Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification

TL;DR

This paper introduces DDSFL, a hierarchical local feature learning method that captures class correlation, discriminative information, and shared visual patterns for improved scene image classification.

Contribution

The paper proposes a novel hierarchical feature learning approach with shareable filters and exemplar selection for enhanced scene image classification.

Findings

DDSFL achieves promising classification performance.

It complements state-of-the-art Caffe features effectively.

Shareable filters encode common visual patterns across classes.

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.