---
library_name: transformers
pipeline_tag: image-segmentation
---

# UnSAM: Segment Anything without Supervision

Whole image segmentation model for UnSAM (NeurIPS 2024: https://arxiv.org/pdf/2406.20081). The base model is Mask2Former.

**Code:** https://github.com/frank-xwang/UnSAM


**BibTeX:**

@article{wang2024segment,
  title={Segment anything without supervision},
  author={Wang, XuDong and Yang, Jingfeng and Darrell, Trevor},
  journal={Advances in Neural Information Processing Systems},
  volume={37},
  pages={138731--138755},
  year={2024}
}

@article{yu2025unsamv2,
  title={UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity},
  author={Yu, Junwei and Darrell, Trevor and Wang, XuDong},
  journal={arXiv preprint arXiv:2511.13714},
  year={2025}
}