Look before we leap: reinforced active sampling framework for image classification

Zhipeng Ye; Rui Jia; Xi Chen; Qiang Wu

doi:10.1117/1.JEI.27.4.043034

2 August 2018 Look before we leap: reinforced active sampling framework for image classification

Zhipeng Ye, Rui Jia, Xi Chen, Qiang Wu

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 4, 043034 (August 2018). https://doi.org/10.1117/1.JEI.27.4.043034

Abstract

We aim to improve the negative-accelerated sampling framework and construct a more reasonable and effective active sampling framework by introducing the technique of reinforcement learning. Compared with traditional uncertainty-based active sampling strategy, the proposed sample selection framework consists of both a certainty metric and sample postprocessing for more precise evaluation. The certainty metric is measured by the visual classifying model, and the postprocessing module is implemented by the Q-learning algorithm to construct a compact training set for the visual module to further improve the effectiveness and efficiency of classification. Meanwhile, the parameters of the whole sampling framework are calculated adaptively instead of being set manually to improve the adaptiveness of the whole framework. Experimental results on real-world datasets show the effectiveness of the proposed framework.

Citation Download Citation

Zhipeng Ye, Rui Jia, Xi Chen, and Qiang Wu "Look before we leap: reinforced active sampling framework for image classification," Journal of Electronic Imaging 27(4), 043034 (2 August 2018). https://doi.org/10.1117/1.JEI.27.4.043034

Received: 8 April 2018; Accepted: 10 July 2018; Published: 2 August 2018

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