English

Learning to map between ferns with differentiable binary embedding networks

Computer Vision and Pattern Recognition 2020-05-29 v1

Abstract

Current deep learning methods are based on the repeated, expensive application of convolutions with parameter-intensive weight matrices. In this work, we present a novel concept that enables the application of differentiable random ferns in end-to-end networks. It can then be used as multiplication-free convolutional layer alternative in deep network architectures. Our experiments on the binary classification task of the TUPAC'16 challenge demonstrate improved results over the state-of-the-art binary XNOR net and only slightly worse performance than its 2x more parameter intensive floating point CNN counterpart.

Keywords

Cite

@article{arxiv.2005.12563,
  title  = {Learning to map between ferns with differentiable binary embedding networks},
  author = {Max Blendowski and Mattias P. Heinrich},
  journal= {arXiv preprint arXiv:2005.12563},
  year   = {2020}
}
R2 v1 2026-06-23T15:48:46.084Z