SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909990470549504 |
|---|---|
| author | Shen, Ruiqi Liu, Chang Ding, Henghui |
| author_facet | Shen, Ruiqi Liu, Chang Ding, Henghui |
| contents | Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its original implementation, its group-level collective memory selection is suboptimal for complex multi-object scenarios, as it employs a synchronized decision across all concurrent targets conditioned on their average performance, often overlooking individual reliability. To this end, we propose SAM3-DMS, a training-free decoupled strategy that utilizes fine-grained memory selection on individual objects. Experiments demonstrate that our approach achieves robust identity preservation and tracking stability. Notably, our advantage becomes more pronounced with increased target density, establishing a solid foundation for simultaneous multi-target video segmentation in the wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09699 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3 Shen, Ruiqi Liu, Chang Ding, Henghui Computer Vision and Pattern Recognition Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its original implementation, its group-level collective memory selection is suboptimal for complex multi-object scenarios, as it employs a synchronized decision across all concurrent targets conditioned on their average performance, often overlooking individual reliability. To this end, we propose SAM3-DMS, a training-free decoupled strategy that utilizes fine-grained memory selection on individual objects. Experiments demonstrate that our approach achieves robust identity preservation and tracking stability. Notably, our advantage becomes more pronounced with increased target density, establishing a solid foundation for simultaneous multi-target video segmentation in the wild. |
| title | SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.09699 |