TY - GEN
T1 - A visual attention based convolutional neural network for image classification
AU - Chen, Yaran
AU - Zhao, Dongbin
AU - Lv, Le
AU - Li, Chengdong
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/9/27
Y1 - 2016/9/27
N2 - This paper presents a visual attention based convolutional neural network (CNN) to solve the image classification problem in the real complex world scene. The presented method can simulate the process of recognizing objects and find the area of interest which is related with the task. Compared with the CNN method in image classification, the model is proficient in fine-grained classification problem and has a better robustness due to its mechanism of multi-glance and visual attention. We evaluate the model on vehicle dataset, where its performance exceeds CNN baseline on image classification.
AB - This paper presents a visual attention based convolutional neural network (CNN) to solve the image classification problem in the real complex world scene. The presented method can simulate the process of recognizing objects and find the area of interest which is related with the task. Compared with the CNN method in image classification, the model is proficient in fine-grained classification problem and has a better robustness due to its mechanism of multi-glance and visual attention. We evaluate the model on vehicle dataset, where its performance exceeds CNN baseline on image classification.
UR - http://www.scopus.com/inward/record.url?scp=84991585452&partnerID=8YFLogxK
U2 - 10.1109/WCICA.2016.7578651
DO - 10.1109/WCICA.2016.7578651
M3 - Conference Proceeding
AN - SCOPUS:84991585452
T3 - Proceedings of the World Congress on Intelligent Control and Automation (WCICA)
SP - 764
EP - 769
BT - Proceedings of the 2016 12th World Congress on Intelligent Control and Automation, WCICA 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th World Congress on Intelligent Control and Automation, WCICA 2016
Y2 - 12 June 2016 through 15 June 2016
ER -