SAMAug: Point Prompt Augmentation for Segment Anything Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dai, Haixing, Ma, Chong, Yan, Zhiling, Liu, Zhengliang, Shi, Enze, Li, Yiwei, Shu, Peng, Wei, Xiaozheng, Zhao, Lin, Wu, Zihao, Zeng, Fang, Zhu, Dajiang, Liu, Wei, Li, Quanzheng, Sun, Lichao, Liu, Shu Zhang Tianming, Li, Xiang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910372287479808
author Dai, Haixing
Ma, Chong
Yan, Zhiling
Liu, Zhengliang
Shi, Enze
Li, Yiwei
Shu, Peng
Wei, Xiaozheng
Zhao, Lin
Wu, Zihao
Zeng, Fang
Zhu, Dajiang
Liu, Wei
Li, Quanzheng
Sun, Lichao
Liu, Shu Zhang Tianming
Li, Xiang
author_facet Dai, Haixing
Ma, Chong
Yan, Zhiling
Liu, Zhengliang
Shi, Enze
Li, Yiwei
Shu, Peng
Wei, Xiaozheng
Zhao, Lin
Wu, Zihao
Zeng, Fang
Zhu, Dajiang
Liu, Wei
Li, Quanzheng
Sun, Lichao
Liu, Shu Zhang Tianming
Li, Xiang
contents This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about the user's intention to SAM. Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts. By incorporating these extra points, SAM can generate augmented segmentation masks based on both the augmented point prompts and the initial prompt, resulting in improved segmentation performance. We conducted evaluations using four different point augmentation strategies: random sampling, sampling based on maximum difference entropy, maximum distance, and saliency. Experiment results on the COCO, Fundus, COVID QUEx, and ISIC2018 datasets show that SAMAug can boost SAM's segmentation results, especially using the maximum distance and saliency. SAMAug demonstrates the potential of visual prompt augmentation for computer vision. Codes of SAMAug are available at github.com/yhydhx/SAMAug
format Preprint
id arxiv_https___arxiv_org_abs_2307_01187
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SAMAug: Point Prompt Augmentation for Segment Anything Model
Dai, Haixing
Ma, Chong
Yan, Zhiling
Liu, Zhengliang
Shi, Enze
Li, Yiwei
Shu, Peng
Wei, Xiaozheng
Zhao, Lin
Wu, Zihao
Zeng, Fang
Zhu, Dajiang
Liu, Wei
Li, Quanzheng
Sun, Lichao
Liu, Shu Zhang Tianming
Li, Xiang
Computer Vision and Pattern Recognition
Artificial Intelligence
This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about the user's intention to SAM. Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts. By incorporating these extra points, SAM can generate augmented segmentation masks based on both the augmented point prompts and the initial prompt, resulting in improved segmentation performance. We conducted evaluations using four different point augmentation strategies: random sampling, sampling based on maximum difference entropy, maximum distance, and saliency. Experiment results on the COCO, Fundus, COVID QUEx, and ISIC2018 datasets show that SAMAug can boost SAM's segmentation results, especially using the maximum distance and saliency. SAMAug demonstrates the potential of visual prompt augmentation for computer vision. Codes of SAMAug are available at github.com/yhydhx/SAMAug
title SAMAug: Point Prompt Augmentation for Segment Anything Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2307.01187