Table 5 Proposed model’s performance compared to the prior research.

From: Improving diagnosis accuracy with an intelligent image retrieval system for lung pathologies detection: a features extractor approach

Methods

mAP 0.5

mAP [0.5:0.95]

30: YOLOv5 + ResNet50

–

0.254

30: YOLOv5

–

0.244

30: Fast RCNN

–

0.234

30: EfficientDet

 

0.231

31: Faster RCNN

0.417

–

31: YOLOv5 + ResNet50

0.812

0.466

Ours: YOLOv5 + EfficientNet

0.884

0.546

Back to article page