Semi-supervised adversarial training of a lightweight neural network for visual recognition

Kaan Karaman; Ibrahim Batuhan Akkaya

doi:10.1117/12.2533456

7 October 2019 Semi-supervised adversarial training of a lightweight neural network for visual recognition

Kaan Karaman, Ibrahim Batuhan Akkaya

Proceedings Volume 11166, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III; 111660O (2019) https://doi.org/10.1117/12.2533456
Event: SPIE Security + Defence, 2019, Strasbourg, France

Abstract

Deep learning is a widely utilized approach specifically for computer vision applications. Visual recognition is one of the applications utilizing deep learning. Several challenges limit the performance of visual recognition methods. One of the most important challenges is the insufficient number of labeled data in the datasets. To overcome this challenge, the recent studies propose sophisticated methods which require high computational resources, which may create another problem. That is, the implementation of such algorithms on mobile devices is quite challenging. Especially, these issues are encountered in surveillance systems that utilize the drones and/or CC-TVs. To solve these problems and obtain high accuracy, the network should be able to extract both representative and discriminative features from such a small amount of data. In this paper, we propose a generative adversarial semi-supervised training method for visual recognition. Experiments are performed to evaluate a lightweight deep convolutional neural network as a classifier network that is trained by the proposed method and a conditional/unconditional generator networks that are examined in adversarial training.

Conference Presentation

Citation Download Citation

Kaan Karaman and Ibrahim Batuhan Akkaya "Semi-supervised adversarial training of a lightweight neural network for visual recognition", Proc. SPIE 11166, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III, 111660O (7 October 2019); https://doi.org/10.1117/12.2533456

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