SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910562569420800 |
|---|---|
| author | Chen, Tianrun Lu, Ankang Zhu, Lanyun Ding, Chaotao Yu, Chunan Ji, Deyi Li, Zejian Sun, Lingyun Mao, Papa Zang, Ying |
| author_facet | Chen, Tianrun Lu, Ankang Zhu, Lanyun Ding, Chaotao Yu, Chunan Ji, Deyi Li, Zejian Sun, Lingyun Mao, Papa Zang, Ying |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04579 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More Chen, Tianrun Lu, Ankang Zhu, Lanyun Ding, Chaotao Yu, Chunan Ji, Deyi Li, Zejian Sun, Lingyun Mao, Papa Zang, Ying Computer Vision and Pattern Recognition 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/ |
| title | SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.04579 |