论文标题
小波集成的CNN用于噪声图像分类
Wavelet Integrated CNNs for Noise-Robust Image Classification
论文作者
论文摘要
卷积神经网络（CNN）通常容易出现噪声中断，即，小图像噪声会导致输出发生巨大变化。为了抑制最终预测的噪声效应，我们通过替换最大通用，横向卷积和通过离散小波变换（DWT）来增强CNN。我们提供了适用于Haar，Daubechies和Cohen等各种小波的DWT和逆DWT（IDWT）层，并使用这些图层进行图像分类，以及设计小波集成的CNNS（WAVECNET）。在WAVECNET中，特征图在下采样过程中分解为低频和高频组件。低频组件存储主要信息，包括基本对象结构，该信息将传输到后续层中以提取可靠的高级特征。在推断过程中，含有大多数数据噪声的高频组件被删除，以提高WAVECNET的噪声。我们对Imagenet和Imagenet-C（嘈杂的Imagenet版本）的实验结果表明，WaveCnet，VGG，Resnets和Densenet的小波集成版本比其香草版获得了更高的精度和更好的噪声。
Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.
