DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection

TL;DR

DeepSaliency introduces a multi-task deep neural network that jointly learns saliency detection and semantic segmentation, effectively capturing semantic properties and improving salient object detection accuracy.

Contribution

It proposes a novel multi-task FCNN model that leverages shared features for saliency detection and segmentation, enhancing semantic understanding of salient objects.

Findings

Outperforms state-of-the-art methods in saliency detection accuracy

Effectively captures semantic information across different levels

Reduces feature redundancy through shared convolutional layers

Abstract

A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner. In this paper, we propose a multi-task deep saliency model based on a fully convolutional neural network (FCNN) with global input (whole raw images) and global output (whole saliency maps). In principle, the proposed saliency model takes a data-driven strategy for encoding the underlying saliency prior information, and then sets up a multi-task learning scheme for exploring the intrinsic correlations between saliency detection and semantic image segmentation. Through collaborative feature learning from such two correlated tasks, the shared fully convolutional layers produce effective features for object perception. Moreover, it is capable of capturing the semantic information on salient objects across different levels using the fully convolutional layers, which investigate the feature-sharing properties of salient object detection with great feature redundancy reduction. Finally, we present a graph Laplacian regularized nonlinear regression model for saliency refinement. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.