CSL-YOLO: A New Lightweight Object Detection System for Edge Computing

TL;DR

This paper introduces CSL-YOLO, a lightweight object detection system optimized for edge devices, utilizing a novel CSL-Module to reduce computation while maintaining detection accuracy.

Contribution

It proposes the CSL-Module, a new lightweight convolution technique that generates redundant features efficiently, enabling a more resource-efficient detector.

Findings

CSL-Module reduces FLOPs by 57% compared to Tiny-YOLOv4.

CSL-YOLO achieves comparable detection performance with fewer parameters.

The method is validated on MS-COCO dataset.

Abstract

The development of lightweight object detectors is essential due to the limited computation resources. To reduce the computation cost, how to generate redundant features plays a significant role. This paper proposes a new lightweight Convolution method Cross-Stage Lightweight (CSL) Module, to generate redundant features from cheap operations. In the intermediate expansion stage, we replaced Pointwise Convolution with Depthwise Convolution to produce candidate features. The proposed CSL-Module can reduce the computation cost significantly. Experiments conducted at MS-COCO show that the proposed CSL-Module can approximate the fitting ability of Convolution-3x3. Finally, we use the module to construct a lightweight detector CSL-YOLO, achieving better detection performance with only 43% FLOPs and 52% parameters than Tiny-YOLOv4.