Task-Aware Low-Rank Adaptation of Segment Anything Model

arXiv:2403.10971v1 Announce Type: new
Abstract: The Segment Anything Model (SAM), with its remarkable zero-shot capability, has been proven to be a powerful foundation model for image segmentation tasks, which is an important task in computer vision. However, the transfer of its rich semantic information to multiple different downstream tasks remains unexplored. In this paper, we propose the Task-Aware Low-Rank Adaptation (TA-LoRA) method, which enables SAM to work as a foundation model for multi-task learning. Specifically, TA-LoRA injects an update parameter …

abstract arxiv capability computer computer vision cs.cv foundation foundation model however image information low low-rank adaptation multiple sam segment segment anything segment anything model segmentation semantic tasks transfer type vision zero-shot