Harmonic Networks: Integrating Spectral Information into CNNs
Computer Vision and Pattern Recognition
2018-12-11 v1 Machine Learning
Abstract
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinations of spectral filters defined by the Discrete Cosine Transform. The harmonic blocks are used to replace conventional convolutional layers to construct partial or fully harmonic CNNs. We extensively validate our approach and show that the introduction of harmonic blocks into state-of-the-art CNN baseline architectures results in comparable or better performance in classification tasks on small NORB, CIFAR10 and CIFAR100 datasets.
Cite
@article{arxiv.1812.03205,
title = {Harmonic Networks: Integrating Spectral Information into CNNs},
author = {Matej Ulicny and Vladimir A. Krylov and Rozenn Dahyot},
journal= {arXiv preprint arXiv:1812.03205},
year = {2018}
}