An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems

The Segment Anything Model (SAM) has demonstrated exceptional performance and versatility, making it a promising tool for various related tasks. In this report, we explore the application of SAM in Weakly-Supervised Semantic Segmentation (WSSS). Particularly, we adapt SAM as the pseudo-label generat...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Sun, Weixuan, Liu, Zheyuan, Zhang, Yanhao, Zhong, Yiran, Barnes, Nick
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 18.06.2023
Subjects
Image segmentation
Performance evaluation
Semantic segmentation
Online AccessGet full text

Cover

More Information
Summary:The Segment Anything Model (SAM) has demonstrated exceptional performance and versatility, making it a promising tool for various related tasks. In this report, we explore the application of SAM in Weakly-Supervised Semantic Segmentation (WSSS). Particularly, we adapt SAM as the pseudo-label generation pipeline given only the image-level class labels. While we observed impressive results in most cases, we also identify certain limitations. Our study includes performance evaluations on PASCAL VOC and MS-COCO, where we achieved remarkable improvements over the latest state-of-the-art methods on both datasets. We anticipate that this report encourages further explorations of adopting SAM in WSSS, as well as wider real-world applications.
ISSN:2331-8422