AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915466185801728 |
|---|---|
| author | Lu, Kaixuan Kaya, Mehmet Onurcan Papadopoulos, Dim P. |
| author_facet | Lu, Kaixuan Kaya, Mehmet Onurcan Papadopoulos, Dim P. |
| contents | Video Instance Segmentation (VIS) faces significant annotation challenges due to its dual requirements of pixel-level masks and temporal consistency labels. While recent unsupervised methods like VideoCutLER eliminate optical flow dependencies through synthetic data, they remain constrained by the synthetic-to-real domain gap. We present AutoQ-VIS, a novel unsupervised framework that bridges this gap through quality-guided self-training. Our approach establishes a closed-loop system between pseudo-label generation and automatic quality assessment, enabling progressive adaptation from synthetic to real videos. Experiments demonstrate state-of-the-art performance with 52.6 $\text{AP}_{50}$ on YouTubeVIS-2019 val set, surpassing the previous state-of-the-art VideoCutLER by 4.4$\%$, while requiring no human annotations. This demonstrates the viability of quality-aware self-training for unsupervised VIS. The source code of our method is available at https://github.com/wcbup/AutoQ-VIS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19808 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment Lu, Kaixuan Kaya, Mehmet Onurcan Papadopoulos, Dim P. Computer Vision and Pattern Recognition Video Instance Segmentation (VIS) faces significant annotation challenges due to its dual requirements of pixel-level masks and temporal consistency labels. While recent unsupervised methods like VideoCutLER eliminate optical flow dependencies through synthetic data, they remain constrained by the synthetic-to-real domain gap. We present AutoQ-VIS, a novel unsupervised framework that bridges this gap through quality-guided self-training. Our approach establishes a closed-loop system between pseudo-label generation and automatic quality assessment, enabling progressive adaptation from synthetic to real videos. Experiments demonstrate state-of-the-art performance with 52.6 $\text{AP}_{50}$ on YouTubeVIS-2019 val set, surpassing the previous state-of-the-art VideoCutLER by 4.4$\%$, while requiring no human annotations. This demonstrates the viability of quality-aware self-training for unsupervised VIS. The source code of our method is available at https://github.com/wcbup/AutoQ-VIS. |
| title | AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.19808 |