# DAVOS: Semi-Supervised Video Object Segmentation via Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/2105.10201 · HTML: https://mlsanity.com/paper/2105.10201/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 21 May 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks](https://mlsanity.com/paper/2001.06810/) (2020)
- [Domain-Symmetric Networks for Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.04663/) (2019)
- [Video Object Segmentation with Episodic Graph Memory Networks](https://mlsanity.com/paper/2007.07020/) (2020)
- [Online Adaptation of Convolutional Neural Networks for Video Object Segmentation](https://mlsanity.com/paper/1706.09364/) (2017)
- [Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks](https://mlsanity.com/paper/2001.06807/) (2020)
- [Beyond Sharing Weights for Deep Domain Adaptation](https://mlsanity.com/paper/1603.06432/) (2016)
- [FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos](https://mlsanity.com/paper/1701.05384/) (2017)
- [Unsupervised Domain Adaptation with Similarity Learning](https://mlsanity.com/paper/1711.08995/) (2017)
- [Unsupervised Moving Object Detection via Contextual Information Separation](https://mlsanity.com/paper/1901.03360/) (2019)
- [Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2007.02424/) (2020)
- [Learning Video Object Segmentation with Visual Memory](https://mlsanity.com/paper/1704.05737/) (2017)
- [Learning Motion Patterns in Videos](https://mlsanity.com/paper/1612.07217/) (2016)
- [Make One-Shot Video Object Segmentation Efficient Again](https://mlsanity.com/paper/2012.01866/) (2020)
- [Unsupervised Online Video Object Segmentation with Motion Property Understanding](https://mlsanity.com/paper/1810.03783/) (2018)
- [Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation](https://mlsanity.com/paper/1809.01125/) (2018)
- [Unseen Object Segmentation in Videos via Transferable Representations](https://mlsanity.com/paper/1901.02444/) (2019)

## Abstract (arXiv)

Domain shift has always been one of the primary issues in video object segmentation (VOS), for which models suffer from degeneration when tested on unfamiliar datasets. Recently, many online methods have emerged to narrow the performance gap between training data (source domain) and test data (target domain) by fine-tuning on annotations of test data which are usually in shortage. In this paper, we propose a novel method to tackle domain shift by first introducing adversarial domain adaptation to the VOS task, with supervised training on the source domain and unsupervised training on the target domain. By fusing appearance and motion features with a convolution layer, and by adding supervision onto the motion branch, our model achieves state-of-the-art performance on DAVIS2016 with 82.6% mean IoU score after supervised training. Meanwhile, our adversarial domain adaptation strategy significantly raises the performance of the trained model when applied on FBMS59 and Youtube-Object, without exploiting extra annotations.