Adding the CBAM attention module to ResNet50 lowered the reported MAPE for PCI prediction from pavement images to 58.16%, from 70.76% for ResNet50 and 65.48% for DenseNet161.
Research trends in pavement management during the first years of the 21st century: A bibliometric analysis during the 2000–2013 period,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Improved ResNet50 Model for Predicting Pavement Condition Index (PCI) Directly from Pavement Images
Adding the CBAM attention module to ResNet50 lowered the reported MAPE for PCI prediction from pavement images to 58.16%, from 70.76% for ResNet50 and 65.48% for DenseNet161.