SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More
It addresses segmentation challenges in specialized domains like medical imaging and low-level vision, but is incremental as it builds on prior adapter work for SAM.
The paper tackles limitations of Segment Anything 2 (SAM2) in complex segmentation tasks like camouflage, shadow, and medical imaging by introducing SAM2-Adapter, achieving new state-of-the-art results in these specific downstream tasks.
The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2), a successor with enhanced architecture and a larger training corpus, we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/