Skip to content

zhengli97/Awesome-Prompt-Adapter-Learning-for-VLMs

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

92 Commits
LICENSE
LICENSE
 
 
README.md
README.md
 
 

Repository files navigation

Awesome-Prompt-Adapter-Learning-for-VLMs

A curated list of prompt/adapter learning methods for vision-language models (e.g., CLIP, ALIGN).

Table of Contents

💡Tips:

  • 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.
  • We would appreciate more people joining us in maintaining this list of papers.
  • Note that papers without open-source code are not recommended.
  • We sincerely thank the following people for contributing to this list: Lingfeng Yang, Ge Wu, Jiazuo Yu, Qiji Ma[List]

Keywords

Use text-based prompts/adapters.

Use image-based prompts/adapters.

Use text- and image-based prompts/adapters.

Surveys

  • A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models. [Paper]
  • Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey. [Paper]

Foundation Models

  • CLIP Learning Transferable Visual Models From Natural Language Supervision. ICML 2021.
    [Paper] [Code]
  • ALIGN Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. ICML 2021.
    [Paper]
  • LiT LiT: Zero-Shot Transfer with Locked-image text Tuning. CVPR 2022.
    [Paper] [Code]
  • EVA-CLIP EVA-CLIP: Improved Training Techniques for CLIP at Scale. 2023.
    [Paper] [Code]
  • SigLIP Sigmoid Loss for Language Image Pre-Training. ICCV 2023.
    [Paper] [Code]
  • AlphaCLIP Alpha-CLIP: A CLIP Model Focusing on Wherever You Want. CVPR 2024.
    [Paper] [Code]
  • CLIP-KD CLIP-KD: An Empirical Study of CLIP Model Distillation. CVPR 2024.
    [Paper] [Code] [论文解读]
  • LongCLIP Long-CLIP: Unlocking the Long-Text Capability of CLIP. ECCV 2024.
    [Paper] [Code]

Datasets

Base-to-Novel: ImageNet-1K, Caltech101, Oxford Pets, StanfordCars, Flowers102, Food101, FGVC Aircraft, SUN397, DTD, EuroSAT, UCF101.

Domain Generalization: ImageNet-V2, ImageNet-Sketch, ImageNet-Adversarial, ImageNet-Rendition.

Due to various factors, the links to some datasets may be outdated or invalid.
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.

[Huggingface_Dataset_Download_Link]

General Prompt Learning

Experimental Comparison

Base-to-Novel Generalization. (ViT-B/16 CLIP)

Methods Paper Pub Base Novel HM (main) Code Type
CLIP Link ICML 21 69.34 74.22 71.70 Link Model
CoOp Link IJCV 22 82.69 63.22 71.66 Link -
ATPrompt Link ICCV 25 82.68 68.04 74.65 Link -
ATPrompt+PromptKD - - 87.05 81.82 84.35 - Plugin
CoCoOp Link CVPR 22 80.47 71.69 75.83 Link -
DPC Link CVPR 25 85.15 68.84 76.13 Link -
DPC+PromptKD - - 87.55 80.55 83.91 - Plugin
ProDA Link CVPR 22 81.56 72.30 76.65 Link -
TextRefiner Link AAAI 25 79.74 74.32 76.94 Link -
TextRefiner+PromptKD - - 85.22 79.64 82.33 - Plugin
KgCoOp Link CVPR 23 80.73 73.60 77.00 Link -
RPO Link ICCV 23 81.13 75.00 77.78 Link -
DePT Link CVPR 24 83.80 72.89 77.97 Link -
DePT+PromptSRC - - 85.19 76.17 80.43 - Plugin
MaPLe Link CVPR 23 82.28 75.14 78.55 Link -
QNet Link ICLR 24 83.32 75.65 79.30 Link -
CasPL Link ECCV 24 84.78 74.49 79.30 Link -
CasPL+PromptSRC - - 86.11 79.54 82.69 - Plugin
TCP Link CVPR 24 84.13 75.36 79.51 Link -
MMA Link CVPR 24 83.20 76.80 79.87 Link -
PromptSRC Link ICCV 23 84.26 76.10 79.97 Link -
2SFS Link CVPR 25 85.55 75.48 80.20 Link -
HPT Link AAAI 24 84.32 76.86 80.23 Link -
CoPrompt Link ICLR 24 84.00 77.23 80.48 Link -
SkipT Link CVPR 25 85.04 77.53 81.11 Link -
MMRL Link CVPR 25 85.68 77.16 81.20 Link -
LLaMP Link CVPR 24 85.16 77.71 81.27 Link -
PromptKD Link CVPR 24 86.96 80.73 83.73 Link -

Table 1. Average results on 11 datasets. (Only works with open-source code will be listed.)

Paper List

2022

  • CoOp Learning to Prompt for Vision-Language Models. IJCV 2022.
    [Paper] [Code]
  • CoCoOp Conditional Prompt Learning for Vision-Language Models. CVPR 2022.
    [Paper] [Code]
  • ProDA Prompt Distribution Learning. CVPR 2022.
    [Paper] [Code]
  • VPT Visual Prompt Tuning. ECCV 2022.
    [Paper] [Code]
  • VP Exploring Visual Prompts for Adapting Large-Scale Models. Arxiv 2022.
    [Paper] [Code]

2023

  • MaPLe MaPLe: Multi-modal Prompt Learning. CVPR 2023.
    [Paper] [Code]
  • KgCoOp Visual-Language Prompt Tuningx with Knowledge-guided Context Optimization. CVPR 2023.
    [Paper] [Code]
  • LASP LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models. CVPR 2023.
    [Paper] [Code]
  • DAM-VP Diversity-Aware Meta Visual Prompting. CVPR 2023.
    [Paper] [Code]
  • TaskRes Task Residual for Tuning Vision-Language Models. CVPR 2023.
    [Paper] [Code]
  • RPO Read-only Prompt Optimization for Vision-Language Few-shot Learning. ICCV 2023.
    [Paper] [Code]
  • KAPT Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models. ICCV 2023.
    [Paper] [Code Not Found]
  • CuPL What does a platypus look like? Generating customized prompts for zero-shot image classification. ICCV 2023.
    [Paper] [Code]
  • ProGrad Prompt-aligned Gradient for Prompt Tuning. ICCV 2023.
    [Paper][Code]
  • PromptSRC Self-regulating Prompts: Foundational Model Adaptation without Forgetting. ICCV 2023.
    [Paper] [Code]
  • LFA Black Box Few-Shot Adaptation for Vision-Language models. ICCV 2023.
    [Paper] [Code]
  • DeFo Learning to Decompose Visual Features with Latent Textual Prompts. ICLR 2023.
    [Paper] [Code Not Found]
  • PLOT PLOT: Prompt Learning with Optimal Transport for Vision-Language Models. ICLR 2023.
    [Paper] [Code]
  • POMP Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition. NeurIPS 2023.
    [Paper] [Code]

2024

  • MetaPrompt Learning Domain Invariant Prompt for Vision-Language Models. TIP 2024.
    [Paper] [Code Not Found]
  • ProVP Progressive Visual Prompt Learning with Contrastive Feature Re-formation. IJCV 2024.
    [Paper] [Code]
  • CoPL CoPL: Contextual Prompt Learning for Vision-Language Understanding. AAAI 2024.
    [Paper] [Code Not Found]
  • SA2VP SA2VP: Spatially Aligned-and-Adapted Visual Prompt. AAAI 2024.
    [Paper] [Code]
  • HPT Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models. AAAI 2024.
    [Paper] [Code]
  • LaViP LaViP: Language-Grounded Visual Prompts. AAAI 2024.
    [Paper] [Code Not Found]
  • CoPrompt Consistency-guided Prompt Learning for Vision-Language Models. ICLR 2024.
    [Paper] [Code]
  • PromptKD PromptKD: Unsupervised Prompt Distillation for Vision Language Models. CVPR 2024.
    [Paper] [Code] [中文版] [论文解读] [视频解读]
  • DePT DePT: Decoupled Prompt Tuning. CVPR 2024.
    [Paper] [Code]
  • ArGue ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models. CVPR 2024.
    [Paper] [Code Not Found]
  • TCP TCP: Textual-based Class-aware Prompt tuning for Visual-Language Model. CVPR 2024.
    [Paper] [Code]
  • MMA MMA: Multi-Modal Adapter for Vision-Language Models. CVPR 2024.
    [Paper] [Code]
  • LLaMP Large Language Models are Good Prompt Learners for Low-Shot Image Classification. CVPR 24.
    [Paper] [Code]
  • KDPL Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation. ECCV 2024.
    [Paper] [Code]
  • CoCoLe Conceptual Codebook Learning for Vision-Language Models. ECCV 2024.
    [Paper] [Code Not Found]
  • CasPL Cascade Prompt Learning for Vision-Language Model Adaptation. ECCV 2024.
    [Paper] [Code] [论文解读]
  • GalLoP GalLoP: Learning Global and Local Prompts for Vision-Language Models. ECCV 2024.
    [Paper] [Code Not Found]
  • AWT AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation. NeurIPS 2024.
    [Paper] [Code]
  • QNet Prompt Learning with Quaternion Networks. ICLR 2024.
    [Paper] [Code(Empty)]
  • QMaPLe Quantized Prompt for Efficient Generalization of Vision-Language Models. ECCV 2024.
    [Paper] [Code(Empty)]

2025

  • TextRefiner TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning. AAAI 2025.
    [Paper] [Code] [论文解读]
  • ProText Learning to Prompt with Text Only Supervision for Vision-Language Models. AAAI 2025.
    [Paper] [Code]
  • FATE FATE: Feature-Adapted Parameter Tuning for Vision-Language Models. AAAI 2025.
    [Paper] [Code Not Found]
  • TAP Tree of Attributes Prompt Learning For Vision Language Models. ICLR 2025.
    [Paper] [Code]
  • DeKg Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning. ICLR 2025.
    [Paper] [Code]
  • MMRL MMRL: Multi-Modal Representation Learning for Vision-Language Models. CVPR 2025.
    [Paper] [Code]
  • DPC DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models. CVPR 2025.
    [Paper] [Code] [论文解读]
  • 2SFS Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages. CVPR 2025.
    [Paper] [Code]
  • SkipT Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves. CVPR 2025.
    [Paper] [Code]
  • NLPrompt NLPrompt: Noise-Label Prompt Learning for Vision-Language Models. CVPR 2025.
    [Paper] [Code]
  • TAC Task-Aware Clustering for Prompting Vision-Language Models. CVPR 2025.
    [Paper] [Code]
  • OpenworldAUC OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning. ICML 2025.
    [Paper] [Code]
  • FM Enhancing Target-unspecific Tasks through a Features Matrix. ICML 2025.
    [Paper] [Code Not Found]
  • SurPL Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models. ICML 2025.
    [Paper] [Code]
  • ATPrompt Advancing Textual Prompt Learning with Anchored Attributes. ICCV 2025.
    [Paper] [Code] [论文解读] [中文版]
  • HicroPL Hierarchical Cross-modal Prompt Learning for Vision-Language Models. ICCV 2025.
    [Paper] [Code]
  • CaPL Causality-guided Prompt Learning for Vision-language Models via Visual Granulation. ICCV 2025.
    [Paper] [Code(Empty)]
  • LwEIB Learning with Enriched Inductive Biases for Vision-Language Models IJCV 2025.
    [Paper] [Code]
  • BIP Bi-modality Individual-aware Prompt tuning for Visual-Language Model. TPAMI 2025.
    [Paper] [Code]
  • DAPT Decouple before Align: Visual Disentanglement Enhances Prompt Tuning. TPAMI 2025.
    [Paper] [Code]
  • Spotlighter Spotlighter: Revisiting Prompt Tuning from a Representative Mining View. EMNLP 2025 Findings.
    [Paper] [Code]
  • VaMP VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models. NeurIPS 2025.
    [Paper] [Code Not Found]
  • KAID KAID: Knowledge-Aware Interactive Distillation for Vision-Language Models. ACM MM 2025.
    [Paper] [Code Not Found] [论文解读]

Another form of Prompt

Paper List

  • CPT CPT: Colorful Prompt Tuning for pre-trained vision-language models. Arxiv 2021.
    [Paper] [Code]
  • DetPro Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model. CVPR 2022.
    [Paper] [Code]
  • PromptDet PromptDet: Towards Open-vocabulary Detection using Uncurated Images. ECCV 2022.
    [Paper] [Code]
  • Visual Prompting via Image Inpainting. NeurIPS 2022.
    [Paper]
  • OVSeg Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP. CVPR 2023.
    [Paper] [Code]
  • LoGoPrompt LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models. ICCV 2023.
    [Paper]
  • RedCircle What does CLIP know about a red circle? Visual prompt engineering for VLMs. ICCV 2023.
    [Paper]]
  • FGVP Fine-Grained Visual Prompting. NeurIPS 2023.
    [Paper] [Code]
  • SoM Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v. Arxiv 2023.
    [Paper] [Code]
  • Alpha-CLIP Alpha-CLIP: A CLIP Model Focusing on Wherever You Want. CVPR 2024.
    [Paper] [Code]
  • ViP-LLaVA Making Large Multimodal Models Understand Arbitrary Visual Prompts. CVPR 2024.
    [Paper] [Code]
  • SSC Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation. ECCV 2024.
    [Paper] [Code]

General Test-time Prompt Learning

Experimental Comparison

Methods Pub ImageNet -A -V2 -R -S Avg. (main) Code
CoOp IJCV 22 71.51 49.71 64.20 75.21 47.99 59.28 Link
CoCoOp CVPR 22 71.02 50.63 64.07 76.18 48.75 59.91 Link
DiffTPT ICCV 23 70.30 55.68 65.10 75.00 46.80 60.65 Link
TPT NeurIPS 22 68.98 54.77 63.45 77.06 47.94 60.81 Link
TPT+CoOp NeurIPS 22 73.61 57.95 66.83 77.27 49.29 62.84 Link
PromptAlign NeurIPS 23 --- 59.37 65.29 79.33 59.37 63.55 Link
TPS+CoOp Arxiv 24 73.73 60.49 66.84 77.44 49.08 65.52 Link
RLCF ICLR 24 73.23 65.45 69.77 83.35 54.74 68.33 Link
RLCF+CoOp ICLR 24 76.05 69.74 70.62 84.51 56.49 70.34 Link
COSMIC CVPR 25 78.19 73.32 69.62 85.60 62.79 72.83 Link

Table 2. Test-time prompt tuning methods on OOD data.

Paper List

  • TPT Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models. NeurIPS 2022.
    [Paper] [Code]
  • SwapPrompt SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models. NeurIPS 2023.
    [Paper]
  • PrompAlign Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization. NeurIPS 2023.
    [Paper] [Code]
  • TPS Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models. Arxiv 2024.
    [Paper] [Code]
  • RLCF Test-time Adaptation with CLIP reward for zero-shot generalization in Vision-Language Models. ICLR 2024.
    [Paper] [Code]
  • InTTA Invariant Test-Time Adaptation for Vision-Language Model Generalization. Arxiv 2024.
    [Paper] [Code]
  • TDA Efficient Test-Time Adaptation of Vision-Language Models. CVPR 2024.
    [Paper] [Code]
  • DMN Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models. CVPR 2024.
    [Paper] [Code]
  • C-TPT C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion. ICLR 2024.
    [Paper] [Code]
  • DynaPrompt DynaPrompt: Dynamic Test-Time Prompt Tuning. ICLR 2025.
    [Paper]
  • R-TPT R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning. CVPR 2025.
    [Paper] [Code]
  • StatA Realistic Test-Time Adaptation of Vision-Language Models. CVPR 2025.
    [Paper] [Code]
  • O-TPT O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models. CVPR 2025.
    [Paper] [Code]
  • COSMIC COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation. CVPR 2025.
    [Paper] [Code]
  • Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models. ICCV 2025. [Paper] [Code(https://github.com/CenturyChen/ICCV25-MCP)]

General Adapter Learning

Paper List

  • CLIP-Adapter CLIP-Adapter: Better Vision-Language Models with Feature Adapters. Arxiv 2021.
    [Paper] [Code]
  • Tip-Adapter Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification. ECCV 2022.
    [Paper] [Code]
  • APE Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement. ICCV 2023.
    [Paper] [Code]
  • CaFoPrompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners. CVPR 2023.
    [Paper] [Code]
  • Meta-Adapter Meta-Adapter: An Online Few-shot Learner for Vision-Language Model. NeurIPS 2023.
    [Paper] [Code]

Video Understanding

Prompt Learning

  • ActionCLIP Actionclip: A new paradigm for video action recognition. arxiv 21.
    [Paper] [Code]
  • VideoPrompt Prompting visual-language models for efficient video understanding. ECCV 2022.
    [Paper] [Code]
  • InTTA Expanding Language-Image Pretrained Models for General Video Recognition. ECCV 2022.
    [Paper] [Code]
  • RePro Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection. ICLR 2023.
    [Paper] [Code]
  • Vita-CLIP Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting. CVPR 2023.
    [Paper] [Code]
  • ViFi-CLIP Fine-tuned CLIP Models are Efficient Video Learners. CVPR 2023.
    [Paper] [Code]
  • OpenVCLIP Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization. ICML 2023.
    [Paper] [Code]
  • M2-CLIP M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition. AAAI 2024.
    [Paper] [Code]
  • ViLT-CLIP ViLT-CLIP: Video and Language Tuning CLIP with Multimodal Prompt Learning and Scenario-Guided Optimization. AAAI 2024.
    [Paper] [Code(None)]
  • FROSTER FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition. ICLR 2024.
    [Paper] [Code]

Adapter Learning

  • BT-Adapter BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning. CVPR 2024.
    [Paper] [Code]

Continual Learning

Prompt Learning

  • L2P Learning to Prompt for Continual Learning. CVPR 2022.
    [Paper] [Code]
  • DualPrompt DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning. ECCV 2022.
    [Paper] [Code]
  • EvoPrompt Evolving Parameterized Prompt Memory for Continual Learning. AAAI 2024.
    [Paper]
  • CPrompt Consistent Prompting for Rehearsal-Free Continual Learning. CVPR 2024.
    [Paper] [Code]
  • DIKI Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models. ECCV 2024.
    [Paper] [Code]

Adapter Learning

  • MoE-Adapters4CL Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters. CVPR 2024.
    [Paper] [Code]
  • SSIAT Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer. CVPR 2024.
    [Paper] [Code]

Others

OOD

  • LoCoOp LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning. NeurIPS 2023.
    [Paper] [Code]
  • DeCoOp DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection. ICML 2024.
    [Paper] [Code]

Point Cloud

  • IDPT Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models. ICCV 2023. [Paper] [Code]
  • PPT Parameter-efficient Prompt Learning for 3D Point Cloud Understanding. ICRA 2024.
    [Paper] [Code]
  • Point-PRC Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis. NeurIPS 2024.
    [Paper] [Code]

BioMedical

  • BiomedCoOp BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models. CVPR 2025.
    [Paper] [Code]

Robot

  • PPL Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation. CVPR 2025.
    [Paper]

Retrival

  • CLIP4clip Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 2022.
    [Paper] [Code]
  • VoP VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval. CVPR 2023.
    [Paper] [Code]
  • DGL DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval. AAAI 2024.
    [Paper] [Code]

About

A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.

Topics

zero-shot-learning few-shot-learning paper-list few-shot-classifcation prompt-learning adapter-learning vision-language-model

Resources

Readme

License

Apache-2.0 license
Activity

Stars

712 stars

Watchers

13 watching

Forks

32 forks
Report repository

Contributors 4