# Anchor Diffusion for Unsupervised Video Object Segmentation

arXiv: https://arxiv.org/abs/1910.10895 · HTML: https://mlsanity.com/paper/1910.10895/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2019.

## Built on by (most cited first, 30 of 50)

- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [SwiftNet: Real-time Video Object Segmentation](https://mlsanity.com/paper/2102.04604/) (2021)
- [Segmenting Moving Objects via an Object-Centric Layered Representation](https://mlsanity.com/paper/2207.02206/) (2022)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [Implicit Motion Handling for Video Camouflaged Object Detection](https://mlsanity.com/paper/2203.07363/) (2022)
- [Self-supervised Object-Centric Learning for Videos](https://mlsanity.com/paper/2310.06907/) (2023)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)
- [Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2207.08485/) (2022)
- [Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2209.03138/) (2022)
- [Unsupervised Video Object Segmentation via Prototype Memory Network](https://mlsanity.com/paper/2209.03712/) (2022)
- [Moving Object Segmentation: All You Need Is SAM (and Flow)](https://mlsanity.com/paper/2404.12389/) (2024)
- [Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier](https://mlsanity.com/paper/2112.12402/) (2021)
- [Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation](https://mlsanity.com/paper/2104.04782/) (2021)
- [Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps](https://mlsanity.com/paper/2104.10386/) (2021)
- [D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos](https://mlsanity.com/paper/2111.07774/) (2021)
- [Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview](https://mlsanity.com/paper/2211.08352/) (2022)
- [A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2209.09341/) (2022)
- [Dual Prototype Attention for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2211.12036/) (2022)
- [Video Salient Object Detection via Contrastive Features and Attention Modules](https://mlsanity.com/paper/2111.02368/) (2021)
- [SimulFlow: Simultaneously Extracting Feature and Identifying Target for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2311.18286/) (2023)
- [Appearance-Based Refinement for Object-Centric Motion Segmentation](https://mlsanity.com/paper/2312.11463/) (2023)
- [Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2204.02791/) (2022)
- [Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation](https://mlsanity.com/paper/2308.06693/) (2023)
- [Co-attention Propagation Network for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2304.03910/) (2023)
- [Temporal Transductive Inference for Few-Shot Video Object Segmentation](https://mlsanity.com/paper/2203.14308/) (2022)
- [Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery](https://mlsanity.com/paper/2204.01276/) (2022)
- [Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2309.11707/) (2023)

## Abstract (arXiv)

Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow. Despite their complexity, these kinds of approaches tend to favour short-term temporal dependencies and are thus prone to accumulating inaccuracies, which cause drift over time. Moreover, simple (static) image segmentation models, alone, can perform competitively against these methods, which further suggests that the way temporal dependencies are modelled should be reconsidered. Motivated by these observations, in this paper we explore simple yet effective strategies to model long-term temporal dependencies. Inspired by the non-local operators of [70], we introduce a technique to establish dense correspondences between pixel embeddings of a reference "anchor" frame and the current one. This allows the learning of pairwise dependencies at arbitrarily long distances without conditioning on intermediate frames. Without online supervision, our approach can suppress the background and precisely segment the foreground object even in challenging scenarios, while maintaining consistent performance over time. With a mean IoU of 81.7%, our method ranks first on the DAVIS-2016 leaderboard of unsupervised methods, while still being competitive against state-of-the-art online semi-supervised approaches. We further evaluate our method on the FBMS dataset and the ViSal video saliency dataset, showing results competitive with the state of the art.