A Unified Structure for Efficient RGB and RGB-D Salient Object Detection

TL;DR

This paper introduces a unified, efficient neural network structure with a cross-attention module that effectively handles both RGB and RGB-D salient object detection tasks, outperforming existing methods.

Contribution

The paper presents a novel unified architecture with a cross-attention context extraction module that efficiently fuses RGB and depth information for salient object detection.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively fuses RGB and depth data with a unified network

Achieves superior metrics in both RGB and RGB-D SOD tasks

Abstract

Salient object detection (SOD) has been well studied in recent years, especially using deep neural networks. However, SOD with RGB and RGB-D images is usually treated as two different tasks with different network structures that need to be designed specifically. In this paper, we proposed a unified and efficient structure with a cross-attention context extraction (CRACE) module to address both tasks of SOD efficiently. The proposed CRACE module receives and appropriately fuses two (for RGB SOD) or three (for RGB-D SOD) inputs. The simple unified feature pyramid network (FPN)-like structure with CRACE modules conveys and refines the results under the multi-level supervisions of saliency and boundaries. The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently. Experimental results show that our method outperforms other state-of-the-art methods in both RGB and RGB-D SOD tasks on various datasets and in terms of most metrics.