GalLoP: Learning Global and Local Prompts for Vision-Language Models

Understand

Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs), e.g.

• CLIP, for few-shot image classification.
• Despite their success, most prompt learning methods trade-off between classification accuracy and robustness, e.g.
• in domain generalization or out-of-distribution (OOD) detection.