W&B Paper Reading Group - EfficientNetV2

In this edition of W&B’s Paper Reading Group we will look into the EfficientNetV2 paper in detail & learn all about it. In the paper, the authors seek to establish a general recipe for training deep ResNets without normalization layers which achieve test accuracies competitive with state-of-the-art! Batch Normalization (BatchNorm) has been key in advancing deep learning research in computer vision, but in the past few years a new line of research has emerged that seeks to eliminate layers which normalize activations entirely. --- W&B’s Paper Reading Group is a biweekly, beginner-friendly space led by Aman Arora Register: 📍 --- Agenda: 0:00 Welcome and introduction 3:40 How to read a paper 7:13 EfficientNetV2 Paper 1:05:43 Q&A on the paper Links 👉 EfficientNetV2 paper summary & comments: 👉 Nf-ResNets paper: