Research map / Label-efficient and robust learning / Test-time adaptation
Learning to Memorize with Attributive and Associative Memory for Online Test-Time Adaptation of Vision-Language Models
Yuchao Zhang, Hao Wang, Fan Zhang, Qirui Mi, Mengyue Yang, Yisen Wang, Jun Wang, Haoxuan Li, Zhouchen Lin
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 prior textual representation T (ablation) | A2Memory · ImageNet OOD benchmark (OOD avg) (ViT-B/16) | top-1 accuracy: 63.80 -> 65.99 | Improved |
| add prior textual representation T (ablation) | A2Memory · Cross-dataset generalization (10 datasets, avg) (ViT-B/16) | top-1 accuracy: 68.50 -> 71.41 | Improved |
| add surrogate visual representation via soft assignment (ablation) | A2Memory · ImageNet OOD benchmark (OOD avg) (ViT-B/16) | top-1 accuracy: 64.12 -> 65.99 | Improved |
| add surrogate visual representation via soft assignment (ablation) | A2Memory · Cross-dataset generalization (10 datasets, avg) (ViT-B/16) | top-1 accuracy: 69.45 -> 71.41 | Improved |
| add class-wise associative memory (ablation) | A2Memory · ImageNet OOD benchmark (OOD avg) (ViT-B/16) | top-1 accuracy: 63.45 -> 65.99 | Improved |
| add class-wise associative memory (ablation) | A2Memory · Cross-dataset generalization (10 datasets, avg) (ViT-B/16) | top-1 accuracy: 68.95 -> 71.41 | Improved |
| use entropy-adaptive retention instead of fixed alpha 0.9 (ablation) | A2Memory · ImageNet OOD benchmark (OOD avg) (ViT-B/16) | top-1 accuracy: 64.23 -> 65.99 | Improved |
| use entropy-adaptive retention instead of random update (ablation) | A2Memory · ImageNet OOD benchmark (OOD avg) (ViT-B/16) | top-1 accuracy: 41.55 -> 65.99 | Improved |
| use entropy-adaptive retention instead of cumulative average (ablation) | A2Memory · ImageNet OOD benchmark (OOD avg) (ViT-B/16) | top-1 accuracy: 59.90 -> 65.99 | Improved |
| fuse memory branch with CLIP zero-shot branch (ablation) | A2Memory · ImageNet (ViT-B/16) | top-1 accuracy: 71.34 -> 72.21 | Improved |
| use GPT-4o attributes instead of hand-crafted templates (ablation) | A2Memory · Cross-dataset generalization (10 datasets, avg) 100% stream (ViT-B/16) | top-1 accuracy: 71.09 -> 71.53 | Improved |
| replace ADAPT with A2Memory | ADAPT · Cross-dataset generalization (10 datasets, avg) (ViT-B/16) | top-1 accuracy: 70.76 -> 71.41 | Improved |
Closest papers by meaning
- Efficient Test-Time Adaptation of Vision-Language Models (CVPR 2024 · similarity 0.91)
- DOTA: Distributional Test-time Adaptation of Vision-Language Models (NeurIPS 2025 · similarity 0.90)
- Frustratingly Easy Test-Time Adaptation of Vision-Language Models (NeurIPS 2024 · similarity 0.90)
- Bayesian Test-Time Adaptation for Vision-Language Models (CVPR 2025 · similarity 0.90)
- Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts (NeurIPS 2026 · similarity 0.89)
- The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models (NeurIPS 2025 · similarity 0.89)
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.
