2025/12/07 by Lu, Kaixuan, Kaya, Mehmet Onurcan, Papadopoulos, Dim P.
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Video Analysis and Summarization #Visual Attention and Saliency Detection
paper · doi:10.48550/arxiv.2512.06864
openalex publication_date 2025/12/07 · openalex created_date 2025/12/10 · openalex updated_date 2026/07/28
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 AP50 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. We will release the code at https://github.com/wcbup/AutoQ-VIS.