SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915506508791808 |
|---|---|
| author | Xie, Yujie Zhang, Hongyang Liu, Zhihui Ruan, Shihai |
| author_facet | Xie, Yujie Zhang, Hongyang Liu, Zhihui Ruan, Shihai |
| contents | Large-scale Video Object Segmentation (LSVOS) addresses the challenge of accurately tracking and segmenting objects in long video sequences, where difficulties stem from object reappearance, small-scale targets, heavy occlusions, and crowded scenes. Existing approaches predominantly adopt SAM2-based frameworks with various memory mechanisms for complex video mask generation. In this report, we proposed Segment Anything with Memory Strengthened Object Navigation (SAMSON), the 3rd place solution in the MOSE track of ICCV 2025, which integrates the strengths of stateof-the-art VOS models into an effective paradigm. To handle visually similar instances and long-term object disappearance in MOSE, we incorporate a long-term memorymodule for reliable object re-identification. Additionly, we adopt SAM2Long as a post-processing strategy to reduce error accumulation and enhance segmentation stability in long video sequences. Our method achieved a final performance of 0.8427 in terms of J &F in the test-set leaderboard. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17500 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge Xie, Yujie Zhang, Hongyang Liu, Zhihui Ruan, Shihai Computer Vision and Pattern Recognition Large-scale Video Object Segmentation (LSVOS) addresses the challenge of accurately tracking and segmenting objects in long video sequences, where difficulties stem from object reappearance, small-scale targets, heavy occlusions, and crowded scenes. Existing approaches predominantly adopt SAM2-based frameworks with various memory mechanisms for complex video mask generation. In this report, we proposed Segment Anything with Memory Strengthened Object Navigation (SAMSON), the 3rd place solution in the MOSE track of ICCV 2025, which integrates the strengths of stateof-the-art VOS models into an effective paradigm. To handle visually similar instances and long-term object disappearance in MOSE, we incorporate a long-term memorymodule for reliable object re-identification. Additionly, we adopt SAM2Long as a post-processing strategy to reduce error accumulation and enhance segmentation stability in long video sequences. Our method achieved a final performance of 0.8427 in terms of J &F in the test-set leaderboard. |
| title | SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17500 |