Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

Pengxiang Yan¹   Guanbin Li¹   Yuan Xie¹   Zhen Li²   Chuan Wang³   Tianshui Chen¹   Liang Lin¹ 

¹Sun Yat-sen University                  ²CUHK (Shenzhen)                  ³Megvii Technology

Accepted by ICCV 2019

Figure: The architecture of our flow guided pseudo-label generation model (FGPLG)

Abstract

Deep learning based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rely on a large quantity of pixel-wise annotated video frames to deliver such promising results. In this paper, we address the semi-supervised video salient object detection task using pseudo-labels. Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module. Based on the same refinement network and motion information in terms of optical flow, we further propose a novel method to generate pixellevel pseudo-labels from sparsely annotated frames. By utilizing the generated pseudo-labels together with a part of manual annotations, our video saliency detector learns spatial and temporal cues for both contrast inference and coherence enhancement, thus producing accurate saliency maps. Experimental results demonstrate that our proposed semi-supervised method even greatly outperforms all the state-of-the-art fully-supervised methods across three public benchmarks of VOS, DAVIS, and FBMS.

Downloads

Bibtex

@article{yan2019semi,
  title={Semi-Supervised Video Salient Object Detection Using Pseudo-Labels},
  author={Yan, Pengxiang and Li, Guanbin and Xie, Yuan and Li, Zhen and Wang, Chuan and Chen, Tianshui and Lin, Liang},
  journal={arXiv preprint arXiv:1908.04051},
  year={2019}
}