CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kang, Ming, Ting, Chee-Ming, Ting, Fung Fung, Phan, Raphaël
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929528414142464
author Kang, Ming
Ting, Chee-Ming
Ting, Fung Fung
Phan, Raphaël
author_facet Kang, Ming
Ting, Chee-Ming
Ting, Fung Fung
Phan, Raphaël
contents 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., RT-DETR, YOLOv5, and YOLOv7. Our code is available at https://github.com/mkang315/CST-YOLO.
format Preprint
id arxiv_https___arxiv_org_abs_2306_14590
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer
Kang, Ming
Ting, Chee-Ming
Ting, Fung Fung
Phan, Raphaël
Computer Vision and Pattern Recognition
Signal Processing
Applications
Machine Learning
68T07, 68T10, 68U10, 62P10
I.4.6; I.5.1; J.3
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., RT-DETR, YOLOv5, and YOLOv7. Our code is available at https://github.com/mkang315/CST-YOLO.
title CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer
topic Computer Vision and Pattern Recognition
Signal Processing
Applications
Machine Learning
68T07, 68T10, 68U10, 62P10
I.4.6; I.5.1; J.3
url https://arxiv.org/abs/2306.14590