TY - GEN
T1 - Chinese herbal recognition by Spatial-/Channel-wise attention
AU - Wu, Nan
AU - Lou, Jie
AU - Lv, Juan
AU - Liu, Feihan
AU - Wu, Xingjiao
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Chinese herbal recognition has played an essential role in traditional Chinese medicine. Chinese herbal recognition is essentially an image classification task. However, unlike general image classification tasks, due to the particularity of Chinese medicine, traditional Chinese herbal medicine recognition pays more attention to the details of identification objects. However, the details that rely on the delicate paper size cannot be completely distinguished. In many cases, there is a large variety of different types of Chinese medicine. Paying too much attention to the details will cause the model to fall into partial dependence. So many times users need to use global features. In order to solve this challenge, we propose an effective way to model the mechanism by exploiting Spatial-/Channel-wise attention. Besides, we also leverage a dynamic adaptation mechanism that helps the model to balance global and detailed information. We verified the effectiveness of the proposed method via a series of experiments.
AB - Chinese herbal recognition has played an essential role in traditional Chinese medicine. Chinese herbal recognition is essentially an image classification task. However, unlike general image classification tasks, due to the particularity of Chinese medicine, traditional Chinese herbal medicine recognition pays more attention to the details of identification objects. However, the details that rely on the delicate paper size cannot be completely distinguished. In many cases, there is a large variety of different types of Chinese medicine. Paying too much attention to the details will cause the model to fall into partial dependence. So many times users need to use global features. In order to solve this challenge, we propose an effective way to model the mechanism by exploiting Spatial-/Channel-wise attention. Besides, we also leverage a dynamic adaptation mechanism that helps the model to balance global and detailed information. We verified the effectiveness of the proposed method via a series of experiments.
KW - Channel-wise attention
KW - Chinese herbal recognition
KW - Spatial-wise attention
KW - global features
UR - https://www.scopus.com/pages/publications/85147245686
U2 - 10.1109/TOCS56154.2022.10016159
DO - 10.1109/TOCS56154.2022.10016159
M3 - 会议稿件
AN - SCOPUS:85147245686
T3 - 2022 IEEE Conference on Telecommunications, Optics and Computer Science, TOCS 2022
SP - 1145
EP - 1150
BT - 2022 IEEE Conference on Telecommunications, Optics and Computer Science, TOCS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE Conference on Telecommunications, Optics and Computer Science, TOCS 2022
Y2 - 11 December 2022 through 12 December 2022
ER -