31 citations · 69 across the 10 of their papers we have counts for
10 papers
Exploiting Invariance in Training Deep Neural Networks
Chengxi Ye, Xiong Zhou, Tristan McKinney +3
Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. Th…
Network Deconvolution
Chengxi Ye, Matthew Evanusa, Hua He +5
Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong c…
EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras
Anton Mitrokhin, Chengxi Ye, Cornelia Fermuller +2
We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion m…
Unsupervised Learning of Dense Optical Flow, Depth and Egomotion from Sparse Event Data
Chengxi Ye, Anton Mitrokhin, Cornelia Fermüller +2
In this work we present a lightweight, unsupervised learning pipeline for \textit{dense} depth, optical flow and egomotion estimation from sparse event output of the Dynamic Vision…
Evenly Cascaded Convolutional Networks
Chengxi Ye, Chinmaya Devaraj, Michael Maynord +2
We introduce Evenly Cascaded convolutional Network (ECN), a neural network taking inspiration from the cascade algorithm of wavelet analysis. ECN employs two feature streams - a lo…
On the Importance of Consistency in Training Deep Neural Networks
Chengxi Ye, Yezhou Yang, Cornelia Fermuller +1
We explain that the difficulties of training deep neural networks come from a syndrome of three consistency issues. This paper describes our efforts in their analysis and treatment…