A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions
Authors:
- 3 December 2020
- book chapter
- Published by Springer Nature
- p. 53-69
Abstract
No abstract availableKeywords
All Related Versions
This publication has 16 references indexed in Scilit:
- AutoAugment: Learning Augmentation Strategies From Data2019
- Exploring the Limits of Weakly Supervised Pretraining2018
- Data augmentation for improving deep learning in image classification problem2018
- Mastering the game of Go without human knowledgeNature, 2017
- Toward Human Parity in Conversational Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- Human-level control through deep reinforcement learningNature, 2015
- Torchvision the machine-vision package of torch2010
- Deep BlueArtificial Intelligence, 2002