TY - GEN
T1 - Fine-tuning and visualization of convolutional neural networks
AU - Yin, Xiangnan
AU - Chen, Weihai
AU - Wu, Xingming
AU - Yue, Haosong
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - Image classification is a widely discussed topic in the field of computer vision. In recent years, with the application of Convolutional Neural Networks (CNNs), the state-of-the-art in this area has progressed rapidly. To yield a well performed CNN, the advanced GPU and large amount of training data are employed, thus training an entire CNN from scratch is difficult. In practice, fine-tuning a pre-trained CNN is a simple yet effective method to solve a target task. In this paper, we address on the issue of visualizing a fine-tuned CNN, comparing with a small CNN trained from scratch on the same task, to explain how fine-tuning achieve such good performance.
AB - Image classification is a widely discussed topic in the field of computer vision. In recent years, with the application of Convolutional Neural Networks (CNNs), the state-of-the-art in this area has progressed rapidly. To yield a well performed CNN, the advanced GPU and large amount of training data are employed, thus training an entire CNN from scratch is difficult. In practice, fine-tuning a pre-trained CNN is a simple yet effective method to solve a target task. In this paper, we address on the issue of visualizing a fine-tuned CNN, comparing with a small CNN trained from scratch on the same task, to explain how fine-tuning achieve such good performance.
UR - https://www.scopus.com/pages/publications/85047481128
U2 - 10.1109/ICIEA.2017.8283041
DO - 10.1109/ICIEA.2017.8283041
M3 - 会议稿件
AN - SCOPUS:85047481128
T3 - Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017
SP - 1310
EP - 1315
BT - Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017
Y2 - 18 June 2017 through 20 June 2017
ER -