RobustSAM: Segment Anything Robustly on Degraded Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914833931173888 |
|---|---|
| author | Chen, Wei-Ting Vong, Yu-Jiet Kuo, Sy-Yen Ma, Sizhuo Wang, Jian |
| author_facet | Chen, Wei-Ting Vong, Yu-Jiet Kuo, Sy-Yen Ma, Sizhuo Wang, Jian |
| contents | Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images with degraded quality. Addressing this limitation, we propose the Robust Segment Anything Model (RobustSAM), which enhances SAM's performance on low-quality images while preserving its promptability and zero-shot generalization. Our method leverages the pre-trained SAM model with only marginal parameter increments and computational requirements. The additional parameters of RobustSAM can be optimized within 30 hours on eight GPUs, demonstrating its feasibility and practicality for typical research laboratories. We also introduce the Robust-Seg dataset, a collection of 688K image-mask pairs with different degradations designed to train and evaluate our model optimally. Extensive experiments across various segmentation tasks and datasets confirm RobustSAM's superior performance, especially under zero-shot conditions, underscoring its potential for extensive real-world application. Additionally, our method has been shown to effectively improve the performance of SAM-based downstream tasks such as single image dehazing and deblurring. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09627 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RobustSAM: Segment Anything Robustly on Degraded Images Chen, Wei-Ting Vong, Yu-Jiet Kuo, Sy-Yen Ma, Sizhuo Wang, Jian Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images with degraded quality. Addressing this limitation, we propose the Robust Segment Anything Model (RobustSAM), which enhances SAM's performance on low-quality images while preserving its promptability and zero-shot generalization. Our method leverages the pre-trained SAM model with only marginal parameter increments and computational requirements. The additional parameters of RobustSAM can be optimized within 30 hours on eight GPUs, demonstrating its feasibility and practicality for typical research laboratories. We also introduce the Robust-Seg dataset, a collection of 688K image-mask pairs with different degradations designed to train and evaluate our model optimally. Extensive experiments across various segmentation tasks and datasets confirm RobustSAM's superior performance, especially under zero-shot conditions, underscoring its potential for extensive real-world application. Additionally, our method has been shown to effectively improve the performance of SAM-based downstream tasks such as single image dehazing and deblurring. |
| title | RobustSAM: Segment Anything Robustly on Degraded Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2406.09627 |