Segment Anything Model is a Good Teacher for Local Feature Learning

arXiv:2309.16992v2 Announce Type: replace-cross
Abstract: Local feature detection and description play an important role in many computer vision tasks, which are designed to detect and describe keypoints in "any scene" and "any downstream task". Data-driven local feature learning methods need to rely on pixel-level correspondence for training, which is challenging to acquire at scale, thus hindering further improvements in performance. In this paper, we propose SAMFeat to introduce SAM (segment anything model), a fundamental model trained on 11 million images, …

arxiv cs.cv cs.lg feature good segment segment anything segment anything model type