Timezone: »

 
Poster
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
Sheng Liu · Xiao Li · Simon Zhai · Chong You · Zhihui Zhu · Carlos Fernandez-Granda · Qing Qu

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve robustness. For ConvNets, most existing methods are based on penalizing or normalizing weight matrices derived from concatenating or flattening the convolutional kernels. These methods often destroy or ignore the benign convolutional structure of the kernels; therefore, they are often expensive or impractical for deep ConvNets. In contrast, we introduce a simple and efficient ``Convolutional Normalization'' (ConvNorm) method that can fully exploit the convolutional structure in the Fourier domain and serve as a simple plug-and-play module to be conveniently incorporated into any ConvNets. Our method is inspired by recent work on preconditioning methods for convolutional sparse coding and can effectively promote each layer's channel-wise isometry. Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets. Applied to classification under noise corruptions and generative adversarial network (GAN), we show that the ConvNorm improves the robustness of common ConvNets such as ResNet and the performance of GAN. We verify our findings via numerical experiments on CIFAR and ImageNet. Our implementation is available online at \url{https://github.com/shengliu66/ConvNorm}.

Keywords: Deep Learning · Machine Learning · Robustness · Generative Model

Author Information

Sheng Liu (NYU)
Xiao Li (University of Michigan)
Simon Zhai (UC Berkeley)
Chong You (University of California, Berkeley)
Zhihui Zhu (University of Denver)
Carlos Fernandez-Granda (NYU)
Qing Qu (University of Michigan)

More from the Same Authors