What is Point Supervision Worth in Video Instance Segmentation?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917628984950784 |
|---|---|
| author | Huang, Shuaiyi Huang, De-An Yu, Zhiding Lan, Shiyi Radhakrishnan, Subhashree Alvarez, Jose M. Shrivastava, Abhinav Anandkumar, Anima |
| author_facet | Huang, Shuaiyi Huang, De-An Yu, Zhiding Lan, Shiyi Radhakrishnan, Subhashree Alvarez, Jose M. Shrivastava, Abhinav Anandkumar, Anima |
| contents | Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annotations. Comprehensive experiments on three VIS benchmarks demonstrate competitive performance of the proposed framework, nearly matching fully supervised methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01990 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What is Point Supervision Worth in Video Instance Segmentation? Huang, Shuaiyi Huang, De-An Yu, Zhiding Lan, Shiyi Radhakrishnan, Subhashree Alvarez, Jose M. Shrivastava, Abhinav Anandkumar, Anima Computer Vision and Pattern Recognition Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annotations. Comprehensive experiments on three VIS benchmarks demonstrate competitive performance of the proposed framework, nearly matching fully supervised methods. |
| title | What is Point Supervision Worth in Video Instance Segmentation? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.01990 |