More Like this

1. 1-D Convolutional Graph Convolutional Networks for Fault Detection in Distributed Energy Systems

   https://doi.org/10.1109/ONCON56984.2022.10126859  

   Nguyen, Bang L.H. ; Vu, Tuyen ; Nguyen, Thai-Thanh ; Panwar, Mayank ; Hovsapian, Rob ( December 2022 , IEEE)
2. Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling [Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling]

   https://doi.org/10.5220/0009156201850195  

   Olmschenk, Greg ; Tang, Hao ; Zhu, Zhigang ( January 2020 , 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications)

   Gatherings of thousands to millions of people frequently occur for an enormous variety of events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event. In this work, we show that the regularly accepted labeling scheme of crowd density maps for training deep neural networks is less effective than our alternative inverse k-nearest neighbor (i$k$NN) maps, even when used directly in existing state-of-the-art network structures. We also provide a new network architecture MUD-i$k$NN, which uses multi-scale upsampling via transposed convolutions to take full advantage of the provided i$k$NN labeling. This upsampling combined with the i$k$NN maps further improves crowd counting accuracy. Our new network architecture performs favorably in comparison with the state-of-the-art. However, our labeling and upsampling techniques are generally applicable to existing crowd counting architectures. 

   more » « less
3. Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

   Liu, Sheng ; Li, Xiao ; Zhai, Yuexiang ; You, Chong ; Zhu, Zhihui ; Fernandez-Granda, Carlos ; Qu, Qing ( January 2021 , Advances in neural information processing systems)

   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}. 

   more » « less
4. How convolutional neural networks see the world --- A survey of convolutional neural network visualization methods

   https://doi.org/10.3934/mfc.2018008  

   Qin, Zhuwei ; Yu, Fuxun ; Liu, Chenchen ; Chen, Xiang ( January 2018 , Mathematical Foundations of Computing)
5. Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

   Sheng Liu ; Xiao Li ; Yuexiang Zhai ; Chong You ; Zhihui Zhu ; Carlos Fernandez-Granda ; Qing Qu ( January 2021 , Neural Information Processing Systems (NeurIPS))