CSL-YOLO: A New Lightweight Object Detection System for Edge Computing
This work addresses the need for efficient object detection in resource-constrained edge computing environments, representing an incremental improvement over existing lightweight methods.
The paper tackled the problem of high computational cost in object detection for edge devices by proposing a new lightweight convolution module, CSL, which reduces FLOPs by 57% and parameters by 48% compared to Tiny-YOLOv4 while achieving better detection performance.
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.