# Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation

arXiv: https://arxiv.org/abs/2311.17893 · HTML: https://mlsanity.com/paper/2311.17893/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 89 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 30 of 68)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Space-Time Correspondence as a Contrastive Random Walk](https://mlsanity.com/paper/2006.14613/) (2020)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://mlsanity.com/paper/2311.16933/) (2023)
- [Tracking Emerges by Colorizing Videos](https://mlsanity.com/paper/1806.09594/) (2018)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion](https://mlsanity.com/paper/2308.12469/) (2023)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)
- [MAST: A Memory-Augmented Self-supervised Tracker](https://mlsanity.com/paper/2002.07793/) (2020)
- [Video Object Segmentation Without Temporal Information](https://mlsanity.com/paper/1709.06031/) (2017)

## Built on by (most cited first, 10 of 10)

- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction](https://mlsanity.com/paper/2501.03218/) (2025)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [Advancing Complex Video Object Segmentation via Progressive Concept Construction](https://mlsanity.com/paper/2507.15852/) (2025)
- [Rethinking Image-to-Video Adaptation: An Object-centric Perspective](https://mlsanity.com/paper/2407.06871/) (2024)
- [UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning](https://mlsanity.com/paper/2509.06165/) (2025)
- [Compositional Video Synthesis by Temporal Object-Centric Learning](https://mlsanity.com/paper/2507.20855/) (2025)
- [Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning](https://mlsanity.com/paper/2604.04467/) (2026)
- [`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation](https://mlsanity.com/paper/2607.07230/) (2026)

## Abstract (arXiv)

In this paper, we propose a simple yet effective approach for self-supervised video object segmentation (VOS). Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust spatio-temporal correspondences in videos. Furthermore, simple clustering on this correspondence cue is sufficient to yield competitive segmentation results. Previous self-supervised VOS techniques majorly resort to auxiliary modalities or utilize iterative slot attention to assist in object discovery, which restricts their general applicability and imposes higher computational requirements. To deal with these challenges, we develop a simplified architecture that capitalizes on the emerging objectness from DINO-pretrained Transformers, bypassing the need for additional modalities or slot attention. Specifically, we first introduce a single spatio-temporal Transformer block to process the frame-wise DINO features and establish spatio-temporal dependencies in the form of self-attention. Subsequently, utilizing these attention maps, we implement hierarchical clustering to generate object segmentation masks. To train the spatio-temporal block in a fully self-supervised manner, we employ semantic and dynamic motion consistency coupled with entropy normalization. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and particularly excels in complex real-world multi-object video segmentation tasks such as DAVIS-17-Unsupervised and YouTube-VIS-19. The code and model checkpoints will be released at https://github.com/shvdiwnkozbw/SSL-UVOS.