DHNet: working double hard to learn a convolutional neural network-based local descriptor

Dandan Li; Dan Zeng; Kai Zhao

doi:10.1117/1.JEI.27.4.043008

10 July 2018 DHNet: working double hard to learn a convolutional neural network-based local descriptor

Dandan Li, Dan Zeng, Kai Zhao

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 4, 043008 (July 2018). https://doi.org/10.1117/1.JEI.27.4.043008

Abstract

Designing effective local descriptors is crucial for many computer vision tasks such as image matching and patch verification. We propose a convolutional neural network (CNN)-based local descriptor named DHNet with a considerate sampling strategy and a dedicated loss function. By considerate sampling, both the closest nonmatching sample and the farther matching sample can be obtained for effectively training a discriminative model. In addition, an improved triplet loss is designed by adding a constraint that limits the absolute distance for the closest nonmatching pair. Based on hard samples and the constraint, our lightweight CNN can quickly generate local descriptors with enhanced intraclass compactness and interclass separation. Experimental results show that our method significantly outperforms the state-of-the-art methods in terms of strong discrimination ability, as evidenced by a considerable performance improvement on several benchmarks.

Citation Download Citation

Dandan Li, Dan Zeng, and Kai Zhao "DHNet: working double hard to learn a convolutional neural network-based local descriptor," Journal of Electronic Imaging 27(4), 043008 (10 July 2018). https://doi.org/10.1117/1.JEI.27.4.043008

Received: 3 April 2018; Accepted: 12 June 2018; Published: 10 July 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

Includes PDF, HTML & Video, when available