The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both sparse and dense prompt levels, improving the segmentation performance of SAM to produce high-quality masks. Experimental results demonstrate that our PA-SAM outperforms other SAM-based methods in high-quality, zero-shot, and open-set segmentation. We're making the source code and models available at https://github.com/xzz2/pa-sam.
@article{arxiv.2401.13051,
title = {PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation},
author = {Zhaozhi Xie and Bochen Guan and Weihao Jiang and Muyang Yi and Yue Ding and Hongtao Lu and Lei Zhang},
journal= {arXiv preprint arXiv:2401.13051},
year = {2024}
}
Comments
Code is available at https://github.com/xzz2/pa-sam