Stride determines the distance between adjacent filter positions as the
filter moves across the input. A fixed stride causes important information
contained in the image can not be captured, so that important information is
not classified. Therefore, in previous research, the DiffStride Method was
applied, namely the Strided Convolution Method with which it can learn its own
stride value. Severe Quantization and a constraining lower bound on preserved
information are arises with Max Pooling Downsampling Method. Spectral Pooling
reduce the constraint lower bound on preserved information by cutting off the
representation in the frequency domain. In this research a CNN Model is
proposed with the Downsampling Learnable Stride Technique performed by
Backpropagation combined with the Spectral Pooling Technique. Diffstride and
Spectral Pooling techniques are expected to maintain most of the information
contained in the image. In this study, we compare the Hybrid Method, which is a
combined implementation of Spectral Pooling and DiffStride against the Baseline
Method, which is the DiffStride implementation on ResNet 18. The accuracy
result of the DiffStride combination with Spectral Pooling improves over
DiffStride which is baseline method by 0.0094. This shows that the Hybrid
Method can maintain most of the information by cutting of the representation in
the frequency domain and determine the stride of the learning result through
Backpropagation.

本研究提出了一种卷积神经网络模型，通过反向传播结合频谱汇聚技术，执行学习可调步长技术的下采样，旨在保留图像中的大部分信息。与基线方法 DiffStride 相比，DiffStride 与频谱汇聚的混合方法在准确率上提高了 0.0094。

卷积神经网络中的 DiffStride 和 Spectral Pooling 的混合

Hybrid of DiffStride and Spectral Pooling in Convolutional Neural  Networks

Winograd's minimal filtering algorithm has been widely used in Convolutional
Neural Networks (CNNs) to reduce the number of multiplications for faster
processing. However, it is only effective on convolutions with kernel size as
3x3 and stride as 1, because it suffers from significantly increased FLOPs and
numerical accuracy problem for kernel size larger than 3x3 and fails on
convolution with stride larger than 1. In this paper, we propose a novel
Decomposable Winograd Method (DWM), which breaks through the limitation of
original Winograd's minimal filtering algorithm to a wide and general
convolutions. DWM decomposes kernels with large size or large stride to several
small kernels with stride as 1 for further applying Winograd method, so that
DWM can reduce the number of multiplications while keeping the numerical
accuracy. It enables the fast exploring of larger kernel size and larger stride
value in CNNs for high performance and accuracy and even the potential for new
CNNs. Comparing against the original Winograd, the proposed DWM is able to
support all kinds of convolutions with a speedup of ~2, without affecting the
numerical accuracy.

本文提出了一种新的分解 Winograd 方法（DWM），可以显著提高 Winograd 算法在卷积神经网络中的应用范围（包括大尺寸核和大步长卷积），从而在保持数值精度的同时，减少计算量和提高性能。