DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection

TL;DR

This paper introduces DS-Net, a novel dynamic spatiotemporal network that effectively fuses spatial and temporal features for video salient object detection, outperforming existing methods across multiple benchmarks.

Contribution

The paper proposes a symmetric two-bypass network with a dynamic weight generator and cross attentive aggregation for improved spatiotemporal feature fusion in saliency detection.

Findings

Achieves superior performance on five benchmark datasets.

Effectively handles camera movement and partial object movement.

Outperforms state-of-the-art algorithms in video saliency detection.

Abstract

As moving objects always draw more attention of human eyes, the temporal motive information is always exploited complementarily with spatial information to detect salient objects in videos. Although efficient tools such as optical flow have been proposed to extract temporal motive information, it often encounters difficulties when used for saliency detection due to the movement of camera or the partial movement of salient objects. In this paper, we investigate the complimentary roles of spatial and temporal information and propose a novel dynamic spatiotemporal network (DS-Net) for more effective fusion of spatiotemporal information. We construct a symmetric two-bypass network to explicitly extract spatial and temporal features. A dynamic weight generator (DWG) is designed to automatically learn the reliability of corresponding saliency branch. And a top-down cross attentive aggregation (CAA) procedure is designed so as to facilitate dynamic complementary aggregation of spatiotemporal features. Finally, the features are modified by spatial attention with the guidance of coarse saliency map and then go through decoder part for final saliency map. Experimental results on five benchmarks VOS, DAVIS, FBMS, SegTrack-v2, and ViSal demonstrate that the proposed method achieves superior performance than state-of-the-art algorithms. The source code is available at https://github.com/TJUMMG/DS-Net.