Visual Prompting via Image Inpainting
This provides a flexible method for computer vision practitioners to apply models to diverse tasks without retraining, though it is incremental as it builds on NLP prompting ideas.
The paper tackles adapting pre-trained visual models to new tasks without task-specific fine-tuning by introducing visual prompting via image inpainting, achieving effective results on tasks like segmentation and detection using a dataset of 88k unlabeled figures.
How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by prompting in NLP, this paper investigates visual prompting: given input-output image example(s) of a new task at test time and a new input image, the goal is to automatically produce the output image, consistent with the given examples. We show that posing this problem as simple image inpainting - literally just filling in a hole in a concatenated visual prompt image - turns out to be surprisingly effective, provided that the inpainting algorithm has been trained on the right data. We train masked auto-encoders on a new dataset that we curated - 88k unlabeled figures from academic papers sources on Arxiv. We apply visual prompting to these pretrained models and demonstrate results on various downstream image-to-image tasks, including foreground segmentation, single object detection, colorization, edge detection, etc.