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

Weixuan Sun, Zheyuan Liu, Yanhao Zhang, Yiran Zhong, Nick Barnes
5/2/2023
cs.CV

No official code found. Best implementation: weixuansun/wsss_sam (17 stars, MIT, last commit 2024-09-15).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

weixuansun/wsss_samCommunity100%
MIT
171C++, CudaJun 18, 20232 years agoMIT

Cite this paper

@article{sun2023alternative,
  title  = {An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems},
  author = {Weixuan Sun and Zheyuan Liu and Yanhao Zhang and Yiran Zhong and Nick Barnes},
  year   = {2023},
  eprint = {2305.01586},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.01586v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.01586.svg)](https://codeofpaper.com/paper/2305.01586)

Discussion