Blood cell detection is a typical small-scale object detection problem in computer vision. In this paper, we propose a CST-YOLO model for blood cell detection based on YOLOv7 architecture and enhance it with the CNN-Swin Transformer (CST), which is a new attempt at CNN-Transformer fusion. We also introduce three other useful modules: Weighted Efficient Layer Aggregation Networks (W-ELAN), Multiscale Channel Split (MCS), and Concatenate Convolutional Layers (CatConv) in our CST-YOLO to improve small-scale object detection precision. Experimental results show that the proposed CST-YOLO achieves 92.7, 95.6, and 91.1 mAP@0.5 respectively on three blood cell datasets, outperforming state-of-the-art object detectors, e.g., YOLOv5 and YOLOv7. Our code is available at https://github.com/mkang315/CST-YOLO.

本文提出了一种基于 YOLOv7 框架的 CST-YOLO 模型来解决典型的计算机视觉中的小物体检测问题，CST 算法被用于增强模型，同时引入了 W-ELAN、MCS 和 CatConv 等模块以提高小尺度目标检测的准确性，实验结果表明，CST-YOLO 在三个血细胞数据集上均超过了现有的目标检测器，如 YOLOv5 和 YOLOv7，达到了92.7、95.6 和 91.1 的 mAP@0.5。

基于改进的YOLOv7和CNN-Swin Transformer的新型血细胞检测方法CST-YOLO