Toward Optimal Adenovirus Detection Using YOLO26
2026-07-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors tested different ways to make their training data more varied (called data augmentation) to help a computer program called YOLO26 detect adenoviruses in microscope images. They used a special virus image dataset, updated the labels to fit YOLO26’s needs, and compared several augmentation methods under the same conditions. Their experiments showed which data augmentation method helped YOLO26 detect adenoviruses best. This research helps understand how to improve virus detection in images using machine learning.
data augmentationYOLO26adenovirustransmission electron microscopy (TEM)object detectionbounding box annotationNASGASGMASDAS
Authors
Olivier Rukundo
Abstract
This study systematically benchmarks different data augmentation setups across YOLO26 model size variants to determine the most effective setup for adenovirus detection in TEM images. The benchmarked setups include NAS, GAS, GMAS and DAS, all evaluated under identical training conditions. The adenovirus dataset, selected from the published TEM virus dataset, was re-annotated by leveraging adenovirus particle positions to generate YOLO-compatible bounding box annotations. The experimental results demonstrated the impact of the benchmarked data augmentation setups on adenovirus detection with YOLO26 and indicated the most effective data augmentation setup.