A lightweight and efficient one-stage detection framework?

Jianchen Huang

doi:10.1016/j.compeleceng.2022.108520

A lightweight and efficient one-stage detection framework?

2023-01-01

4

PRE

AI

DOI：10.1016/j.compeleceng.2022.108520

Original

Original request for help

Save

Abstract

En 中文

Deploying high-performance one-stage object detectors on resource-constrained applications is a challenging task. This paper analyzes factors affecting the computational complexity of onestage 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.

Keywords:

Convolutional neural network

Object detection

Lightweight models

Attention module

Multiscale fusion

A lightweight and efficient one-stage detection framework?

Abstract

Journal

Organization