Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
This work addresses the data annotation bottleneck for researchers and practitioners in video analysis, offering a more efficient approach to video salient object detection.
The paper tackles the problem of reducing the need for large amounts of pixel-wise annotated video frames in video salient object detection by proposing a semi-supervised method using pseudo-labels, achieving results that outperform state-of-the-art fully supervised methods on benchmarks like VOS, DAVIS, and FBMS.
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 for generating pixel-level 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.