Drawing Multiple Augmentation Samples Per Image During Training
Efficiently Decreases Test Error

Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error

27 May 2021

Samuel L. Smith

Papers citing "Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error"

10 / 10 papers shown

Title
Poly-View Contrastive Learning Amitis Shidani Devon Hjelm Jason Ramapuram Russ Webb Eeshan Gunesh Dhekane Dan Busbridge VLM SSL 34 4 0 08 Mar 2024
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization Jonas Geiping Micah Goldblum Gowthami Somepalli Ravid Shwartz-Ziv Tom Goldstein A. Wilson 26 35 0 12 Oct 2022
Extreme Masking for Learning Instance and Distributed Visual Representations Zhirong Wu Zihang Lai Xiao Sun Stephen Lin 32 22 0 09 Jun 2022
Deep AutoAugment Yu Zheng Z. Zhang Shen Yan Mi Zhang ViT 21 26 0 11 Mar 2022
Regularising for invariance to data augmentation improves supervised learning Aleksander Botev Matthias Bauer Soham De 30 14 0 07 Mar 2022
Using Soft Labels to Model Uncertainty in Medical Image Segmentation Joao Lourencco Silva Arlindo L. Oliveira UQCV 16 19 0 26 Sep 2021
Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation Joao Lourencco Silva M. Menezes T. Rodrigues B. Silva F. Pinto Arlindo L. Oliveira MedIm 31 17 0 21 Jun 2021
Data augmentation in Bayesian neural networks and the cold posterior effect Seth Nabarro Stoil Ganev Adrià Garriga-Alonso Vincent Fortuin Mark van der Wilk Laurence Aitchison BDL 21 37 0 10 Jun 2021
High-Performance Large-Scale Image Recognition Without Normalization Andrew Brock Soham De Samuel L. Smith Karen Simonyan VLM 223 512 0 11 Feb 2021
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 281 2,889 0 15 Sep 2016