通过自动质量评估实现无监督视频实例分割的闭环自训练。
Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training
- 构建伪标签生成与质量评估的闭环系统，逐步适应真实视频。
- 在YouTubeVIS-2019上达到52.6 AP₅₀，比之前最优方法高4.4%。
- 无需人工标注，适合追求无监督视频分割性能的研究者。
视频实例分割（VIS）因需要像素级掩码和时序一致性标签，面临严重的标注挑战。尽管近期无监督方法如VideoCutLER通过合成数据消除了对光流的依赖，但仍受限于合成到真实的数据域差距。本文提出AutoQ-VIS，一种新颖的无监督框架，通过质量引导的自训练弥合该差距。方法建立伪标签生成与自动质量评估之间的闭环系统，实现从合成视频到真实视频的渐进式适应。实验表明，在YouTubeVIS-2019验证集上达到52.6 AP₅₀，超越此前最优方法VideoCutLER 4.4%，且无需任何人工标注。结果证明了质量感知自训练在无监督VIS中的可行性。代码将开源至https://github.com/wcbup/AutoQ-VIS。
原文摘要 · Abstract (English)
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 $\texttt{val}$ 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. We will release the code at https://github.com/wcbup/AutoQ-VIS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。