Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection

TL;DR

This paper introduces a novel framework for video salient object detection that adaptively combines spatial and temporal cues using confidence-guided gating and differential enhancement, improving detection accuracy in challenging scenarios.

Contribution

The proposed method integrates Confidence-guided Adaptive Gate modules and Dual Differential Enhancement modules to effectively fuse spatial and temporal features in video saliency detection.

Findings

Outperforms thirteen state-of-the-art methods on four datasets.

Effectively handles low-contrast, fast motion, and multiple objects.

Demonstrates robustness in real-world scenarios.

Abstract

Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world scenarios, such as low-contrast foreground, fast motion, and multiple moving objects. To address these problems, we propose a new framework to adaptively capture available information from spatial and temporal cues, which contains Confidence-guided Adaptive Gate (CAG) modules and Dual Differential Enhancement (DDE) modules. For both RGB features and optical flow features, CAG estimates confidence scores supervised by the IoU between predictions and the ground truths to re-calibrate the information with a gate mechanism. DDE captures the differential feature representation to enrich the spatial and temporal information and generate the fused features. Experimental results on four widely used datasets demonstrate the effectiveness of the proposed method against thirteen state-of-the-art methods.