Visual Explanations of ResNet 101 for Blister Package Classification
Issued Date
2022-01-01
Resource Type
Scopus ID
2-s2.0-85141810183
Journal Title
Proceedings - 2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022
Start Page
148
End Page
152
Rights Holder(s)
SCOPUS
Bibliographic Citation
Proceedings - 2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022 (2022) , 148-152
Suggested Citation
Hnoohom N., Maitrichit N., Wongpatikaseree K., Yuenyong S., Mekruksavanich S., Jitpattanakul A. Visual Explanations of ResNet 101 for Blister Package Classification. Proceedings - 2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022 (2022) , 148-152. 152. doi:10.1109/RI2C56397.2022.9910317 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/84338
Title
Visual Explanations of ResNet 101 for Blister Package Classification
Author's Affiliation
Other Contributor(s)
Abstract
This paper presents an efficient approach to generate visual explanations from a ResNet 101 model for identification of medication. The blister package dataset is used to train a deep learning model built on the PyTorch framework's ResNet 101 pre-trained model. Visual inspections and a quantitative localization benchmark demonstrate that the model approach correctly identifies the critical components of blister packs for medicine identification. A Gradient-weighted Class Activation Mapping (Grad-CAM) method is used to extract the feature map, and then the attention mechanism is utilized to extract the high-level attention maps, that emphasizes the part of the image that is significant to the target class, which can be considered as a visual representation. The experimental results indicated that the Grad-CAM achieved the better visualization and interpretation of ResNet 101 in blister package classification.