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

TL;DR

This paper introduces DAVOS, a semi-supervised video object segmentation method using adversarial domain adaptation to improve performance across different datasets without requiring additional annotations.

Contribution

It presents a novel adversarial domain adaptation approach for VOS, combining appearance and motion features with supervised and unsupervised training to handle domain shift.

Findings

Achieved 82.6% mean IoU on DAVIS2016.

Significantly improved performance on FBMS59 and Youtube-Object datasets.

No extra annotations needed for domain adaptation.

Abstract

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.