Conditional Prompt Learning for Vision-Language Models

🤖 Plain-English Summary

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. Extensive experiments show that CoCoOp generalizes much better than CoOp to unseen classes, even showing promising transferability beyond a single dataset; and yields stronger domain generalization performance as well.

🔑 Key Findings

• A recently proposed method named Context Optimization (CoOp) introduces the concept of prompt learning—a recent trend in NLP—to the vision domain for adapting pre-trained vision-language models.
• Specifically, CoOp turns context words in a prompt into a set of learnable vectors and, with only a few labeled images for learning, can achieve huge improvements over intensively-tuned manual prompts.
• In our study we identify a critical problem of CoOp: the learned context is not generalizable to wider unseen classes within the same dataset, suggesting that CoOp overfits base classes observed during training.

🔗 Related Resources