Web: http://arxiv.org/abs/2205.05671

May 12, 2022, 1:10 a.m. | Xintao Wang, Chao Dong, Ying Shan

cs.CV updates on arXiv.org arxiv.org

This paper explores training efficient VGG-style super-resolution (SR)
networks with the structural re-parameterization technique. The general
pipeline of re-parameterization is to train networks with multi-branch topology
first, and then merge them into standard 3x3 convolutions for efficient
inference. In this work, we revisit those primary designs and investigate
essential components for re-parameterizing SR networks. First of all, we find
that batch normalization (BN) is important to bring training non-linearity and
improve the final performance. However, BN is typically ignored in …

arxiv cv networks training

More from arxiv.org / cs.CV updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California