Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation

TL;DR

This paper introduces an unsupervised video object segmentation method that generates pseudo ground truth using motion cues, improving segmentation accuracy efficiently without manual labels.

Contribution

It proposes a novel approach to create high-quality pseudo ground truth with motion cues for unsupervised training, outperforming existing methods.

Findings

Outperforms state-of-the-art unsupervised segmentation methods on DAVIS and FBMS datasets.

Uses motion cues to select and refine pseudo ground truth for better segmentation.

Efficiently extends to multiple arbitrary object tracking scenarios.

Abstract

One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training. Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information. Afterwards, the pseudo ground truth is exploited to finetune the pretrained objectness network to facilitate object segmentation in the remaining frames of the video. We show that the pseudo ground truth could effectively improve the segmentation performance. This straightforward unsupervised video object segmentation method is more efficient than existing methods. Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets. And the category-agnostic pseudo ground truth has great potential to extend to multiple arbitrary object tracking.