Abstract
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 this https URL.
Abstract (translated)
视频实例分割（VIS）面临着显著的标注挑战，因为其需要像素级别的掩码和时间一致性标签。虽然近期的一些无监督方法如VideoCutLER通过合成数据消除了光流依赖性，但它们仍受限于合成与现实之间的领域差距。我们提出了AutoQ-VIS，这是一种新的无监督框架，它通过质量引导的自我训练来弥合这一差距。我们的方法建立了一个闭循环系统，在伪标签生成和自动质量评估之间进行迭代改进，从而能够逐步适应从合成到真实视频的过程。 实验结果表明，AutoQ-VIS在YouTubeVIS-2019验证集上达到了52.6 $\text{AP}_{50}$ 的性能指标，超越了之前的最佳方法VideoCutLER 4.4%，并且无需任何人工标注。这证明了质量感知自我训练在无监督VIS中的可行性。 我们将在[此处](https://example.com)发布代码。
URL
https://arxiv.org/abs/2512.06864
