A lightweight and efficient one-stage detection framework. (January 2023)

• Record Type: Journal Article
• Authors: Huang, Jianchen; Chen, Jun; Wang, Han
• Is Part Of: Computers & electrical engineering. Volume 105(2023)
• Publication Date: 2023-01
• Subjects: Convolutional neural network -- Object detection -- Lightweight models -- Attention module -- Multiscale fusion; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108520
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Deploying high-performance one-stage object detectors on resource-constrained applications is a challenging task. This paper analyzes factors affecting the computational complexity of one-stage detectors and proposes a lightweight and efficient detection framework named LEYOLO. Under this framework, a series of efficient feature extraction modules and a novel channel attention module are designed to compose a lightweight backbone network for detection task. To efficiently combine the features extracted from the backbone, a lightweight multiscale feature fusion structure with a weighted fusion method is proposed to avoid the overhead of dimensionality reduction and downsampling. Further, two detectors (i.e., LEYOLOs and LEYOLOm) are developed based on this framework. Experimental results show that LEYOLO achieves state-of-the-art trade-offs between performance and complexity, given only small computational budgets. Graphical abstract: Highlights: An efficient and lightweight one-stage detector framework is designed. Efficient feature extraction modules and a novel dilated channel attention block are designed. Building CNN modules based on Ghost modules can reduce computational complexity.