论文标题
2srelu中频域中的图像分类：第二个谐波叠加激活函数
Image classification in frequency domain with 2SReLU: a second harmonics superposition activation function
论文作者
论文摘要
深度卷积神经网络能够识别复杂的模式并具有超人能力。但是，除了出色的结果外，它们尚未完全理解，并且手工设计类似解决方案仍然不切实际。在这项工作中，从频域的角度描述了图像分类卷积神经网络及其构件。一些网络层已经在频域中建立了同行，例如卷积和合并层。我们提出了2srelu层，这是一种新型的非线性激活函数，可保留深网中的高频分量。证明在频域中，可以在不使用计算昂贵的卷积操作的情况下获得竞争成果。提供了Pytorch中的源代码实现：https：//gitlab.com/thomio/2srelu
Deep Convolutional Neural Networks are able to identify complex patterns and perform tasks with super-human capabilities. However, besides the exceptional results, they are not completely understood and it is still impractical to hand-engineer similar solutions. In this work, an image classification Convolutional Neural Network and its building blocks are described from a frequency domain perspective. Some network layers have established counterparts in the frequency domain like the convolutional and pooling layers. We propose the 2SReLU layer, a novel non-linear activation function that preserves high frequency components in deep networks. It is demonstrated that in the frequency domain it is possible to achieve competitive results without using the computationally costly convolution operation. A source code implementation in PyTorch is provided at: https://gitlab.com/thomio/2srelu
