Research map / Vision-language and multimodal / CLIP and zero-shot
Tip-Adapter: Training-Free Adaption of CLIP for Few-Shot Classification
Renrui Zhang, Wei Zhang, Rongyao Fang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, Hongsheng Li
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 training-free key-value cache model to zero-shot CLIP | Zero-shot CLIP · ImageNet (16-shot) | accuracy (%): 60.33 -> 62.03 | Improved |
| fine-tune the cached keys (Tip-Adapter-F) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 62.03 -> 65.51 | Improved |
| set residual ratio alpha to 1.0 instead of 0.0 (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 60.33 -> 62.03 | Improved |
| raise residual ratio alpha from 1.0 to 4.0 (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 62.03 -> 59.14 | Hurt |
| change sharpness beta from 1.5 to 5.5 (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 61.82 -> 62.03 | No clear effect |
| cache all 16 shots per class instead of none (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 60.33 -> 62.03 | Improved |
| increase training shots from 16 to 128 (cache fixed at 16 prototypes) (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 62.03 -> 63.15 | Improved |
| increase training shots from 16 to 128 (ablation) | Tip-Adapter-F · ImageNet (16-shot) | accuracy (%): 65.47 -> 69.74 | Improved |
| also fine-tune the cached values L_train (ablation) | Tip-Adapter-F · ImageNet (16-shot) | accuracy (%): 65.51 -> 60.90 | Hurt |
| fine-tune CLIP visual encoder instead of keys (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 62.03 -> 62.84 | Mixed |
| fine-tune CLIP textual encoder instead of keys (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 62.03 -> 63.15 | Mixed |
| jointly fine-tune both CLIP encoders (ablation) | Tip-Adapter · ImageNet (16-shot) | accuracy (%): 62.03 -> 51.22 | Hurt |
Later papers that compared with this method
11 later accepted papers report TIP-Adapter as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.
- Exploring Cross-Modal Flows for Few-Shot Learning (ICLR 2026 · better on 1 of 1 shared result)
- Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models (AAAI 2026 · better on 1 of 1 shared result)
- Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning (ICCV 2025 · better on 5 of 5 shared results)
- Adaptive Parameter Selection for Tuning Vision-Language Models (CVPR 2025 · better on 2 of 2 shared results)
- ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models (CVPR 2025 · better on 1 of 1 shared result)
- Bridging the Pathology Domain Gap: Efficiently Adapting CLIP for Pathology Image Analysis with Limited Labeled Data (ECCV 2024 · better on 4 of 4 shared results)
- On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning? (CVPR 2024 · better on 1 of 1 shared result)
- Meta-Adapter: An Online Few-shot Learner for Vision-Language Model (NeurIPS 2023 · better on 7 of 7 shared results)
3 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation (ICLR 2024 · similarity 0.92)
- ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models (CVPR 2025 · similarity 0.91)
- Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge (NeurIPS 2024 · similarity 0.90)
- Post-pre-training for Modality Alignment in Vision-Language Foundation Models (CVPR 2025 · similarity 0.89)
- Demystifying CLIP Data (ICLR 2024 · similarity 0.89)
- PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts (ICLR 2024 · 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.
