Share Email Print
cover

Proceedings Paper

An ethnic costumes classification model with optimized learning rate
Author(s): Shuang Zhang; Zongxi Song
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In the convolutional neural network model, the learning rate represents the magnitude of the neural network parameters that change at each iteration. When the learning rate is too high, the loss function will oscillate without converging. When the learning rate is too low, the loss function converges slowly. How to set the appropriate value of the learning rate becomes an important issue. Based on the learning rate annealing algorithm, this paper sets the segmentation attenuation and adds periodic pulse perturbation. The learning rate gradually declines and rises at the end of the cycle, and then continues to fall. This prevents the network from oscillating at a local minimum or saddle point in the late training period due to the low learning rate [1]. Finally, this paper verifies the method in the application of ethnic clothing classification using the transfer learning VGG-16 model.

Paper Details

Date Published: 14 August 2019
PDF: 7 pages
Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 111791K (14 August 2019); doi: 10.1117/12.2539608
Show Author Affiliations
Shuang Zhang, Xi'an Institute of Optics and Precision Mechanics of CAS (China)
Univ. of Chinese Academy of Sciences (China)
Zongxi Song, Xi'an Institute of Optics and Precision Mechanics of CAS (China)


Published in SPIE Proceedings Vol. 11179:
Eleventh International Conference on Digital Image Processing (ICDIP 2019)
Jenq-Neng Hwang; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray