# Regularized Binary Network Training

Source: [Regularized Binary Network Training](<https://www.sota2.com/research/paper/68fa676d1e209131cea16215>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:42.559Z

Authors: Sajad Darabi, Mouloud Belbahri, Matthieu Courbariaux, Vahid Partovi Nia

Published: 2018-12-31T14:07:08.000Z

## Abstract

There is a significant performance gap between Binary Neural Networks (BNNs) and floating point Deep Neural Networks (DNNs). We propose to improve the binary training method, by introducing a new regularization function that encourages training weights around binary values. In addition, we add trainable scaling factors to our regularization functions. Additionally, an improved approximation of the derivative of the sign activation function in the backward computation. These modifications are based on linear operations that are easily implementable into the binary training framework. Experimental results on ImageNet shows our method outperforms the traditional BNN method and XNOR-net.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: 91.31.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1812.11800>)

[PDF](<https://arxiv.org/pdf/1812.11800.pdf>)