Adapting Segment Anything Model for Unseen Object Instance 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_ | 1866909323886592000 |
|---|---|
| author | Cao, Rui Song, Chuanxin Yang, Biqi Wang, Jiangliu Heng, Pheng-Ann Liu, Yun-Hui |
| author_facet | Cao, Rui Song, Chuanxin Yang, Biqi Wang, Jiangliu Heng, Pheng-Ann Liu, Yun-Hui |
| contents | Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining. In this paper, we propose UOIS-SAM, a data-efficient solution for the UOIS task that leverages SAM's high accuracy and strong generalization capabilities. UOIS-SAM integrates two key components: (i) a Heatmap-based Prompt Generator (HPG) to generate class-agnostic point prompts with precise foreground prediction, and (ii) a Hierarchical Discrimination Network (HDNet) that adapts SAM's mask decoder, mitigating issues introduced by the SAM baseline, such as background confusion and over-segmentation, especially in scenarios involving occlusion and texture-rich objects. Extensive experimental results on OCID, OSD, and additional photometrically challenging datasets including PhoCAL and HouseCat6D, demonstrate that, even using only 10% of the training samples compared to previous methods, UOIS-SAM achieves state-of-the-art performance in unseen object segmentation, highlighting its effectiveness and robustness in various tabletop scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15481 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adapting Segment Anything Model for Unseen Object Instance Segmentation Cao, Rui Song, Chuanxin Yang, Biqi Wang, Jiangliu Heng, Pheng-Ann Liu, Yun-Hui Robotics Computer Vision and Pattern Recognition Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining. In this paper, we propose UOIS-SAM, a data-efficient solution for the UOIS task that leverages SAM's high accuracy and strong generalization capabilities. UOIS-SAM integrates two key components: (i) a Heatmap-based Prompt Generator (HPG) to generate class-agnostic point prompts with precise foreground prediction, and (ii) a Hierarchical Discrimination Network (HDNet) that adapts SAM's mask decoder, mitigating issues introduced by the SAM baseline, such as background confusion and over-segmentation, especially in scenarios involving occlusion and texture-rich objects. Extensive experimental results on OCID, OSD, and additional photometrically challenging datasets including PhoCAL and HouseCat6D, demonstrate that, even using only 10% of the training samples compared to previous methods, UOIS-SAM achieves state-of-the-art performance in unseen object segmentation, highlighting its effectiveness and robustness in various tabletop scenes. |
| title | Adapting Segment Anything Model for Unseen Object Instance Segmentation |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.15481 |