SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912521571532800 |
|---|---|
| author | Xiong, Xinyu Wu, Zihuang Zhang, Lei Lu, Lei Li, Ming Li, Guanbin |
| author_facet | Xiong, Xinyu Wu, Zihuang Zhang, Lei Lu, Lei Li, Ming Li, Guanbin |
| contents | Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance remains an open challenge. In this work, we propose SAM2-UNeXT, an advanced framework that builds upon the core principles of SAM2-UNet while extending the representational capacity of SAM2 through the integration of an auxiliary DINOv2 encoder. By incorporating a dual-resolution strategy and a dense glue layer, our approach enables more accurate segmentation with a simple architecture, relaxing the need for complex decoder designs. Extensive experiments conducted on four benchmarks, including dichotomous image segmentation, camouflaged object detection, marine animal segmentation, and remote sensing saliency detection, demonstrate the superior performance of our proposed method. The code is available at https://github.com/WZH0120/SAM2-UNeXT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks Xiong, Xinyu Wu, Zihuang Zhang, Lei Lu, Lei Li, Ming Li, Guanbin Computer Vision and Pattern Recognition Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance remains an open challenge. In this work, we propose SAM2-UNeXT, an advanced framework that builds upon the core principles of SAM2-UNet while extending the representational capacity of SAM2 through the integration of an auxiliary DINOv2 encoder. By incorporating a dual-resolution strategy and a dense glue layer, our approach enables more accurate segmentation with a simple architecture, relaxing the need for complex decoder designs. Extensive experiments conducted on four benchmarks, including dichotomous image segmentation, camouflaged object detection, marine animal segmentation, and remote sensing saliency detection, demonstrate the superior performance of our proposed method. The code is available at https://github.com/WZH0120/SAM2-UNeXT. |
| title | SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03566 |