Histogram Layers for Neural Engineered Features

TL;DR

This paper introduces neural histogram layers that embed traditional histogram-based features like local binary patterns and edge histograms into deep learning models, enhancing image classification performance.

Contribution

It proposes neural implementations of histogram features, enabling their integration into neural networks for improved feature representation and classification.

Findings

Neural histogram layers effectively learn local binary patterns and edge histograms.

Incorporating histogram layers improves classification accuracy.

Experiments demonstrate superior performance on benchmark datasets.

Abstract

In the computer vision literature, many effective histogram-based features have been developed. These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer vision tasks. In this paper, we explore whether these features can be learned through histogram layers embedded in a neural network and, therefore, be leveraged within deep learning frameworks. By using histogram features, local statistics of the feature maps from the convolution neural networks can be used to better represent the data. We present neural versions of local binary pattern and edge histogram descriptors that jointly improve the feature representation and perform image classification. Experiments are presented on benchmark and real-world datasets.