PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation
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_ | 1866913407080333312 |
|---|---|
| author | Yang, Zhangjing Liu, Dun Wang, Xin Li, Zhe Anandan, Barathwaj Wu, Yi |
| author_facet | Yang, Zhangjing Liu, Dun Wang, Xin Li, Zhe Anandan, Barathwaj Wu, Yi |
| contents | Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that eliminates video annotations by utilizing image datasets. The PM-VIS algorithm is adapted to handle both bounding box and instance-level pixel annotations dynamically. We introduce ImageNet-bbox to supplement missing categories in video datasets and propose the PM-VIS+ algorithm to adjust supervision based on annotation types. To enhance accuracy, we use pseudo masks and semi-supervised optimization techniques on unannotated video data. This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications. The code will be available in https://github.com/ldknight/PM-VIS-plus |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19665 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation Yang, Zhangjing Liu, Dun Wang, Xin Li, Zhe Anandan, Barathwaj Wu, Yi Computer Vision and Pattern Recognition Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that eliminates video annotations by utilizing image datasets. The PM-VIS algorithm is adapted to handle both bounding box and instance-level pixel annotations dynamically. We introduce ImageNet-bbox to supplement missing categories in video datasets and propose the PM-VIS+ algorithm to adjust supervision based on annotation types. To enhance accuracy, we use pseudo masks and semi-supervised optimization techniques on unannotated video data. This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications. The code will be available in https://github.com/ldknight/PM-VIS-plus |
| title | PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.19665 |