Paper
13 October 2022 A brief analysis on damaged building classification: optimizer and learning rate
Ruixin Qiao, Ruhan Wang, Yukang Zou
Author Affiliations +
Proceedings Volume 12287, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022); 122871H (2022) https://doi.org/10.1117/12.2640965
Event: International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022), 2022, Wuhan, China
Abstract
Image Classification is a fundamental task that attempts to comprehend an entire image as a whole. Using a suitable optimizer and useful learning rate adjustment strategy is very important in this task. Recently some papers have discussed the effects of different learning rate adjustment strategies combined with different neural networks. However, there is little discussion about the effects of learning rate adjustment strategies combined with different optimizers. In this paper, we compare the effects of different combinations of different optimizers and learning rate adjustment strategies on image classification task. After analyzing the experimental results, we found that the combination of RMSProp and ExponentialLR obtained the best result. The combination increases the training speed and achieves high accuracy.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ruixin Qiao, Ruhan Wang, and Yukang Zou "A brief analysis on damaged building classification: optimizer and learning rate", Proc. SPIE 12287, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022), 122871H (13 October 2022); https://doi.org/10.1117/12.2640965
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Image classification

Signal attenuation

Convolution

Visual process modeling

Visualization

Process modeling

Back to Top