# Decoupling Features in Hierarchical Propagation for Video Object Segmentation

arXiv: https://arxiv.org/abs/2210.09782 · HTML: https://mlsanity.com/paper/2210.09782/

## Key facts

- Cited by 148 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 81 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Scaling Local Self-Attention for Parameter Efficient Visual Backbones](https://mlsanity.com/paper/2103.12731/) (2021)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Transformer Quality in Linear Time](https://mlsanity.com/paper/2202.10447/) (2022)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)

## Built on by (most cited first, 30 of 148)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Segment and Track Anything](https://mlsanity.com/paper/2305.06558/) (2023)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [Foundational Models Defining a New Era in Vision: A Survey and Outlook](https://mlsanity.com/paper/2307.13721/) (2023)
- [Segment Anything Meets Point Tracking](https://mlsanity.com/paper/2307.01197/) (2023)
- [Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation](https://mlsanity.com/paper/2309.04946/) (2023)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [A Comprehensive Survey on Segment Anything Model for Vision and Beyond](https://mlsanity.com/paper/2305.08196/) (2023)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)](https://mlsanity.com/paper/2401.08392/) (2024)
- [XMem++: Production-level Video Segmentation From Few Annotated Frames](https://mlsanity.com/paper/2307.15958/) (2023)
- [Matching Anything by Segmenting Anything](https://mlsanity.com/paper/2406.04221/) (2024)
- [EPIC Fields: Marrying 3D Geometry and Video Understanding](https://mlsanity.com/paper/2306.08731/) (2023)
- [Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing](https://mlsanity.com/paper/2412.19806/) (2024)
- [Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.14747/) (2023)
- [A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering](https://mlsanity.com/paper/2306.06211/) (2023)
- [LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation](https://mlsanity.com/paper/2404.19326/) (2024)
- [Look Before You Match: Instance Understanding Matters in Video Object Segmentation](https://mlsanity.com/paper/2212.06826/) (2022)
- [Moving Object Segmentation: All You Need Is SAM (and Flow)](https://mlsanity.com/paper/2404.12389/) (2024)
- [Follow Anything: Open-set detection, tracking, and following in real-time](https://mlsanity.com/paper/2308.05737/) (2023)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation](https://mlsanity.com/paper/2309.09501/) (2023)
- [UniVS: Unified and Universal Video Segmentation with Prompts as Queries](https://mlsanity.com/paper/2402.18115/) (2024)
- [Advancing Complex Video Object Segmentation via Progressive Concept Construction](https://mlsanity.com/paper/2507.15852/) (2025)
- [MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors](https://mlsanity.com/paper/2303.05071/) (2023)
- [UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces](https://mlsanity.com/paper/2312.15715/) (2023)
- [Object Segmentation-Assisted Inter Prediction for Versatile Video Coding](https://mlsanity.com/paper/2403.11694/) (2024)
- [Event-assisted Low-Light Video Object Segmentation](https://mlsanity.com/paper/2404.01945/) (2024)

## Abstract (arXiv)

This paper focuses on developing a more effective method of hierarchical propagation for semi-supervised Video Object Segmentation (VOS). Based on vision transformers, the recently-developed Associating Objects with Transformers (AOT) approach introduces hierarchical propagation into VOS and has shown promising results. The hierarchical propagation can gradually propagate information from past frames to the current frame and transfer the current frame feature from object-agnostic to object-specific. However, the increase of object-specific information will inevitably lead to the loss of object-agnostic visual information in deep propagation layers. To solve such a problem and further facilitate the learning of visual embeddings, this paper proposes a Decoupling Features in Hierarchical Propagation (DeAOT) approach. Firstly, DeAOT decouples the hierarchical propagation of object-agnostic and object-specific embeddings by handling them in two independent branches. Secondly, to compensate for the additional computation from dual-branch propagation, we propose an efficient module for constructing hierarchical propagation, i.e., Gated Propagation Module, which is carefully designed with single-head attention. Extensive experiments show that DeAOT significantly outperforms AOT in both accuracy and efficiency. On YouTube-VOS, DeAOT can achieve 86.0% at 22.4fps and 82.0% at 53.4fps. Without test-time augmentations, we achieve new state-of-the-art performance on four benchmarks, i.e., YouTube-VOS (86.2%), DAVIS 2017 (86.2%), DAVIS 2016 (92.9%), and VOT 2020 (0.622). Project page: https://github.com/z-x-yang/AOT.