Temporally Efficient Vision Transformer for Video Instance Segmentation
About
Recently vision transformer has achieved tremendous success on image-level visual recognition tasks. To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS). Different from previous transformer-based VIS methods, TeViT is nearly convolution-free, which contains a transformer backbone and a query-based video instance segmentation head. In the backbone stage, we propose a nearly parameter-free messenger shift mechanism for early temporal context fusion. In the head stages, we propose a parameter-shared spatiotemporal query interaction mechanism to build the one-to-one correspondence between video instances and queries. Thus, TeViT fully utilizes both framelevel and instance-level temporal context information and obtains strong temporal modeling capacity with negligible extra computational cost. On three widely adopted VIS benchmarks, i.e., YouTube-VIS-2019, YouTube-VIS-2021, and OVIS, TeViT obtains state-of-the-art results and maintains high inference speed, e.g., 46.6 AP with 68.9 FPS on YouTube-VIS-2019. Code is available at https://github.com/hustvl/TeViT.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Video Instance Segmentation | YouTube-VIS 2019 (val) | AP46.6 | 567 | |
| Video Instance Segmentation | YouTube-VIS 2021 (val) | AP37.9 | 344 | |
| Video Instance Segmentation | OVIS (val) | AP17.4 | 301 | |
| Video Instance Segmentation | YouTube-VIS 2019 (test) | AP56.8 | 13 | |
| Video Instance Segmentation | OVIS (test) | AP17.4 | 12 | |
| Video Instance Segmentation | OVIS 1.0 (val) | AP17.4 | 11 | |
| Video Instance Segmentation | AVISeg (test) | FSLA32.28 | 7 |