├── LICENSE └── README.md /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-Prompt-Adapter-Learning-for-VLMs 2 | A curated list of prompt/adapter learning methods for vision-language models (e.g., CLIP, ALIGN). 3 | 4 | # Table of Contents 5 | 6 | - [Papers](#papers) 7 | - [Surveys](#surveys) 8 | - [Foundation Models](#foundation-models) 9 | - [Datasets](#datasets) 10 | - [General Prompt Learning](#general-prompt-learning) 11 | - [Another form of Prompt](#another-form-of-prompt) 12 | - [General Test-time Prompt Learning](#general-test-time-prompt-learning) 13 | - [General Adapter Learning](#general-adapter-learning) 14 | - [Video Understanding](#video-understanding) 15 | - [Continual Learning](#continual-learning) 16 | - [Others](#others) 17 | 18 | ## 💡Tips: 19 | 20 | - If you know that some papers published in top conferences (CVPR, ICCV, ECCV, ICML, NeurlPS, ICLR) or journals (TPAMI, IJCV, TIP) have not been included in this list, please feel free to contact me at any time, either by sending an email (zhengli97[at]qq.com) or submitting an issue. 21 | - We would appreciate more people joining us in maintaining this list of papers. 22 | - Note that papers without open-source code are not recommended. 23 | - We sincerely thank the following people for contributing to this list: [Lingfeng Yang](https://scholar.google.com/citations?user=RLhH0jwAAAAJ&hl=en), [Ge Wu](https://github.com/Martinser), [Jiazuo Yu](https://scholar.google.com/citations?user=FPoIE0UAAAAJ&hl=zh-CN), [Qiji Ma](https://github.com/StellarOdys2ey)[[List](https://github.com/StellarOdys2ey/Generalizable-Prompt-Learning-for-VLMs)] 24 | 25 | 26 | ## Keywords 27 | 28 | ![](https://img.shields.io/badge/Text-green) Use text-based prompts/adapters. 29 | 30 | ![](https://img.shields.io/badge/Image-orange) Use image-based prompts/adapters. 31 | 32 | ![](https://img.shields.io/badge/Image--Text-blue) Use text- and image-based prompts/adapters. 33 | 34 | ## Surveys 35 | 36 | - A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models. [[Paper](https://arxiv.org/abs/2307.12980)] 37 | - Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey. [[Paper](https://arxiv.org/abs/2402.02242)] 38 | 39 | ## Foundation Models 40 | 41 | - `CLIP` **Learning Transferable Visual Models From Natural Language Supervision.** ICML 2021. 42 | [[Paper](https://arxiv.org/abs/2103.00020)] [[Code](https://github.com/OpenAI/CLIP)] 43 | - `ALIGN` **Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision.** ICML 2021. 44 | [[Paper](https://arxiv.org/abs/2102.05918)] 45 | - `LiT` **LiT: Zero-Shot Transfer with Locked-image text Tuning.** CVPR 2022. 46 | [[Paper](https://arxiv.org/abs/2111.07991)] [[Code](https://github.com/google-research/vision_transformer#lit-models)] 47 | - `EVA-CLIP` **EVA-CLIP: Improved Training Techniques for CLIP at Scale.** 2023. 48 | [[Paper](https://arxiv.org/abs/2303.15389)] [[Code](https://github.com/baaivision/EVA)] 49 | - `SigLIP` **Sigmoid Loss for Language Image Pre-Training.** ICCV 2023. 50 | [[Paper](https://arxiv.org/abs/2303.15343)] [[Code](https://github.com/google-research/big_vision)] 51 | - `AlphaCLIP` **Alpha-CLIP: A CLIP Model Focusing on Wherever You Want.** CVPR 2024. 52 | [[Paper](https://arxiv.org/abs/2312.03818)] [[Code](https://github.com/SunzeY/AlphaCLIP)] 53 | - `CLIP-KD` **CLIP-KD: An Empirical Study of CLIP Model Distillation.** CVPR 2024. 54 | [[Paper](https://arxiv.org/abs/2307.12732)] [[Code](https://github.com/winycg/CLIP-KD)] [[论文解读](https://www.zhihu.com/question/646919153/answer/3553439426)] 55 | - `LongCLIP` **Long-CLIP: Unlocking the Long-Text Capability of CLIP.** ECCV 2024. 56 | [[Paper](https://arxiv.org/abs/2403.15378)] [[Code](https://github.com/beichenzbc/Long-CLIP)] 57 | 58 | ## Datasets 59 | 60 | Base-to-Novel: [ImageNet-1K](https://image-net.org/challenges/LSVRC/2012/index.php), [Caltech101](https://data.caltech.edu/records/mzrjq-6wc02), [Oxford Pets](https://www.robots.ox.ac.uk/~vgg/data/pets/), [StanfordCars](https://ai.stanford.edu/~jkrause/cars/car_dataset.html), [Flowers102](https://www.robots.ox.ac.uk/~vgg/data/flowers/102/), [Food101](https://vision.ee.ethz.ch/datasets_extra/food-101/), [FGVC Aircraft](https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/), [SUN397](http://vision.princeton.edu/projects/2010/SUN/), [DTD](https://www.robots.ox.ac.uk/~vgg/data/dtd/), [EuroSAT](https://github.com/phelber/EuroSAT), [UCF101](https://www.crcv.ucf.edu/data/UCF101.php). 61 | 62 | Domain Generalization: [ImageNet-V2](https://github.com/modestyachts/ImageNetV2), [ImageNet-Sketch](https://github.com/HaohanWang/ImageNet-Sketch), [ImageNet-Adversarial](https://github.com/hendrycks/natural-adv-examples), [ImageNet-Rendition](https://github.com/hendrycks/imagenet-r). 63 | 64 | **Due to various factors, the links to some datasets may be outdated or invalid. 65 | To make it easy for you to download these datasets, we maintain a repository on HuggingFace, which contains all the datasets to be used (except ImageNet). Each dataset also includes the corresponding split_zhou_xx.json file.** 66 | 67 | [[Huggingface_Dataset_Download_Link](https://huggingface.co/zhengli97/prompt_learning_dataset)] 68 | 69 | ## General Prompt Learning 70 | ### Experimental Comparison 71 | 72 | Base-to-Novel Generalization. (ViT-B/16 CLIP) 73 | 74 | | Methods | Paper | Pub | Base | Novel | HM (main) | Code | Type | 75 | | :---: | :---: | :---: | --- | --- | :---: | :--: | :--: | 76 | | CLIP | [Link](https://arxiv.org/abs/2103.00020) | ICML 21 | 69.34 | 74.22 | 71.70 | [Link](https://github.com/openai/CLIP) | Model | 77 | | CoOp | [Link](https://arxiv.org/abs/2203.05557) | IJCV 22 | 82.69 | 63.22 | 71.66 | [Link](https://github.com/kaiyangzhou/coop) | - | 78 | | ATPrompt | [Link](https://arxiv.org/abs/2412.09442) | ICCV 25 | 82.68 | 68.04 | 74.65 | [Link](https://github.com/zhengli97/ATPrompt) | - | 79 | | ATPrompt+PromptKD | - | - | 87.05 | 81.82 | **84.35** | - | Plugin | 80 | | CoCoOp | [Link](https://arxiv.org/abs/2203.05557) | CVPR 22 | 80.47 | 71.69 | 75.83 | [Link](https://github.com/KaiyangZhou/CoOp) | - | 81 | | DPC | [Link](https://arxiv.org/abs/2503.13443) | CVPR 25 | 85.15 | 68.84 | 76.13 | [Link](https://github.com/JREion/DPC) | - | 82 | | DPC+PromptKD | - | - | 87.55 | 80.55 | **83.91** | - | Plugin | 83 | | ProDA | [Link](https://arxiv.org/abs/2205.03340) | CVPR 22 | 81.56 | 72.30 | 76.65 | [Link](https://github.com/bbbdylan/proda) | - | 84 | | TextRefiner | [Link](https://arxiv.org/abs/2412.08176) | AAAI 25 | 79.74 | 74.32 | 76.94 | [Link](https://github.com/xjjxmu/TextRefiner) | - | 85 | | TextRefiner+PromptKD | - | - | 85.22 | 79.64 | **82.33** | - | Plugin | 86 | | KgCoOp | [Link](https://arxiv.org/abs/2303.13283) | CVPR 23 | 80.73 | 73.60 | 77.00 | [Link](https://github.com/htyao89/KgCoOp) | - | 87 | | RPO | [Link](https://arxiv.org/abs/2308.14960) | ICCV 23 | 81.13 | 75.00 | 77.78 | [Link](https://github.com/mlvlab/RPO) | - 88 | | DePT | [Link](https://arxiv.org/abs/2309.07439) | CVPR 24 | 83.80 | 72.89 | 77.97 | [Link](https://github.com/Koorye/DePT) | - | 89 | | DePT+PromptSRC | - | - | 85.19 | 76.17 | **80.43** | - | Plugin | 90 | | MaPLe | [Link](https://arxiv.org/abs/2210.03117) | CVPR 23 | 82.28 | 75.14 | 78.55 | [Link](https://github.com/muzairkhattak/multimodal-prompt-learning) | - | 91 | | QNet | [Link](https://openreview.net/forum?id=dKlxDx2SoS) | ICLR 24 | 83.32 | 75.65 | 79.30 | [Link](https://github.com/SHIBOYA/QNet) | - | 92 | | CasPL | [Link](https://arxiv.org/abs/2409.17805) | ECCV 24 | 84.78 | 74.49 | 79.30 | [Link](https://github.com/megvii-research/CasPL) | - | 93 | | CasPL+PromptSRC | - | - | 86.11 | 79.54 | **82.69** | - | Plugin | 94 | | TCP | [Link](https://arxiv.org/abs/2311.18231) | CVPR 24 | 84.13 | 75.36 | 79.51 | [Link](https://github.com/htyao89/Textual-based_Class-aware_prompt_tuning) | - | 95 | | MMA | [Link](https://openaccess.thecvf.com/content/CVPR2024/papers/Yang_MMA_Multi-Modal_Adapter_for_Vision-Language_Models_CVPR_2024_paper.pdf) | CVPR 24 | 83.20 | 76.80 | 79.87 | [Link](https://github.com/ZjjConan/Multi-Modal-Adapter) | - | 96 | | PromptSRC | [Link](https://arxiv.org/abs/2307.06948) | ICCV 23 | 84.26 | 76.10 | 79.97 | [Link](https://github.com/muzairkhattak/PromptSRC) | - | 97 | | 2SFS | [Link](https://arxiv.org/abs/2503.11609) | CVPR 25 | 85.55 | 75.48 | 80.20 | [Link](https://github.com/FarinaMatteo/rethinking_fewshot_vlms) | - | 98 | | HPT | [Link](https://arxiv.org/abs/2312.06323) | AAAI 24 | 84.32 | 76.86 | 80.23 | [Link](https://github.com/vill-lab/2024-aaai-hpt) | - | 99 | | CoPrompt | [Link](https://arxiv.org/abs/2306.01195) | ICLR 24 | 84.00 | 77.23 | 80.48 | [Link](https://github.com/shuvenduroy/coprompt) | - | 100 | | SkipT | [Link](https://arxiv.org/abs/2412.11509) | CVPR 25 | 85.04 | 77.53 | 81.11 | [Link](https://github.com/Koorye/SkipTuning) | - | 101 | | MMRL | [Link](https://arxiv.org/abs/2503.08497) | CVPR 25 | 85.68 | 77.16 | 81.20 | [Link](https://github.com/yunncheng/MMRL) | - | 102 | | LLaMP | [Link](https://arxiv.org/abs/2312.04076) | CVPR 24 | 85.16 | 77.71 | 81.27 | [Link](https://github.com/zhaohengz/LLaMP) | - | 103 | | PromptKD | [Link](https://arxiv.org/abs/2403.02781) | CVPR 24 | 86.96 | 80.73 | 83.73 | [Link](https://github.com/zhengli97/promptkd) | - | 104 | 105 | Table 1. Average results on 11 datasets. (Only works with open-source code will be listed.) 106 | 107 | ### Paper List 108 | 109 | #### 2022 110 | - `CoOp` **Learning to Prompt for Vision-Language Models.** IJCV 2022. 111 | [[Paper](https://arxiv.org/abs/2203.05557)] [[Code](https://github.com/KaiyangZhou/CoOp)] ![](https://img.shields.io/badge/Text-green) 112 | - `CoCoOp` **Conditional Prompt Learning for Vision-Language Models.** CVPR 2022. 113 | [[Paper](https://arxiv.org/abs/2203.05557)] [[Code](https://github.com/KaiyangZhou/CoOp)] ![](https://img.shields.io/badge/Text-green) 114 | - `ProDA` **Prompt Distribution Learning.** CVPR 2022. 115 | [[Paper](https://arxiv.org/abs/2205.03340)] [[Code](https://github.com/bbbdylan/proda)] ![](https://img.shields.io/badge/Text-green) 116 | - `VPT` **Visual Prompt Tuning**. ECCV 2022. 117 | [[Paper](https://arxiv.org/abs/2203.12119)] [[Code](https://github.com/kmnp/vpt)] ![](https://img.shields.io/badge/Image-orange) 118 | - `VP` **Exploring Visual Prompts for Adapting Large-Scale Models.** Arxiv 2022. 119 | [[Paper](https://arxiv.org/abs/2203.17274)] [[Code](https://github.com/hjbahng/visual_prompting)] ![](https://img.shields.io/badge/Image-orange) 120 | 121 | #### 2023 122 | - `MaPLe` **MaPLe: Multi-modal Prompt Learning.** CVPR 2023. 123 | [[Paper](https://arxiv.org/abs/2210.03117)] [[Code](https://github.com/muzairkhattak/multimodal-prompt-learning)] ![](https://img.shields.io/badge/Image--Text-blue) 124 | - `KgCoOp` **Visual-Language Prompt Tuningx with Knowledge-guided Context Optimization.** CVPR 2023. 125 | [[Paper](https://arxiv.org/abs/2303.13283)] [[Code](https://github.com/htyao89/KgCoOp)] ![](https://img.shields.io/badge/Text-green) 126 | - `LASP` **LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models.** CVPR 2023. 127 | [[Paper](https://arxiv.org/abs/2210.01115)] [[Code](https://github.com/1adrianb/lasp)] ![](https://img.shields.io/badge/Text-green) 128 | - `DAM-VP` **Diversity-Aware Meta Visual Prompting.** CVPR 2023. 129 | [[Paper](https://arxiv.org/abs/2303.08138)] [[Code](https://github.com/shikiw/DAM-VP)] ![](https://img.shields.io/badge/Image-orange) 130 | - `TaskRes` **Task Residual for Tuning Vision-Language Models.** CVPR 2023. 131 | [[Paper](https://arxiv.org/abs/2211.10277)] [[Code](https://github.com/geekyutao/TaskRes)] ![](https://img.shields.io/badge/Text-green) 132 | - `RPO` **Read-only Prompt Optimization for Vision-Language Few-shot Learning.** ICCV 2023. 133 | [[Paper](https://arxiv.org/abs/2308.14960)] [[Code](https://github.com/mlvlab/rpo)] ![](https://img.shields.io/badge/Image--Text-blue) 134 | - `KAPT` **Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models.** ICCV 2023. 135 | [[Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Kan_Knowledge-Aware_Prompt_Tuning_for_Generalizable_Vision-Language_Models_ICCV_2023_paper.pdf)] [Code Not Found] ![](https://img.shields.io/badge/Text-green) 136 | - `CuPL` **What does a platypus look like? Generating customized prompts for zero-shot image classification.** ICCV 2023. 137 | [[Paper](https://arxiv.org/pdf/2209.03320)] [[Code](https://github.com/sarahpratt/CuPL)] ![](https://img.shields.io/badge/Text-green) 138 | - `ProGrad` **Prompt-aligned Gradient for Prompt Tuning.** ICCV 2023. 139 | [[Paper](https://arxiv.org/abs/2205.14865)][[Code](https://github.com/BeierZhu/Prompt-align)] ![](https://img.shields.io/badge/Text-green) 140 | - `PromptSRC` **Self-regulating Prompts: Foundational Model Adaptation without Forgetting.** ICCV 2023. 141 | [[Paper](https://arxiv.org/abs/2307.06948)] [[Code](https://github.com/muzairkhattak/PromptSRC)] ![](https://img.shields.io/badge/Image--Text-blue) 142 | - `LFA` **Black Box Few-Shot Adaptation for Vision-Language models.** ICCV 2023. 143 | [[Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Ouali_Black_Box_Few-Shot_Adaptation_for_Vision-Language_Models_ICCV_2023_paper.pdf)] [[Code](https://github.com/saic-fi/LFA)] 144 | - `DeFo` **Learning to Decompose Visual Features with Latent Textual Prompts.** ICLR 2023. 145 | [[Paper](https://arxiv.org/abs/2210.04287)] [Code Not Found] ![](https://img.shields.io/badge/Text-green) 146 | - `PLOT` **PLOT: Prompt Learning with Optimal Transport for Vision-Language Models.** ICLR 2023. 147 | [[Paper](https://arxiv.org/pdf/2210.01253)] [[Code](https://github.com/CHENGY12/PLOT)] ![](https://img.shields.io/badge/Text-green) 148 | - `POMP` **Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition.** NeurIPS 2023. 149 | [[Paper](https://arxiv.org/abs/2304.04704)] [[Code](https://github.com/amazon-science/prompt-pretraining)] ![](https://img.shields.io/badge/Text-green) 150 | 151 | #### 2024 152 | - `MetaPrompt` **Learning Domain Invariant Prompt for Vision-Language Models.** TIP 2024. 153 | [[Paper](https://arxiv.org/abs/2212.04196)] [Code Not Found] ![](https://img.shields.io/badge/Image--Text-blue) 154 | - `ProVP` **Progressive Visual Prompt Learning with Contrastive Feature Re-formation.** IJCV 2024. 155 | [[Paper](https://arxiv.org/abs/2304.08386)] [[Code](https://github.com/MCG-NJU/ProVP)] ![](https://img.shields.io/badge/Image-orange) 156 | - `CoPL` **CoPL: Contextual Prompt Learning for Vision-Language Understanding.** AAAI 2024. 157 | [[Paper](https://arxiv.org/abs/2307.00910)] [Code Not Found] ![](https://img.shields.io/badge/Text-green) 158 | - `SA2VP` **SA2VP: Spatially Aligned-and-Adapted Visual Prompt.** AAAI 2024. 159 | [[Paper](https://arxiv.org/abs/2312.10376)] [[Code](https://github.com/tommy-xq/SA2VP)] ![](https://img.shields.io/badge/Image-orange) 160 | - `HPT` **Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models.** AAAI 2024. 161 | [[Paper](https://arxiv.org/abs/2312.06323)] [[Code](https://github.com/Vill-Lab/2024-AAAI-HPT)] ![](https://img.shields.io/badge/Image--Text-blue) 162 | - `LaViP` **LaViP: Language-Grounded Visual Prompts.** AAAI 2024. 163 | [[Paper](https://arxiv.org/abs/2312.10945)] [Code Not Found] ![](https://img.shields.io/badge/Image-orange) 164 | - `CoPrompt` **Consistency-guided Prompt Learning for Vision-Language Models.** ICLR 2024. 165 | [[Paper](https://arxiv.org/abs/2306.01195)] [[Code](https://github.com/ShuvenduRoy/CoPrompt)] ![](https://img.shields.io/badge/Image--Text-blue) 166 | - `PromptKD` **PromptKD: Unsupervised Prompt Distillation for Vision Language Models.** CVPR 2024. 167 | [[Paper](https://arxiv.org/abs/2403.02781)] [[Code](https://github.com/zhengli97/PromptKD)] [[中文版](https://github.com/zhengli97/PromptKD/blob/main/docs/PromptKD_chinese_version.pdf)] [[论文解读](https://zhuanlan.zhihu.com/p/684269963)] [[视频解读](https://www.techbeat.net/talk-info?id=915)] ![](https://img.shields.io/badge/Image--Text-blue) 168 | - `DePT` **DePT: Decoupled Prompt Tuning.** CVPR 2024. 169 | [[Paper](https://arxiv.org/abs/2309.07439)] [[Code](https://github.com/Koorye/DePT)] ![](https://img.shields.io/badge/Image--Text-blue) 170 | - `ArGue` **ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models.** CVPR 2024. 171 | [[Paper](https://arxiv.org/abs/2311.16494)] [Code Not Found] ![](https://img.shields.io/badge/Text-green) 172 | - `TCP` **TCP: Textual-based Class-aware Prompt tuning for Visual-Language Model.** CVPR 2024. 173 | [[Paper](https://arxiv.org/abs/2311.18231)] [[Code](https://github.com/htyao89/Textual-based_Class-aware_prompt_tuning)] ![](https://img.shields.io/badge/Text-green) 174 | - `MMA` **MMA: Multi-Modal Adapter for Vision-Language Models.** CVPR 2024. 175 | [[Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Yang_MMA_Multi-Modal_Adapter_for_Vision-Language_Models_CVPR_2024_paper.pdf)] [[Code](https://github.com/ZjjConan/Multi-Modal-Adapter)] ![](https://img.shields.io/badge/Image--Text-blue) 176 | - `LLaMP` **Large Language Models are Good Prompt Learners for Low-Shot Image Classification.** CVPR 24. 177 | [[Paper](https://arxiv.org/abs/2312.04076)] [[Code](https://github.com/zhaohengz/LLaMP)] ![](https://img.shields.io/badge/Image--Text-blue) 178 | - `KDPL` **Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation.** ECCV 2024. 179 | [[Paper](https://arxiv.org/abs/2407.03056)] [[Code](https://github.com/miccunifi/KDPL)] ![](https://img.shields.io/badge/Image--Text-blue) 180 | - `CoCoLe` **Conceptual Codebook Learning for Vision-Language Models.** ECCV 2024. 181 | [[Paper](https://arxiv.org/abs/2407.02350)] [Code Not Found] ![](https://img.shields.io/badge/Image--Text-blue) 182 | - `CasPL` **Cascade Prompt Learning for Vision-Language Model Adaptation.** ECCV 2024. 183 | [[Paper](https://arxiv.org/abs/2409.17805)] [[Code](https://github.com/megvii-research/CasPL)] [[论文解读](https://zhuanlan.zhihu.com/p/867291664)] ![](https://img.shields.io/badge/Image--Text-blue) 184 | - `GalLoP` **GalLoP: Learning Global and Local Prompts for Vision-Language Models.** ECCV 2024. 185 | [[Paper](https://arxiv.org/abs/2407.01400)] [Code Not Found] ![](https://img.shields.io/badge/Image--Text-blue) 186 | - `AWT` **AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation.** NeurIPS 2024. 187 | [[Paper](https://arxiv.org/abs/2407.04603)] [[Code](https://github.com/MCG-NJU/AWT)] ![](https://img.shields.io/badge/Image--Text-blue) 188 | - `QNet` **Prompt Learning with Quaternion Networks.** ICLR 2024. 189 | [[Paper](https://openreview.net/forum?id=dKlxDx2SoS)] [[Code](https://github.com/SHIBOYA/QNet)(Empty)] ![](https://img.shields.io/badge/Image--Text-blue) 190 | - `QMaPLe` **Quantized Prompt for Efficient Generalization of Vision-Language Models.** ECCV 2024. 191 | [[Paper](https://arxiv.org/abs/2407.10704)] [[Code](https://github.com/beyondhtx/QPrompt)(Empty)] 192 | 193 | #### 2025 194 | - `TextRefiner` **TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning.** AAAI 2025. 195 | [[Paper](https://arxiv.org/abs/2412.08176)] [[Code](https://github.com/xjjxmu/TextRefiner)] [[论文解读](https://zhuanlan.zhihu.com/p/15940023585)] ![](https://img.shields.io/badge/Text-green) 196 | - `ProText` **Learning to Prompt with Text Only Supervision for Vision-Language Models.** AAAI 2025. 197 | [[Paper](https://arxiv.org/abs/2401.02418)] [[Code](https://github.com/muzairkhattak/ProText)] ![](https://img.shields.io/badge/Text-green) 198 | - `FATE` **FATE: Feature-Adapted Parameter Tuning for Vision-Language Models.** AAAI 2025. 199 | [[Paper](https://ojs.aaai.org/index.php/AAAI/article/view/32975)] [Code Not Found] ![](https://img.shields.io/badge/Text-green) 200 | - `TAP` **Tree of Attributes Prompt Learning For Vision Language Models.** ICLR 2025. 201 | [[Paper](https://arxiv.org/abs/2410.11201)] [[Code](https://github.com/HHenryD/TAP)]![](https://img.shields.io/badge/Image--Text-blue) 202 | - `DeKg` **Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning.** ICLR 2025. 203 | [[Paper](https://openreview.net/pdf?id=6wOmHdwCC4)] [[Code](https://github.com/cnunlp/DeKg)]![](https://img.shields.io/badge/Text-Green) 204 | - `MMRL` **MMRL: Multi-Modal Representation Learning for Vision-Language Models.** CVPR 2025. 205 | [[Paper](https://arxiv.org/abs/2503.08497)] [[Code](https://github.com/yunncheng/MMRL)] ![](https://img.shields.io/badge/Image--Text-blue) 206 | - `DPC` **DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models.** CVPR 2025. 207 | [[Paper](https://arxiv.org/abs/2503.13443)] [[Code](https://github.com/JREion/DPC)] [[论文解读]](https://mp.weixin.qq.com/s/reOUIzVdIpNDcnX4p5ArOg) ![](https://img.shields.io/badge/Text-green) 208 | - `2SFS` **Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages.** CVPR 2025. 209 | [[Paper](https://arxiv.org/abs/2503.11609)] [[Code](https://github.com/FarinaMatteo/rethinking_fewshot_vlms)] ![](https://img.shields.io/badge/Image--Text-blue) 210 | - `SkipT` **Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves.** CVPR 2025. 211 | [[Paper](https://arxiv.org/abs/2412.11509)] [[Code](https://github.com/Koorye/SkipTuning)] ![](https://img.shields.io/badge/Image--Text-blue) 212 | - `NLPrompt` **NLPrompt: Noise-Label Prompt Learning for Vision-Language Models.** CVPR 2025. 213 | [[Paper](https://arxiv.org/abs/2412.01256)] [[Code](https://github.com/qunovo/NLPrompt)] ![](https://img.shields.io/badge/Text-green) 214 | - `TAC` **Task-Aware Clustering for Prompting Vision-Language Models**. CVPR 2025. 215 | [[Paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Hao_Task-Aware_Clustering_for_Prompting_Vision-Language_Models_CVPR_2025_paper.pdf)] [[Code](https://github.com/FushengHao/TAC)] ![](https://img.shields.io/badge/Image--Text-blue) 216 | - `OpenworldAUC` **OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning.** ICML 2025. 217 | [[Paper](https://arxiv.org/abs/2505.05180)] [[Code](https://github.com/huacong/OpenworldAUC)] ![](https://img.shields.io/badge/Text-green) 218 | - `FM` **Enhancing Target-unspecific Tasks through a Features Matrix.** ICML 2025. 219 | [[Paper](https://arxiv.org/abs/2505.03414)] [Code Not Found] ![](https://img.shields.io/badge/Text-Green) 220 | - `SurPL` **Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models.** ICML 2025. 221 | [[Paper](https://openreview.net/pdf?id=zjG9GRG462)] [[Code](https://github.com/llcllc1997/SurPL)] ![](https://img.shields.io/badge/Image--Text-blue) 222 | - `ATPrompt` **Advancing Textual Prompt Learning with Anchored Attributes.** ICCV 2025. 223 | [[Paper](https://arxiv.org/abs/2412.09442)] [[Code](https://github.com/zhengli97/ATPrompt)] [[论文解读](https://zhuanlan.zhihu.com/p/11787739769)] [[中文版](https://github.com/zhengli97/ATPrompt/blob/main/docs/ATPrompt_chinese_version.pdf)] ![](https://img.shields.io/badge/Text-green) 224 | - `HicroPL` **Hierarchical Cross-modal Prompt Learning for Vision-Language Models.** ICCV 2025. 225 | [[Paper](https://arxiv.org/abs/2507.14976)] [[Code](https://github.com/zzeoZheng/HiCroPL)] ![](https://img.shields.io/badge/Image--Text-blue) 226 | - `CaPL` **Causality-guided Prompt Learning for Vision-language Models via Visual Granulation.** ICCV 2025. 227 | [[Paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Gao_Causality-guided_Prompt_Learning_for_Vision-language_Models_via_Visual_Granulation_ICCV_2025_paper.pdf)] [[Code](https://github.com/GaoMY-521/causality-guided-prompt-learning)(Empty)] ![](https://img.shields.io/badge/Image-orange) 228 | - `LwEIB` **Learning with Enriched Inductive Biases for Vision-Language Models** IJCV 2025. 229 | [[Paper](https://link.springer.com/article/10.1007/s11263-025-02354-1)] [[Code](https://github.com/ZjjConan/VLM-LwEIB)]![](https://img.shields.io/badge/Image--Text-blue) 230 | - `BIP` **Bi-modality Individual-aware Prompt tuning for Visual-Language Model.** TPAMI 2025. 231 | [[Paper](https://ieeexplore.ieee.org/abstract/document/10949734)] [[Code](https://github.com/htyao89/BIP)] ![](https://img.shields.io/badge/Image--Text-blue) 232 | - `DAPT` **Decouple before Align: Visual Disentanglement Enhances Prompt Tuning.** TPAMI 2025. 233 | [[Paper](https://ieeexplore.ieee.org/abstract/document/11106768)] [[Code](https://github.com/Ferenas/DAPT)] ![](https://img.shields.io/badge/Image--Text-blue) 234 | - `Spotlighter` **Spotlighter: Revisiting Prompt Tuning from a Representative Mining View.** EMNLP 2025 Findings. 235 | [[Paper](https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.392.pdf)] [[Code](https://github.com/greatest-gourmet/Spotlighter)] ![](https://img.shields.io/badge/Image--Text-blue) 236 | - `VaMP` **VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models.** NeurIPS 2025. 237 | [[Paper](https://openreview.net/forum?id=8an1xVyKxS)] [Code Not Found] 238 | - `KAID` **KAID: Knowledge-Aware Interactive Distillation for Vision-Language Models.** ACM MM 2025. 239 | [[Paper](https://dl.acm.org/doi/abs/10.1145/3746027.3755008)] [Code Not Found] [[论文解读](https://zhuanlan.zhihu.com/p/1972333513954027010)] ![](https://img.shields.io/badge/Image--Text-blue) 240 | - `AnchorOPT` **AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning.** arxiv 25. 241 | [[Paper](https://arxiv.org/abs/2511.21188)] [[Code](https://github.com/zhengli97/ATPrompt)] ![](https://img.shields.io/badge/Text-green) 242 | 243 | 244 | ## Another form of Prompt 245 | 246 | ### Paper List 247 | 248 | - `CPT` **CPT: Colorful Prompt Tuning for pre-trained vision-language models.** Arxiv 2021. 249 | [[Paper](https://arxiv.org/abs/2109.11797)] [[Code](https://github.com/thunlp/CPT)] ![](https://img.shields.io/badge/Image--Text-blue) 250 | - `DetPro` **Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model.** CVPR 2022. 251 | [[Paper](https://arxiv.org/abs/2203.14940)] [[Code](https://github.com/dyabel/detpro)] ![](https://img.shields.io/badge/Text-green) 252 | - `PromptDet` **PromptDet: Towards Open-vocabulary Detection using Uncurated Images.** ECCV 2022. 253 | [[Paper](https://arxiv.org/abs/2203.16513)] [[Code](https://github.com/fcjian/PromptDet)] ![](https://img.shields.io/badge/Text-green) 254 | - **Visual Prompting via Image Inpainting.** NeurIPS 2022. 255 | [[Paper](https://arxiv.org/abs/2209.00647)] ![](https://img.shields.io/badge/Image-orange) 256 | - `OVSeg` **Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.** CVPR 2023. 257 | [[Paper](https://arxiv.org/abs/2210.04150)] [[Code](https://github.com/facebookresearch/ov-seg)] ![](https://img.shields.io/badge/Image-orange) 258 | - `LoGoPrompt` **LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models.** ICCV 2023. 259 | [[Paper](https://arxiv.org/abs/2309.01155)] ![](https://img.shields.io/badge/Image-orange) 260 | - `RedCircle` **What does CLIP know about a red circle? Visual prompt engineering for VLMs.** ICCV 2023. 261 | [[Paper](http://arxiv.org/abs/2304.06712)]] ![](https://img.shields.io/badge/Image-orange) 262 | - `FGVP` **Fine-Grained Visual Prompting.** NeurIPS 2023. 263 | [[Paper](https://arxiv.org/abs/2306.04356)] [[Code](https://github.com/ylingfeng/FGVP)] ![](https://img.shields.io/badge/Image-orange) 264 | - `SoM` **Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v.** Arxiv 2023. 265 | [[Paper](https://arxiv.org/abs/2310.11441)] [[Code](https://github.com/microsoft/SoM)] ![](https://img.shields.io/badge/Image-orange) 266 | - `Alpha-CLIP` **Alpha-CLIP: A CLIP Model Focusing on Wherever You Want.** CVPR 2024. 267 | [[Paper](https://arxiv.org/abs/2312.03818)] [[Code](https://github.com/SunzeY/AlphaCLIP)] ![](https://img.shields.io/badge/Image-orange) 268 | - `ViP-LLaVA` **Making Large Multimodal Models Understand Arbitrary Visual Prompts.** CVPR 2024. 269 | [[Paper](https://arxiv.org/abs/2312.00784)] [[Code](https://github.com/WisconsinAIVision/ViP-LLaVA)] ![](https://img.shields.io/badge/Image-orange) 270 | - `SSC` **Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation.** ECCV 2024. 271 | [[Paper](https://arxiv.org/abs/2310.13479)] [[Code](https://github.com/fgirbal/segment-select-correct)] ![](https://img.shields.io/badge/Image-orange) 272 | 273 | 274 | ## General Test-time Prompt Learning 275 | 276 | ### Experimental Comparison 277 | 278 | | Methods | Pub | ImageNet | -A | -V2 | -R | -S | Avg. (main) | Code | 279 | |-------------|------------|----------| --- | --- | --- | --- | :---: | --- | 280 | | CoOp | IJCV 22 | 71.51 | 49.71 | 64.20 | 75.21 | 47.99 | 59.28 | [Link](https://github.com/kaiyangzhou/coop) | 281 | | CoCoOp | CVPR 22 | 71.02 | 50.63 | 64.07 | 76.18 | 48.75 | 59.91 | [Link](https://github.com/kaiyangzhou/coop) | 282 | | DiffTPT | ICCV 23 | 70.30 | 55.68 | 65.10 | 75.00 | 46.80 | 60.65 | [Link](https://github.com/chunmeifeng/DiffTPT) | 283 | | TPT | NeurIPS 22 | 68.98 | 54.77 | 63.45 | 77.06 | 47.94 | 60.81 | [Link](https://github.com/azshue/TPT) | 284 | | TPT+CoOp | NeurIPS 22 | 73.61 | 57.95 | 66.83 | 77.27 | 49.29 | 62.84 | [Link](https://github.com/azshue/TPT) | 285 | | PromptAlign | NeurIPS 23 | --- | 59.37 | 65.29 | 79.33 | 59.37 | 63.55 | [Link](https://github.com/jameelhassan/PromptAlign) | 286 | | TPS+CoOp | Arxiv 24 | 73.73 | 60.49 | 66.84 | 77.44 | 49.08 | 65.52 | [Link](https://github.com/elaine-sui/TPS) | 287 | | RLCF | ICLR 24 | 73.23 | 65.45 | 69.77 | 83.35 | 54.74 | 68.33 | [Link](https://github.com/mzhaoshuai/RLCF) | 288 | | RLCF+CoOp | ICLR 24 | 76.05 | 69.74 | 70.62 | 84.51 | 56.49 | 70.34 | [Link](https://github.com/mzhaoshuai/RLCF) | 289 | | COSMIC | CVPR 25 | 78.19 | 73.32 | 69.62 | 85.60 | 62.79 | 72.83 | [Link](https://github.com/hf618/COSMIC) | 290 | 291 | Table 2. Test-time prompt tuning methods on OOD data. 292 | 293 | ### Paper List 294 | 295 | - `TPT` **Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models.** NeurIPS 2022. 296 | [[Paper](https://arxiv.org/abs/2209.07511)] [[Code](https://github.com/azshue/TPT)] 297 | - `SwapPrompt` **SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models.** NeurIPS 2023. 298 | [[Paper](https://openreview.net/forum?id=EhdNQiOWgQ&referrer=%5Bthe%20profile%20of%20Song%20Guo%5D(%2Fprofile%3Fid%3D~Song_Guo5))] 299 | - `PrompAlign` **Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization.** NeurIPS 2023. 300 | [[Paper](https://arxiv.org/abs/2311.01459)] [[Code](https://github.com/jameelhassan/PromptAlign)] 301 | - `TPS` **Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models.** Arxiv 2024. 302 | [[Paper](https://arxiv.org/abs/2403.12952)] [[Code](https://github.com/elaine-sui/TPS)] 303 | - `RLCF` **Test-time Adaptation with CLIP reward for zero-shot generalization in Vision-Language Models.** ICLR 2024. 304 | [[Paper](https://openreview.net/forum?id=kIP0duasBb)] [[Code](https://github.com/mzhaoshuai/RLCF)] 305 | - `InTTA` **Invariant Test-Time Adaptation for Vision-Language Model Generalization.** Arxiv 2024. 306 | [[Paper](https://arxiv.org/abs/2403.00376)] [[Code](https://github.com/MaHuanAAA/InTTA)] 307 | - `TDA` **Efficient Test-Time Adaptation of Vision-Language Models.** CVPR 2024. 308 | [[Paper](https://arxiv.org/abs/2403.18293)] [[Code](https://github.com/kdiAAA/TDA?tab=readme-ov-file)] 309 | - `DMN` **Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models.** CVPR 2024. 310 | [[Paper](https://arxiv.org/abs/2403.17589)] [[Code](https://github.com/YBZh/DMN)] 311 | - `C-TPT` **C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion.** ICLR 2024. 312 | [[Paper](https://arxiv.org/abs/2403.14119)] [[Code](https://github.com/hee-suk-yoon/C-TPT)] 313 | - `DynaPrompt` **DynaPrompt: Dynamic Test-Time Prompt Tuning.** ICLR 2025. 314 | [[Paper](https://openreview.net/forum?id=EFZEdHB3Mp)] 315 | - `R-TPT` **R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning.** CVPR 2025. 316 | [[Paper](https://arxiv.org/abs/2504.11195)] [[Code](https://github.com/TomSheng21/R-TPT)] 317 | - `StatA` **Realistic Test-Time Adaptation of Vision-Language Models.** CVPR 2025. 318 | [[Paper](https://arxiv.org/abs/2501.03729)] [[Code](https://github.com/MaxZanella/StatA)] 319 | - `O-TPT` **O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models.** CVPR 2025. 320 | [[Paper](https://arxiv.org/abs/2503.12096)] [[Code](https://github.com/ashshaksharifdeen/O-TPT)] 321 | - `COSMIC` **COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation.** CVPR 2025. 322 | [[Paper](https://arxiv.org/abs/2503.23388)] [[Code](https://github.com/hf618/COSMIC)] 323 | - **Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models.** ICCV 2025. 324 | [[Paper](https://arxiv.org/abs/2508.01225)] [Code(https://github.com/CenturyChen/ICCV25-MCP)] 325 | 326 | 327 | ## General Adapter Learning 328 | 329 | ### Paper List 330 | 331 | - `CLIP-Adapter` **CLIP-Adapter: Better Vision-Language Models with Feature Adapters.** Arxiv 2021. 332 | [[Paper](https://arxiv.org/abs/2110.04544)] [[Code](https://github.com/gaopengcuhk/CLIP-Adapter)] 333 | - `Tip-Adapter` **Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification.** ECCV 2022. 334 | [[Paper](https://arxiv.org/abs/2207.09519)] [[Code](https://github.com/gaopengcuhk/Tip-Adapter)] 335 | - `APE` **Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement.** ICCV 2023. 336 | [[Paper](https://arxiv.org/abs/2304.01195)] [[Code](https://github.com/yangyangyang127/APE)] 337 | - `CaFo`**Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners.** CVPR 2023. 338 | [[Paper](https://arxiv.org/abs/2303.02151)] [[Code](https://github.com/ZrrSkywalker/CaFo)] 339 | - `Meta-Adapter` **Meta-Adapter: An Online Few-shot Learner for Vision-Language Model.** NeurIPS 2023. 340 | [[Paper](https://arxiv.org/abs/2311.03774)] [[Code](https://github.com/ArsenalCheng/Meta-Adapter)] 341 | 342 | ## Video Understanding 343 | 344 | ### Prompt Learning 345 | - `ActionCLIP` **Actionclip: A new paradigm for video action recognition.** arxiv 21. 346 | [[Paper](https://arxiv.org/abs/2109.08472)] [[Code](https://github.com/sallymmx/ActionCLIP)] 347 | - `VideoPrompt` **Prompting visual-language models for efficient video understanding.** ECCV 2022. 348 | [[Paper](https://arxiv.org/pdf/2112.04478.pdf)] [[Code](https://github.com/ju-chen/Efficient-Prompt)] 349 | - `InTTA` **Expanding Language-Image Pretrained Models for General Video Recognition.** ECCV 2022. 350 | [[Paper](https://arxiv.org/pdf/2208.02816.pdf)] [[Code](https://github.com/microsoft/VideoX/tree/master/X-CLIP)] 351 | - `RePro` **Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection.** ICLR 2023. 352 | [[Paper](https://arxiv.org/pdf/2302.00268.pdf)] [[Code](https://github.com/Dawn-LX/OpenVoc-VidVRD)] 353 | - `Vita-CLIP` **Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting.** CVPR 2023. 354 | [[Paper](https://arxiv.org/abs/2304.03307)] [[Code](https://github.com/TalalWasim/Vita-CLIP)] 355 | - `ViFi-CLIP` **Fine-tuned CLIP Models are Efficient Video Learners.** CVPR 2023. 356 | [[Paper](https://arxiv.org/abs/2212.03640)] [[Code](https://github.com/muzairkhattak/ViFi-CLIP)] 357 | - `OpenVCLIP` **Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization.** ICML 2023. 358 | [[Paper](https://arxiv.org/abs/2302.00624)] [[Code](https://github.com/wengzejia1/Open-VCLIP)] 359 | - `M2-CLIP` **M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition.** AAAI 2024. 360 | [[Paper](https://arxiv.org/abs/2401.11649)] [[Code](https://github.com/sallymmx/m2clip)] 361 | - `ViLT-CLIP` **ViLT-CLIP: Video and Language Tuning CLIP with Multimodal Prompt Learning and Scenario-Guided Optimization.** AAAI 2024. 362 | [[Paper](https://ojs.aaai.org/index.php/AAAI/article/view/28347)] [Code(None)] 363 | - `FROSTER` **FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition.** ICLR 2024. 364 | [[Paper](https://arxiv.org/abs/2402.03241)] [[Code](https://github.com/Visual-AI/FROSTER)] 365 | 366 | ### Adapter Learning 367 | - `BT-Adapter` **BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning.** CVPR 2024. 368 | [[Paper](https://arxiv.org/abs/2309.15785)] [[Code](https://github.com/farewellthree/BT-Adapter)] 369 | 370 | 371 | ## Continual Learning 372 | 373 | ### Prompt Learning 374 | - `L2P` **Learning to Prompt for Continual Learning.** CVPR 2022. 375 | [[Paper](https://arxiv.org/pdf/2112.08654)] [[Code](https://github.com/google-research/l2p)] 376 | - `DualPrompt` **DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning.** ECCV 2022. 377 | [[Paper](https://arxiv.org/pdf/2204.04799)] [[Code](https://github.com/google-research/l2p)] 378 | - `EvoPrompt` **Evolving Parameterized Prompt Memory for Continual Learning.** AAAI 2024. 379 | [[Paper](https://ojs.aaai.org/index.php/AAAI/article/view/29231)] 380 | - `CPrompt` **Consistent Prompting for Rehearsal-Free Continual Learning.** CVPR 2024. 381 | [[Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Gao_Consistent_Prompting_for_Rehearsal-Free_Continual_Learning_CVPR_2024_paper.pdf)] [[Code](https://github.com/Zhanxin-Gao/CPrompt)] 382 | - `DIKI` **Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models.** ECCV 2024. 383 | [[Paper](https://arxiv.org/pdf/2407.05342)] [[Code](https://github.com/lloongx/DIKI)] 384 | 385 | ### Adapter Learning 386 | - `MoE-Adapters4CL` **Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters.** CVPR 2024. 387 | [[Paper](https://arxiv.org/pdf/2403.11549)] [[Code](https://github.com/JiazuoYu/MoE-Adapters4CL)] 388 | - `SSIAT` **Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer.** CVPR 2024. 389 | [[Paper](https://arxiv.org/abs/2403.19979)] [[Code](https://github.com/HAIV-Lab/SSIAT)] 390 | 394 | 395 | ## Others 396 | 397 | ### OOD 398 | - `LoCoOp` **LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning.** NeurIPS 2023. 399 | [[Paper](https://proceedings.neurips.cc/paper_files/paper/2023/file/f0606b882692637835e8ac981089eccd-Paper-Conference.pdf)] [[Code](https://github.com/AtsuMiyai/LoCoOp)] 400 | - `DeCoOp` **DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection.** ICML 2024. 401 | [[Paper](https://arxiv.org/abs/2406.00345)] [[Code](https://github.com/WNJXYK/DeCoOp)] 402 | 403 | ### Point Cloud 404 | - `IDPT` **Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models.** ICCV 2023. 405 | [[Paper](https://arxiv.org/abs/2304.07221)] [[Code](https://github.com/zyh16143998882/ICCV23-IDPT)] 406 | - `PPT` **Parameter-efficient Prompt Learning for 3D Point Cloud Understanding.** ICRA 2024. 407 | [[Paper](https://arxiv.org/abs/2402.15823)] [[Code](https://github.com/auniquesun/PPT)] 408 | - `Point-PRC` **Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis.** NeurIPS 2024. 409 | [[Paper](https://arxiv.org/abs/2410.20406)] [[Code](https://github.com/auniquesun/Point-PRC)] 410 | 411 | ### BioMedical 412 | - `BiomedCoOp` **BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models.** CVPR 2025. 413 | [[Paper](https://arxiv.org/abs/2411.15232)] [[Code](https://github.com/HealthX-Lab/BiomedCoOp)] 414 | 415 | ### Robot 416 | - `PPL` **Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation.** CVPR 2025. 417 | [[Paper](https://www.arxiv.org/abs/2504.00420)] 418 | 419 | ### Retrival 420 | - `CLIP4clip` **Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning.** Neurocomputing 2022. 421 | [[Paper](https://arxiv.org/abs/2104.08860)] [[Code](https://github.com/ArrowLuo/CLIP4Clip)] 422 | - `VoP` **VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval.** CVPR 2023. 423 | [[Paper](https://arxiv.org/abs/2211.12764)] [[Code](https://github.com/bighuang624/VoP)] 424 | - `DGL` **DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval.** AAAI 2024. 425 | [[Paper](https://arxiv.org/abs/2401.10588)] [[Code](https://github.com/knightyxp/DGL)] 426 | --------------------------------------------------------------------------------