English

FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching

Computer Vision and Pattern Recognition 2025-05-20 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2505.13174,
  title  = {FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching},
  author = {Alp Eren Sari and Paolo Favaro},
  journal= {arXiv preprint arXiv:2505.13174},
  year   = {2025}
}
R2 v1 2026-07-01T02:22:00.983Z