What does CLIP know about a red circle? Visual prompt engineering for VLMs
This addresses a bottleneck in adapting VLMs for novel tasks, offering a simple yet effective method for researchers and practitioners in computer vision.
The paper tackles the problem of improving Vision-Language Models like CLIP for discriminative tasks beyond classification by introducing visual prompt engineering, where drawing a red circle around an object directs attention and achieves state-of-the-art in zero-shot referring expressions comprehension and strong performance in keypoint localization.
Large-scale Vision-Language Models, such as CLIP, learn powerful image-text representations that have found numerous applications, from zero-shot classification to text-to-image generation. Despite that, their capabilities for solving novel discriminative tasks via prompting fall behind those of large language models, such as GPT-3. Here we explore the idea of visual prompt engineering for solving computer vision tasks beyond classification by editing in image space instead of text. In particular, we discover an emergent ability of CLIP, where, by simply drawing a red circle around an object, we can direct the model's attention to that region, while also maintaining global information. We show the power of this simple approach by achieving state-of-the-art in zero-shot referring expressions comprehension and strong performance in keypoint localization tasks. Finally, we draw attention to some potential ethical concerns of large language-vision models.