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 [email protected] 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.

翻译：血细胞检测是计算机视觉中典型的小尺度目标检测问题。本文提出了一种基于YOLOv7架构的血细胞检测模型CST-YOLO，并通过集成CNN-Swin Transformer（CST）对其进行增强，这是CNN-Transformer融合的一次新尝试。我们还在CST-YOLO中引入了三个其他实用模块：加权高效层聚合网络（W-ELAN）、多尺度通道分割（MCS）和级联卷积层（CatConv），以提高小尺度目标检测精度。实验结果表明，所提出的CST-YOLO在三个血细胞数据集上分别实现了92.7、95.6和91.1的[email protected]，性能优于现有最先进的目标检测器，例如YOLOv5和YOLOv7。我们的代码开源在https://github.com/mkang315/CST-YOLO。