Task-Aware Low-Rank Adaptation of Segment Anything Model

The Segment Anything Model (SAM) 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.

分割一切模型（Segment Anything Model，SAM）已被证实为计算机视觉领域中图像分割任务这一重要研究方向的强大基础模型。然而，如何将其蕴含的丰富语义信息迁移至多种不同下游任务中，目前仍未得到充分探索。本文提出任务感知低秩适配（Task-Aware Low-Rank Adaptation，TA-LoRA）方法，使SAM能够作为多任务学习的基础模型发挥作用。