由於高階的GPU始終定價較高體積較大的等一些較高的門檻，開發輕量級的物件偵測器至關重要，為了減少計算資源的無謂損耗，如何降低冗餘的計算起著重要的作用。本論文提出了一種全新的輕量級卷積方法Cross-Stage Lightweight(CSL) Module，它以廉價的運算來生成較為冗餘的特徵圖。在中間擴展深度的階段，我們將過去使用的pointwise convolution更換為depthwise convolution以生成候選的特徵圖。我們提出的CSL-Module可以顯著地降低計算成本，在CIFAR-10上進行的實驗表明了CSL-Module可以逼近convolution-3x3的擬合能力。最後我們以CSL-Module及其衍伸模組為基礎建構了全新的輕量級物件偵測器CSL-YOLO，與Tiny-YOLOv4相比，在MS-COCO上進行的實驗表明了CSL-YOLO僅以其43% FLOPs和52% parameters即可達到更好的物件偵測性能，達到了state-of-the-art的水準。;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.
