DC-Net: Divide-and-Conquer for Salient Object Detection

TL;DR

DC-Net introduces a divide-and-conquer approach with specialized encoders and a novel decoder to improve salient object detection, achieving high efficiency and competitive accuracy across multiple datasets.

Contribution

The paper proposes a novel divide-and-conquer network architecture with parallel acceleration for efficient and accurate salient object detection.

Findings

Achieves 60 FPS and 55 FPS on LR-SOD and HR-SOD datasets.

Effectively captures multi-scale features with ResASPP$^{2}$ modules.

Outperforms existing methods on multiple benchmark datasets.

Abstract

In this paper, we introduce Divide-and-Conquer into the salient object detection (SOD) task to enable the model to learn prior knowledge that is for predicting the saliency map. We design a novel network, Divide-and-Conquer Network (DC-Net) which uses two encoders to solve different subtasks that are conducive to predicting the final saliency map, here is to predict the edge maps with width 4 and location maps of salient objects and then aggregate the feature maps with different semantic information into the decoder to predict the final saliency map. The decoder of DC-Net consists of our newly designed two-level Residual nested-ASPP (ResASPP$^{2}$) modules, which have the ability to capture a large number of different scale features with a small number of convolution operations and have the advantages of maintaining high resolution all the time and being able to obtain a large and compact effective receptive field (ERF). Based on the advantage of Divide-and-Conquer's parallel computing, we use Parallel Acceleration to speed up DC-Net, allowing it to achieve competitive performance on six LR-SOD and five HR-SOD datasets under high efficiency (60 FPS and 55 FPS). Codes and results are available: https://github.com/PiggyJerry/DC-Net.