CAGNet: Content-Aware Guidance for Salient Object Detection

TL;DR

CAGNet introduces a content-aware guidance framework with multi-scale feature extraction that significantly improves salient object detection accuracy, robustness, and speed across challenging scenarios and datasets.

Contribution

The paper proposes a novel Feature Guide Network with multi-scale feature extraction and a new loss function, enhancing salient object detection with fewer parameters and real-time performance.

Findings

Achieves state-of-the-art results on five challenging datasets.

Operates at 28 FPS with fewer parameters than existing methods.

Effectively handles complex scenarios with salient-like backgrounds.

Abstract

Beneficial from Fully Convolutional Neural Networks (FCNs), saliency detection methods have achieved promising results. However, it is still challenging to learn effective features for detecting salient objects in complicated scenarios, in which i) non-salient regions may have "salient-like" appearance; ii) the salient objects may have different-looking regions. To handle these complex scenarios, we propose a Feature Guide Network which exploits the nature of low-level and high-level features to i) make foreground and background regions more distinct and suppress the non-salient regions which have "salient-like" appearance; ii) assign foreground label to different-looking salient regions. Furthermore, we utilize a Multi-scale Feature Extraction Module (MFEM) for each level of abstraction to obtain multi-scale contextual information. Finally, we design a loss function which outperforms the widely-used Cross-entropy loss. By adopting four different pre-trained models as the backbone, we prove that our method is very general with respect to the choice of the backbone model. Experiments on five challenging datasets demonstrate that our method achieves the state-of-the-art performance in terms of different evaluation metrics. Additionally, our approach contains fewer parameters than the existing ones, does not need any post-processing, and runs fast at a real-time speed of 28 FPS when processing a 480 x 480 image.