SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation

TL;DR

SAM3-Adapter enhances the Segment Anything 3 model for fine-grained segmentation tasks, achieving state-of-the-art results in challenging areas like medical imaging, camouflage detection, and shadow analysis with improved efficiency and adaptability.

Contribution

This work introduces SAM3-Adapter, the first adapter framework for SAM3, significantly improving segmentation accuracy, efficiency, and generalizability across diverse complex tasks.

Findings

Surpasses SAM and SAM2-based solutions in multiple tasks

Achieves new state-of-the-art results in medical, camouflage, and shadow segmentation

Reduces computational overhead while improving accuracy

Abstract

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.