BROWSE

Related Researcher

Author's Photo

Lim, Sungbin
Learning Intelligent Machine Lab
Research Interests
  • Causal Learning / Machine Reasoning
  • Statistical Learning
  • Uncertainty Estimation
  • Stochastic Optimization
  • Planning / Reinforcement Learning
  • Automated Machine Learning

ITEM VIEW & DOWNLOAD

Fast AutoAugment

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Fast AutoAugment
Author
Lim, SungbinKim, IldooKim, TaesupKim, ChiheonKim, Sungwoong
Issue Date
2019-12-08
Publisher
NeurIPS 2019
Citation
33rd Conference on Neural Information Processing Systems (NeurIPS 2019)
Abstract
Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment \cite{cubuk2018autoaugment} has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks. However, its search method requires thousands of GPU hours even for a relatively small dataset. In this paper, we propose an algorithm called Fast AutoAugment that finds effective augmentation policies via a more efficient search strategy based on density matching. In comparison to AutoAugment, the proposed algorithm speeds up the search time by orders of magnitude while achieves comparable performances on image recognition tasks with various models and datasets including CIFAR-10, CIFAR-100, SVHN, and ImageNet. Our code is open to the public by the official GitHub\footnote{\url{https://github.com/kakaobrain/fast-autoaugment}} of Kakao Brain.
URI
https://scholarworks.unist.ac.kr/handle/201301/32918
Appears in Collections:
SME_Conference Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU