Training strategy for convolutional neural networks in pedestrian gender classification

Choon-Boon Ng; Yong-Haur Tay; Bok-Min Goi

doi:10.1117/12.2280487

19 June 2017 Training strategy for convolutional neural networks in pedestrian gender classification

Choon-Boon Ng, Yong-Haur Tay, Bok-Min Goi

Proceedings Volume 10443, Second International Workshop on Pattern Recognition; 104431A (2017) https://doi.org/10.1117/12.2280487
Event: Second International Workshop on Pattern Recognition, 2017, Singapore, Singapore

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.

Citation Download Citation

Choon-Boon Ng, Yong-Haur Tay, and Bok-Min Goi "Training strategy for convolutional neural networks in pedestrian gender classification", Proc. SPIE 10443, Second International Workshop on Pattern Recognition, 104431A (19 June 2017); https://doi.org/10.1117/12.2280487

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available