# Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training

arXiv: https://arxiv.org/abs/2512.06864 · HTML: https://mlsanity.com/paper/2512.06864/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 52 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [YouTube-VOS: Sequence-to-Sequence Video Object Segmentation](https://mlsanity.com/paper/1809.00461/) (2018)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation](https://mlsanity.com/paper/2104.04691/) (2021)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [SeqFormer: Sequential Transformer for Video Instance Segmentation](https://mlsanity.com/paper/2112.08275/) (2021)
- [VITA: Video Instance Segmentation via Object Token Association](https://mlsanity.com/paper/2206.04403/) (2022)
- [RVOS: End-to-End Recurrent Network for Video Object Segmentation](https://mlsanity.com/paper/1903.05612/) (2019)
- [DVIS: Decoupled Video Instance Segmentation Framework](https://mlsanity.com/paper/2306.03413/) (2023)
- [Unsupervised Moving Object Detection via Contextual Information Separation](https://mlsanity.com/paper/1901.03360/) (2019)
- [Segmenting Moving Objects via an Object-Centric Layered Representation](https://mlsanity.com/paper/2207.02206/) (2022)
- [Motion-Attentive Transition for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2003.04253/) (2020)
- [Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation](https://mlsanity.com/paper/2011.11630/) (2020)
- [Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion](https://mlsanity.com/paper/2205.07844/) (2022)
- [VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation](https://mlsanity.com/paper/2308.14710/) (2023)

## Abstract (arXiv)

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 textttval 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.