2025/05/19 by Alp Eren Sari, Sari, Alp Eren, Paolo Favaro +1 · 1 citation
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 · pdf · doi:10.48550/arxiv.2505.13174
openalex publication_date 2025/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose FlowCut, a simple and capable method for unsupervised video instance segmentation consisting of a three-stage framework to construct a high-quality video dataset with pseudo labels. To our knowledge, our work is the first attempt to curate a video dataset with pseudo-labels for unsupervised video instance segmentation. In the first stage, we generate pseudo-instance masks by exploiting the affinities of features from both images and optical flows. In the second stage, we construct short video segments containing high-quality, consistent pseudo-instance masks by temporally matching them across the frames. In the third stage, we use the YouTubeVIS-2021 video dataset to extract our training instance segmentation set, and then train a video segmentation model. FlowCut achieves state-of-the-art performance on the YouTubeVIS-2019, YouTubeVIS-2021, DAVIS-2017, and DAVIS-2017 Motion benchmarks.