25 citations · 32 across the 2 of their papers we have counts for
13 papers
Normalization Techniques in Training DNNs: Methodology, Analysis and Application
Lei Huang, Jie Qin, Yi Zhou +3
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various app…
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
Ionut Cosmin Duta, Li Liu, Fan Zhu +1
This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales. PyConv contains a pyramid of kernels, where each level invo…
Improved Residual Networks for Image and Video Recognition
Ionut Cosmin Duta, Li Liu, Fan Zhu +1
Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an impro…
Controllable Orthogonalization in Training DNNs
Lei Huang, Li Liu, Fan Zhu +4
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in represe…
An Investigation into the Stochasticity of Batch Whitening
Lei Huang, Lei Zhao, Yi Zhou +3
Batch Normalization (BN) is extensively employed in various network architectures by performing standardization within mini-batches. A full understanding of the process has been a…
Auto-Encoding Twin-Bottleneck Hashing
Yuming Shen, Jie Qin, Jiaxin Chen +5
Conventional unsupervised hashing methods usually take advantage of similarity graphs, which are either pre-computed in the high-dimensional space or obtained from random anchor po…