ASP-CNN: aligning semantic parts for fine-grained image classification

Hao Ge; Xiaoguang Tu; Mei Xie; Zheng Ma

doi:10.1117/1.JEI.28.2.023024

1 April 2019 ASP-CNN: aligning semantic parts for fine-grained image classification

Hao Ge, Xiaoguang Tu, Mei Xie, Zheng Ma

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 2, 023024 (April 2019). https://doi.org/10.1117/1.JEI.28.2.023024

Abstract

Recently, numerous methods have been proposed to tackle the problem of fine-grained image classification (FGIC). Most of them follow a two-step strategy that contains detecting the object regions and classifying with the features extracted from these regions. For the feature extraction, the most popular method is directly cropping the feature maps according to the location of detected part regions. However, one challenge of such a method is that the direction of the semantic parts may vary in different images, therefore, it is necessary to capture such differences for better classification. We propose a CNN architecture by aligning semantic parts (ASP-CNN) for FGIC, aiming to increase the interclass variance and meanwhile reduce the intraclass variance in fine-grained datasets. Extensive experiments on CUB-200-2011 and CUB-200-2010 show the effectiveness of our ASP-CNN.

Citation Download Citation

Hao Ge, Xiaoguang Tu, Mei Xie, and Zheng Ma "ASP-CNN: aligning semantic parts for fine-grained image classification," Journal of Electronic Imaging 28(2), 023024 (1 April 2019). https://doi.org/10.1117/1.JEI.28.2.023024

Received: 15 January 2019; Accepted: 20 March 2019; Published: 1 April 2019

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