ELWNet: An Extremely Lightweight Approach for Real-Time Salient Object Detection

Zhenyu Wang, Yunzhou Zhang, Yan Liu, Delong Zhu, Sonya A. Coleman, Dermot Kerr

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
198 Downloads (Pure)

Abstract

Existing lightweight salient object detection (SOD) methods aim to solve the problem of high computational costs that is prevalent with heavyweight methods. However, compared with heavyweight methods, the detection accuracy of lightweight methods is greatly reduced while real-time performance is not significantly improved. Therefore, we aim to establish a trade off between computational cost and detection performance by improving the network efficiency. We propose a fast and extremely lightweight end-to-end wavelet neural network (ELWNet) for real-time salient object detection. ELWNet can achieve salient object detection and segmentation at approximately 70FPS (GPU), 19FPS (CPU) with 76K parameters and 0.38G FLOPs. We introduce wavelet transform theory into a neural network, proposing a wavelet transform module (WTM), a wavelet transform fusion module (WTFM), a novel feature residual mechanism, and construct an efficient architecture. The wavelet transform theory is integrated into the neural network to realize the interaction between the features in the frequency and the time domain. Meanwhile, ELWNet does not rely on a pre-trained model, which significantly reduces redundant features. We validate the performance of ELWNet using five well-known datasets, and demonstrate state-of-the-art performance compared with 24 other SOD models in terms of being lightweight, detection accuracy and real-time capabilities. Our method maintains high detection performance while reducing the number of model parameters by approximately 99% compared with heavyweight methods.
Original languageEnglish
Pages (from-to)6404-6417
Number of pages14
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume33
Issue number11
DOIs
Publication statusPublished (in print/issue) - 24 Apr 2023

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61973066, in part by the Major Science and Technology Projects of Liaoning Province under Grant 2021JH1/10400049, in part by the Foundation of Key Laboratory of Aerospace System Simulation under Grant 6142002200301, and in part by the Fundamental Research Funds for the Central Universities under Grant N2004022. This article was recommended by Associate Editor G. Pastuszak

Publisher Copyright:
© 2023 IEEE.

Keywords

  • Wavelet transforms
  • REal-time systems
  • Object detection
  • Decoding
  • Graphics processing units
  • Feature extraction
  • Computational modeling
  • Salient Object Detection
  • Wavelet Neural Network
  • Extremely Lightweight
  • Accuracy and Real-time
  • Real-time systems

Fingerprint

Dive into the research topics of 'ELWNet: An Extremely Lightweight Approach for Real-Time Salient Object Detection'. Together they form a unique fingerprint.

Cite this