Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

60 Scopus Citations
View graph of relations

Author(s)

  • Zhen Zuo
  • Gang Wang
  • Bing Shuai
  • Lifan Zhao
  • Qingxiong Yang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)3004-3015
Journal / PublicationPattern Recognition
Volume48
Issue number10
Online published16 Feb 2015
Publication statusPublished - Oct 2015

Abstract

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically learn feature transformation filter banks to transform raw pixel image patches to features. The learned filter banks are expected to (1) encode common visual patterns of a flexible number of categories; (2) encode discriminative information; and (3) hierarchically extract patterns at different visual levels. Particularly, in each single layer of DDSFL, shareable filters are jointly learned for classes which share the similar patterns. Discriminative power of the filters is achieved by enforcing the features from the same category to be close, while features from different categories to be far away from each other. Furthermore, we also propose two exemplar selection methods to iteratively select training data for more efficient and effective learning. Based on the experimental results, DDSFL can achieve very promising performance, and it also shows great complementary effect to the state-of-the-art Caffe features.

Research Area(s)

  • Deep feature learning, Discriminative training, Information sharing, Scene image classification

Citation Format(s)

Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification. / Zuo, Zhen; Wang, Gang; Shuai, Bing et al.
In: Pattern Recognition, Vol. 48, No. 10, 10.2015, p. 3004-3015.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review