EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Weakly-supervised Semantic Segmentation with Image-level Labels: From Traditional Models to Foundation Models

Zhaozheng Chen, Qianru Sun

ACM Computing Surveys · 2025-05-31 · 57 (5) · 1-29

DOI: 10.1145/3707447 ↗

At a glance

Journal article in ACM Computing Surveys, published online on 2025-01-09. Written by Zhaozheng Chen and 1 co-authors. Cited 35 times so far (Crossref); 127 references. The full text is freely available (open access, CC BY 4.0). Funded by: DSO National Laboratories, Singapore.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The rapid development of deep learning has driven significant progress in image semantic segmentation—a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e., masks of objects), which are expensive, time consuming, and labor intensive. Weakly supervised semantic segmentation (WSSS) is an effective solution to avoid such labeling. It utilizes only partial or incomplete annotations and provides a cost-effective alternative to fully supervised semantic segmentation. In this article, our focus is on the WSSS with image-level labels, which is the most challenging form of WSSS. Our work has two parts. First, we conduct a comprehensive survey on traditional methods, primarily focusing on those presented at premier research conferences. We categorize them into four groups based on where their methods operate: pixel-wise, image-wise, cross-image, and external data. Second, we investigate the applicability of visual foundation models, such as the Segment Anything Model (SAM), in the context of WSSS. We scrutinize SAM in two intriguing scenarios: text prompting and zero-shot learning. We provide insights into the potential and challenges of deploying visual foundational models for WSSS, facilitating future developments in this exciting research area. Our code is provided at this link: https://github.com/zhaozhengChen/SAM_WSSS .

Funding

  • DSO National Laboratories, Singapore

Cite

APA

Chen, Z., & Sun, Q. (2025). Weakly-supervised Semantic Segmentation with Image-level Labels: From Traditional Models to Foundation Models. ACM Computing Surveys, 57(5), 1-29. https://doi.org/10.1145/3707447

Vancouver

Chen Z, Sun Q. Weakly-supervised Semantic Segmentation with Image-level Labels: From Traditional Models to Foundation Models. ACM Computing Surveys. 2025;57(5):1-29. doi:10.1145/3707447

BibTeX
@article{Chen2025,
  author = {Chen, Zhaozheng and Sun, Qianru},
  title = {Weakly-supervised Semantic Segmentation with Image-level Labels: From Traditional Models to Foundation Models},
  journal = {ACM Computing Surveys},
  year = {2025},
  volume = {57},
  number = {5},
  pages = {1--29},
  doi = {10.1145/3707447}
}
Start for free →