Grad-CAM: Understanding AI Models

Wang, Shuihua; Zhang, Yudong

doi:10.32604/cmc.2023.041419

Cited by 5 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grad-CAM helps to understand the focus of the model by generating heat maps that indicate the regions of interest of the model in the input image [24]. To more accurately assess the contribution of BiFPN-SE in the network, this study compares the visualization effects of PANet and BiFPN-SE structure-based networks using the Grad-CAM technique [25][26][27].…”

Section: Validation Of Bifpn and Se Module Effectsmentioning

confidence: 99%

Improvement of the YOLOv5 Model in the Optimization of the Brown Spot Disease Recognition Algorithm of Kidney Bean

Su,

Li,

Wang

et al. 2023

Plants

View full text Add to dashboard Cite

The kidney bean is an important cash crop whose growth and yield are severely affected by brown spot disease. Traditional target detection models cannot effectively screen out key features, resulting in model overfitting and weak generalization ability. In this study, a Bi-Directional Feature Pyramid Network (BiFPN) and Squeeze and Excitation (SE) module were added to a YOLOv5 model to improve the multi-scale feature fusion and key feature extraction abilities of the improved model. The results show that the BiFPN and SE modules show higher heat in the target location region and pay less attention to irrelevant environmental information in the non-target region. The detection Precision, Recall, and mean average Precision (mAP@0.5) of the improved YOLOv5 model are 94.7%, 88.2%, and 92.5%, respectively, which are 4.9% higher in Precision, 0.5% higher in Recall, and 25.6% higher in the mean average Precision compared to the original YOLOv5 model. Compared with the YOLOv5-SE, YOLOv5-BiFPN, FasterR-CNN, and EfficientDet models, detection Precision improved by 1.8%, 3.0%, 9.4%, and 9.5%, respectively. Moreover, the rate of missed and wrong detection in the improved YOLOv5 model is only 8.16%. Therefore, the YOLOv5-SE-BiFPN model can more effectively detect the brown spot area of kidney beans.

show abstract