Publication
WACV 2014
Conference paper

Learning mid-level features from object hierarchy for image classification

View publication

Abstract

We propose a new approach for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representation implicitly captures the hierarchical structure in object classes. We show that our proposed approach outperforms other baseline methods in image classification. © 2014 IEEE.

Date

24 Mar 2014

Publication

WACV 2014

Share