mlsanityData to 14 Oct 2026

FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching

arXiv 2505.13174 ↗First posted 19 May 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 48 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

41 of 48 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  9. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  11. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
29 more
  1. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  2. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  3. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 412
  4. 2019Video Instance Segmentationcited by 393
  5. 2023Segment Anything in High Qualitycited by 376
  6. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  7. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  8. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  9. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
  10. 2021Mask2Former for Video Instance Segmentationcited by 171
  11. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  12. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  13. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 113
  14. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  15. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  16. 2022Deformable Sprites for Unsupervised Video Decompositioncited by 61
  17. 2019Emergence of Object Segmentation in Perturbed Generative Modelscited by 57
  18. 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
  19. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  20. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  21. 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
  22. 2023VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentationcited by 37
  23. 2024Segment Anything without Supervisioncited by 28
  24. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  25. 2023Multi-Object Discovery by Low-Dimensional Object Motioncited by 16
  26. 2024CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformerscited by 16
  27. 2023LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-trainingcited by 8
  28. 2023SEMPART: Self-supervised Multi-resolution Partitioning of Image Semanticscited by 4
  29. 2024Boosting Unsupervised Segmentation Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Scene-Centric Unsupervised Video Panoptic Segmentationcited by 1
  2. 2026VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videoscited by 0