Awesome-CLIP-Zero/Few-shot-Learning

🚀🚀🚀 This repository lists some awesome public projects about Zero-shot/Few-shot Learning based on CLIP (Contrastive Language-Image Pre-Training).

CLIP

• Learning Transferable Visual Models From Natural Language Supervision [CODE]
• CLIP: Connecting Text and Images
• Multimodal Neurons in Artificial Neural Networks
• OpenCLIP: includes larger and independently trained CLIP models up to ViT-G/14
• Hugging Face implementation of CLIP: for easier integration with the HF ecosystem

Few-shot Learning

• [CoOP] Learning to Prompt for Vision-Language Models, IJCV 2022.

• [CLIP-Adapter] CLIP-Adapter: Better Vision-Language Models with Feature Adapters, arXiv 2110.

• [VT-CLIP] VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts, arXiv 2112.

• [CoCoOp] Conditional Prompt Learning for Vision-Language Models, CVPR 2022.

• [ProGrad] Prompt-aligned Gradient for Prompt Tuning, ICCV 2023.

• [SgVA-CLIP] SgVA-CLIP: Semantic-Guided Visual Adapting of Vision-Language Models for Few-Shot Image Classification, IEEE Transactions on Multimedia 202309.

• [Tip-Adapter] Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling, ECCV 2022.

• [CALIP-FS] CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention, AAAI 2023.

• [SuS-X] SuS-X: Training-Free Name-Only Transfer of Vision-Language Models, ICCV 2023.

• [Cross-Modal] Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models, CVPR 2023.

• [CaFo] Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners, CVPR 2023.

• [APE] Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement, ICCV 2023.

• [PRO] Read-only Prompt Optimization for Vision-Language Few-shot Learning, ICCV 2023.

• [Proto-CLIP] Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning, IROS 2024.

• [GraphAdapter] GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph , NeurIPS 2023.

• [Meta-Adapter] Meta-Adapter: An Online Few-shot Learner for Vision-Language Model , NeurIPS 2023.

• [CLAP] CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts, ECCV 2024.

• [MTA] On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?, CVPR 2024.

• [DMN] Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models , CVPR 2024.

• [AMU-Tuning] AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning , CVPR 2024.

• [DAC] Domain Aligned CLIP for Few-shot Classification, WACV 2024.

Zero-shot Learning

• [TPT] Test-Time Prompt Tuning for Zero-shot Generalization in Vision-Language Models , NeurIPS 2022.

• [ProDA] Prompt Distribution Learning, CVPR 2022.

• [DiffTPT] Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning, ICCV 2023.

• [MaPLe] MaPLe: Multi-modal Prompt Learning , CVPR 2023.

• [PromptSRC] Self-regulating Prompts: Foundational Model Adaptation without Forgetting , ICCV 2023.

• [CALIP] CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention, AAAI 2023.

• [CuPL] Generating customized prompts for zero-shot image classification.

• [OnZeta] Online Zero-Shot Classification with CLIP, ECCV 2024.

Fine-tuning

• [WiSE-FT] Robust fine-tuning of zero-shot models, CVPR 2022.