How deep convolutional neural networks lose spatial information with training

4 October 2022

Papers citing "How deep convolutional neural networks lose spatial information with training"

4 / 4 papers shown

Title
An Empirical Study on Fault Detection and Root Cause Analysis of Indium Tin Oxide Electrodes by Processing S-parameter Patterns Tae Yeob Kang Haebom Lee S. Suh 16 0 0 16 Aug 2023
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups Marc Finzi Max Welling A. Wilson 71 185 0 19 Apr 2021
E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials Simon L. Batzner Albert Musaelian Lixin Sun Mario Geiger J. Mailoa M. Kornbluth N. Molinari Tess E. Smidt Boris Kozinsky 188 1,218 0 08 Jan 2021
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 220 347 0 14 Jun 2018