论文标题
基于深度静止的可分离卷积神经网络
Depthwise-STFT based separable Convolutional Neural Networks
论文作者
论文摘要
在本文中，我们提出了一个新的卷积层，称为深度为stft可分离层，可以作为标准深度可分离卷积层的替代方案。所提出的层的构造灵感来自以下事实：傅立叶系数可以准确地代表重要特征，例如图像中的边缘。它利用输入映射的每个位置的2D局部邻域（例如3x3）中计算出的傅立叶系数（Channelwise）来获得特征图。使用2D短期傅立叶变换（STFT）在每个位置的2D局部邻域中的多个固定低频点上计算傅立叶系数。然后，使用可训练的点（1x1）卷积将不同频率点的这些特征图线性合并。我们表明，所提出的层的表现优于CIFAR-10和CIFAR-100图像分类数据集的标准深度可分离层模型，其时空复杂性降低。
In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is inspired by the fact that the Fourier coefficients can accurately represent important features such as edges in an image. It utilizes the Fourier coefficients computed (channelwise) in the 2D local neighborhood (e.g., 3x3) of each position of the input map to obtain the feature maps. The Fourier coefficients are computed using 2D Short Term Fourier Transform (STFT) at multiple fixed low frequency points in the 2D local neighborhood at each position. These feature maps at different frequency points are then linearly combined using trainable pointwise (1x1) convolutions. We show that the proposed layer outperforms the standard depthwise separable layer-based models on the CIFAR-10 and CIFAR-100 image classification datasets with reduced space-time complexity.
