English

Learning Architectures for Binary Networks

Computer Vision and Pattern Recognition 2020-04-13 v2 Machine Learning

Abstract

Backbone architectures of most binary networks are well-known floating point architectures such as the ResNet family. Questioning that the architectures designed for floating point networks would not be the best for binary networks, we propose to search architectures for binary networks (BNAS) by defining a new search space for binary architectures and a novel search objective. Specifically, based on the cell based search method, we define the new search space of binary layer types, design a new cell template, and rediscover the utility of and propose to use the Zeroise layer instead of using it as a placeholder. The novel search objective diversifies early search to learn better performing binary architectures. We show that our proposed method searches architectures with stable training curves despite the quantization error inherent in binary networks. Quantitative analyses demonstrate that our searched architectures outperform the architectures used in state-of-the-art binary networks and outperform or perform on par with state-of-the-art binary networks that employ various techniques other than architectural changes.

Keywords

Cite

@article{arxiv.2002.06963,
  title  = {Learning Architectures for Binary Networks},
  author = {Dahyun Kim and Kunal Pratap Singh and Jonghyun Choi},
  journal= {arXiv preprint arXiv:2002.06963},
  year   = {2020}
}

Comments

The manuscript was changed to a one-column format along with minor modifications to the content

R2 v1 2026-06-23T13:43:58.828Z