ResNet strikes back: An improved training procedure

Oct 24, 2021 · Palo Alto, United States of America

This session we will discuss:

**ResNet strikes back: An improved training procedure in timm** by Ross Wightman, Hugo Touvron, Hervé Jégou
paper link: https://arxiv.org/abs/2110.00476

EVERYONE SHOULD TAKE THE TIME TO READ THE PAPER IN DETAIL SEVERAL DAYS BEFORE THE MEETUP and ideally also familiarize themselves with any necessary background information and key references (please see below). Everyone should come prepared to participate.

This is an online session. Details will be available to previous attendees in the DLSG Slack channel. Additional attendees by invitation. If you are completely new to the group or not from the Bay Area, please ping Jeff on LinkedIn first - https://www.linkedin.com/in/jeffcoggshall/

PAPER ABSTRACT
=================
* The influential Residual Networks designed by He et al. remain the gold-standard architecture in numerous scientific publications. They typically serve as the default architecture in studies, or as baselines when new architectures are proposed.

* Yet there has been significant progress on best practices for training neural networks since the inception of the ResNet architecture in 2015. Novel optimization & data-augmentation have increased the effectiveness of the training recipes.

* In this paper, we re-evaluate the performance of the vanilla ResNet-50 when trained with a procedure that integrates such advances. We share competitive training settings and pre-trained models in the timm open-source library, with the hope that they will serve as better baselines for future work.

* For instance, with our more demanding training setting, a vanilla ResNet-50 reaches 80.4% top-1 accuracy at resolution 224x224 on ImageNet-val without extra data or distillation. We also report the performance achieved with popular models with our training procedure.
------------------------------------------------------------------------------------

Key Prerequisite Papers
=========================================================
* COMING SOON PLEASE CHECK AGAIN IN A FEW DAYS

Additional Resources
=========================================================
* COMING SOON PLEASE CHECK AGAIN IN A FEW DAYS

Interesting Optional Reading
=========================================================
* COMING SOON PLEASE CHECK AGAIN IN A FEW DAYS

Event organizers

Are you organizing ResNet strikes back: An improved training procedure ?

Claim the event and start manage its content.

I am the organizer
Social
Rating

based on 0 reviews

Featured Events