Lightweight Salient Object Detection via Hierarchical Visual Perception Learning

Recently, salient object detection (SOD) has witnessed vast progress with the rapid development of convolutional neural networks (CNNs). However, the improvement of SOD accuracy comes with the increase in network depth and width, resulting in large network size and heavy computational overhead. This...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2021-09, Vol.51 (9), p.4439-4449
Main Authors: Liu, Yun, Gu, Yu-Chao, Zhang, Xin-Yu, Wang, Weiwei, Cheng, Ming-Ming
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Computational modeling
Convolution
Electronic devices
Hierarchical visual perception (HVP)
Kernel
Learning
Lightweight
lightweight saliency detection
lightweight salient object detection (SOD)
Modules
Object detection
Object recognition
Salience
Signal processing
Task analysis
Visual observation
Visual perception
Visual signals
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, salient object detection (SOD) has witnessed vast progress with the rapid development of convolutional neural networks (CNNs). However, the improvement of SOD accuracy comes with the increase in network depth and width, resulting in large network size and heavy computational overhead. This prevents state-of-the-art SOD methods from being deployed into practical platforms, especially mobile devices. To promote the deployment of real-world SOD applications, we aim at developing a lightweight SOD model in this article. Our observation comes from that the primate visual system processes visual signals hierarchically with different receptive fields and eccentricities in different visual cortex areas. Inspired by this, we propose a hierarchical visual perception (HVP) module to imitate the primate visual cortex for hierarchical perception learning. With the HVP module incorporated, we design a lightweight SOD network, namely, HVPNet. Extensive experiments on popular benchmarks demonstrate that HVPNet achieves highly competitive accuracy compared with state-of-the-art SOD methods while running at 4.3 frames/s CPU speed and 333.2 frames/s GPU speed with only 1.23M parameters.
ISSN:2168-2267
2168-2275
DOI:10.1109/TCYB.2020.3035613