Convolutional neural networks (CNNs) are very popular nowadays for image
processing. CNNs allow one to learn optimal filters in a (mostly) supervised
machine learning context. However this typically requires abundant labelled
training data to estimate the filter parameters. Alternative strategies have
been deployed for reducing the number of parameters and / or filters to be
learned and thus decrease overfitting. In the context of reverting to preset
filters, we propose here a computationally efficient harmonic block that uses
Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the
performance of harmonic networks in limited training data scenario. We validate
experimentally that its performance compares well against scattering networks
that use wavelets as preset filters.

本研究表明，使用离散余弦变换（DCT）滤波器的谐波块，可在有限的训练数据情况下与使用小波作为预设滤波器的散射网络相比，有效降低训练参数数量和过度拟合，从而提高卷积神经网络（CNN）的性能。

有限训练样本下的谐波网络

Harmonic Networks with Limited Training Samples

Translating or rotating an input image should not affect the results of many
computer vision tasks. Convolutional neural networks (CNNs) are already
translation equivariant: input image translations produce proportionate feature
map translations. This is not the case for rotations. Global rotation
equivariance is typically sought through data augmentation, but patch-wise
equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN
exhibiting equivariance to patch-wise translation and 360-rotation. We achieve
this by replacing regular CNN filters with circular harmonics, returning a
maximal response and orientation for every receptive field patch.
H-Nets use a rich, parameter-efficient and low computational complexity
representation, and we show that deep feature maps within the network encode
complicated rotational invariants. We demonstrate that our layers are general
enough to be used in conjunction with the latest architectures and techniques,
such as deep supervision and batch normalization. We also achieve
state-of-the-art classification on rotated-MNIST, and competitive results on
other benchmark challenges.

本研究介绍了一种基于谐波函数的网络 ——Harmonic Networks（H-Nets），H-Nets 可以实现对位移和 360 度旋转的等变性，并应用于深度学习技术及分类问题中，表现出很高的精度表现。