Share Email Print

Proceedings Paper

Training strategy for convolutional neural networks in pedestrian gender classification
Author(s): Choon-Boon Ng; Yong-Haur Tay; Bok-Min Goi
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network’s generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.

Paper Details

Date Published: 19 June 2017
PDF: 5 pages
Proc. SPIE 10443, Second International Workshop on Pattern Recognition, 104431A (19 June 2017); doi: 10.1117/12.2280487
Show Author Affiliations
Choon-Boon Ng, Univ. Tunku Abdul Rahman (Malaysia)
Yong-Haur Tay, Univ. Tunku Abdul Rahman (Malaysia)
Bok-Min Goi, Univ. Tunku Abdul Rahman (Malaysia)

Published in SPIE Proceedings Vol. 10443:
Second International Workshop on Pattern Recognition
Xudong Jiang; Masayuki Arai; Guojian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top