Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
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_ | 1866910575606366208 |
|---|---|
| author | Pan, Feiyu Fang, Hao Cong, Runmin Zhang, Wei Lu, Xiankai |
| author_facet | Pan, Feiyu Fang, Hao Cong, Runmin Zhang, Wei Lu, Xiankai |
| contents | Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong performance across a wide range of tasks. In this work, we evaluate the zero-shot performance of SAM 2 on the more challenging VOS datasets MOSE and LVOS. Without fine-tuning on the training set, SAM 2 achieved 75.79 J&F on the test set and ranked 4th place for 6th LSVOS Challenge VOS Track. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10125 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track Pan, Feiyu Fang, Hao Cong, Runmin Zhang, Wei Lu, Xiankai Computer Vision and Pattern Recognition Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong performance across a wide range of tasks. In this work, we evaluate the zero-shot performance of SAM 2 on the more challenging VOS datasets MOSE and LVOS. Without fine-tuning on the training set, SAM 2 achieved 75.79 J&F on the test set and ranked 4th place for 6th LSVOS Challenge VOS Track. |
| title | Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.10125 |