KaiyangZhou/CoOp

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2221 stars · 233 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A research codebase implementing prompt learning methods (CoOp and CoCoOp) for adapting vision-language models like CLIP to downstream classification datasets. It accompanies CVPR 2022 and IJCV 2022 papers and provides training scripts, dataset loaders, and pre-trained weights.

Use cases

• adapt CLIP to custom image classification datasets via prompt learning
• run few-shot image classification experiments with vision-language models
• reproduce CoOp and CoCoOp paper results
• learn context optimization for multimodal foundation models
• benchmark prompt tuning against linear probing
• fine-tune vision-language models without full model retraining

When to choose

• you want to apply or extend CoOp/CoCoOp prompt learning on CLIP
• you need a reference implementation for few-shot vision-language adaptation research
• you want pre-trained CoOp weights for ImageNet-style classification

When to avoid

• you need a production-ready, actively maintained ML library
• you want general-purpose model training unrelated to vision-language prompt tuning
• you need support for the latest prompt-learning methods beyond CoOp/CoCoOp

Facets

library · maturity maintenance

machine-learning prompt-engineering deep-learning machine-learning computer-vision large-language-models python vision-language-models clip prompt-learning few-shot-learning transfer-learning research-code research gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="KaiyangZhou/CoOp")