PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation
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_ | 1866917572980506624 |
|---|---|
| author | Xie, Zhaozhi Guan, Bochen Jiang, Weihao Yi, Muyang Ding, Yue Lu, Hongtao Zhang, Lei |
| author_facet | Xie, Zhaozhi Guan, Bochen Jiang, Weihao Yi, Muyang Ding, Yue Lu, Hongtao Zhang, Lei |
| contents | The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both sparse and dense prompt levels, improving the segmentation performance of SAM to produce high-quality masks. Experimental results demonstrate that our PA-SAM outperforms other SAM-based methods in high-quality, zero-shot, and open-set segmentation. We're making the source code and models available at https://github.com/xzz2/pa-sam. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13051 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation Xie, Zhaozhi Guan, Bochen Jiang, Weihao Yi, Muyang Ding, Yue Lu, Hongtao Zhang, Lei Computer Vision and Pattern Recognition Image and Video Processing The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both sparse and dense prompt levels, improving the segmentation performance of SAM to produce high-quality masks. Experimental results demonstrate that our PA-SAM outperforms other SAM-based methods in high-quality, zero-shot, and open-set segmentation. We're making the source code and models available at https://github.com/xzz2/pa-sam. |
| title | PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2401.13051 |