Boundary-guided Feature Aggregation Network for Salient Object Detection

TL;DR

This paper introduces a boundary-guided feature aggregation network that effectively combines multi-level convolutional features and boundary information to improve salient object detection accuracy, achieving state-of-the-art results.

Contribution

It proposes a novel FCN framework that recurrently integrates multi-level features with boundary guidance for enhanced salient object detection.

Findings

Achieves new state-of-the-art performance on four large-scale benchmarks.

Effectively fuses boundary information with saliency maps for precise object boundaries.

Demonstrates significant improvement over existing methods in salient object detection.

Abstract

Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains non-trivial to thoroughly utilize the multi-level convolutional feature maps and boundary information for salient object detection. In this paper, we propose a novel FCN framework to integrate multi-level convolutional features recurrently with the guidance of object boundary information. First, a deep convolutional network is used to extract multi-level feature maps and separately aggregate them into multiple resolutions, which can be used to generate coarse saliency maps. Meanwhile, another boundary information extraction branch is proposed to generate boundary features. Finally, an attention-based feature fusion module is designed to fuse boundary information into salient regions to achieve accurate boundary inference and semantic enhancement. The final saliency maps are the combination of the predicted boundary maps and integrated saliency maps, which are more closer to the ground truths. Experiments and analysis on four large-scale benchmarks verify that our framework achieves new state-of-the-art results.