Local Binary Convolutional Neural Networks

TL;DR

This paper introduces local binary convolution (LBC), a parameter-efficient layer inspired by local binary patterns, that approximates standard convolutional layers while reducing model size and computational cost, maintaining comparable accuracy.

Contribution

The paper presents a novel LBC layer with fixed binary filters and learnable weights, achieving significant parameter and size savings while matching CNN performance.

Findings

LBC layers reduce parameters by up to 169x.

LBCNN achieves comparable accuracy to CNNs on multiple datasets.

LBC layers offer substantial computational savings.

Abstract

We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN). The design principles of LBC are motivated by local binary patterns (LBP). The LBC layer comprises of a set of fixed sparse pre-defined binary convolutional filters that are not updated during the training process, a non-linear activation function and a set of learnable linear weights. The linear weights combine the activated filter responses to approximate the corresponding activated filter responses of a standard convolutional layer. The LBC layer affords significant parameter savings, 9x to 169x in the number of learnable parameters compared to a standard convolutional layer. Furthermore, the sparse and binary nature of the weights also results in up to 9x to 169x savings in model size compared to a standard convolutional layer. We demonstrate both theoretically and experimentally that our local binary convolution layer is a good approximation of a standard convolutional layer. Empirically, CNNs with LBC layers, called local binary convolutional neural networks (LBCNN), achieves performance parity with regular CNNs on a range of visual datasets (MNIST, SVHN, CIFAR-10, and ImageNet) while enjoying significant computational savings.