Diagonalwise Refactorization: An Efficient Training Method for Depthwise
Convolutions

Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions

27 March 2018

Dongsheng Li

Papers citing "Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions"

4 / 4 papers shown

Title
Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI Dustin Wright Christian Igel Gabrielle Samuel Raghavendra Selvan 29 15 0 05 Sep 2023
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network Vitaliy Chiley Vithursan Thangarasa Abhay Gupta Anshul Samar Joel Hestness D. DeCoste 40 8 0 28 Jun 2022
ShortcutFusion: From Tensorflow to FPGA-based accelerator with reuse-aware memory allocation for shortcut data Duy-Thanh Nguyen Hyeonseung Je Tuan Nghia Nguyen Soojung Ryu Kyujoong Lee Hyuk-Jae Lee 11 23 0 15 Jun 2021
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights Aojun Zhou Anbang Yao Yiwen Guo Lin Xu Yurong Chen MQ 316 1,047 0 10 Feb 2017