SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation
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_ | 1866912726994911232 |
|---|---|
| author | Chen, Tianrun Cao, Runlong Yu, Xinda Zhu, Lanyun Ding, Chaotao Ji, Deyi Chen, Cheng Zhu, Qi Xu, Chunyan Mao, Papa Zang, Ying |
| author_facet | Chen, Tianrun Cao, Runlong Yu, Xinda Zhu, Lanyun Ding, Chaotao Ji, Deyi Chen, Cheng Zhu, Qi Xu, Chunyan Mao, Papa Zang, Ying |
| contents | The rapid rise of large-scale foundation models has reshaped the landscape of image segmentation, with models such as Segment Anything achieving unprecedented versatility across diverse vision tasks. However, previous generations-including SAM and its successor-still struggle with fine-grained, low-level segmentation challenges such as camouflaged object detection, medical image segmentation, cell image segmentation, and shadow detection. To address these limitations, we originally proposed SAM-Adapter in 2023, demonstrating substantial gains on these difficult scenarios. With the emergence of Segment Anything 3 (SAM3)-a more efficient and higher-performing evolution with a redesigned architecture and improved training pipeline-we revisit these long-standing challenges. In this work, we present SAM3-Adapter, the first adapter framework tailored for SAM3 that unlocks its full segmentation capability. SAM3-Adapter not only reduces computational overhead but also consistently surpasses both SAM and SAM2-based solutions, establishing new state-of-the-art results across multiple downstream tasks, including medical imaging, camouflaged (concealed) object segmentation, and shadow detection. Built upon the modular and composable design philosophy of the original SAM-Adapter, SAM3-Adapter provides stronger generalizability, richer task adaptability, and significantly improved segmentation precision. Extensive experiments confirm that integrating SAM3 with our adapter yields superior accuracy, robustness, and efficiency compared to all prior SAM-based adaptations. We hope SAM3-Adapter can serve as a foundation for future research and practical segmentation applications. Code, pre-trained models, and data processing pipelines are available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19425 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation Chen, Tianrun Cao, Runlong Yu, Xinda Zhu, Lanyun Ding, Chaotao Ji, Deyi Chen, Cheng Zhu, Qi Xu, Chunyan Mao, Papa Zang, Ying Computer Vision and Pattern Recognition The rapid rise of large-scale foundation models has reshaped the landscape of image segmentation, with models such as Segment Anything achieving unprecedented versatility across diverse vision tasks. However, previous generations-including SAM and its successor-still struggle with fine-grained, low-level segmentation challenges such as camouflaged object detection, medical image segmentation, cell image segmentation, and shadow detection. To address these limitations, we originally proposed SAM-Adapter in 2023, demonstrating substantial gains on these difficult scenarios. With the emergence of Segment Anything 3 (SAM3)-a more efficient and higher-performing evolution with a redesigned architecture and improved training pipeline-we revisit these long-standing challenges. In this work, we present SAM3-Adapter, the first adapter framework tailored for SAM3 that unlocks its full segmentation capability. SAM3-Adapter not only reduces computational overhead but also consistently surpasses both SAM and SAM2-based solutions, establishing new state-of-the-art results across multiple downstream tasks, including medical imaging, camouflaged (concealed) object segmentation, and shadow detection. Built upon the modular and composable design philosophy of the original SAM-Adapter, SAM3-Adapter provides stronger generalizability, richer task adaptability, and significantly improved segmentation precision. Extensive experiments confirm that integrating SAM3 with our adapter yields superior accuracy, robustness, and efficiency compared to all prior SAM-based adaptations. We hope SAM3-Adapter can serve as a foundation for future research and practical segmentation applications. Code, pre-trained models, and data processing pipelines are available. |
| title | SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.19425 |