest papers by meaning
- Bayes-CAL: Robust Cross-Modal Alignment by Bayesian Approach for Few-Shot OoD Generalization (IJCV 2025 · similarity 0.89)
- Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations (CVPR 2025 · similarity 0.87)
- Improving Zero-Shot Generalization and Robustness of Multi-Modal Models (CVPR 2023 · similarity 0.86)
- WikiDO: A New Benchmark Evaluating Cross-Modal Retrieval for Vision-Language Models (NeurIPS 2024 · similarity 0.85)
- In Search of Forgotten Domain Generalization (ICLR 2025 · similarity 0.85)
- Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning (NeurIPS 2024 · similarity 0.84)
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.
