Reverse Attention for Salient Object Detection

TL;DR

This paper introduces a compact deep network for salient object detection that uses reverse attention and residual learning to improve accuracy and resolution while maintaining efficiency and small model size.

Contribution

The paper proposes a novel reverse attention mechanism combined with residual learning for efficient and high-resolution salient object detection in a compact model.

Findings

Achieves 45 FPS processing speed.

Model size is only 81 MB.

Outperforms state-of-the-art methods on six benchmarks.

Abstract

Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded devices, low resolution output and heavy model weight. To this end, this paper presents an accurate yet compact deep network for efficient salient object detection. More specifically, given a coarse saliency prediction in the deepest layer, we first employ residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy. Secondly, we further propose reverse attention to guide such side-output residual learning in a top-down manner. By erasing the current predicted salient regions from side-output features, the network can eventually explore the missing object parts and details which results in high resolution and accuracy. Experiments on six benchmark datasets demonstrate that the proposed approach compares favorably against state-of-the-art methods, and with advantages in terms of simplicity, efficiency (45 FPS) and model size (81 MB).