BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM

arXiv:2402.16338v1 Announce Type: new
Abstract: The Segment Anything Model (SAM), a foundation model pretrained on millions of images and segmentation masks, has significantly advanced semantic segmentation, a fundamental task in computer vision. Despite its strengths, SAM encounters two major challenges. Firstly, it struggles with segmenting specific objects autonomously, as it relies on users to manually input prompts like points or bounding boxes to identify targeted objects. Secondly, SAM faces challenges in excelling at specific downstream tasks, like medical imaging, due …

abstract advanced arxiv challenges computer computer vision cs.cv finetuning foundation foundation model images major masks objects optimization overfitting sam segment segment anything segment anything model segmentation semantic type vision