Timezone: »
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.
Author Information
Sungbin Lim (Korea University)
Ildoo Kim (Kakao Brain)
Taesup Kim (Mila, Université de Montréal / Kakao Brain)
Chiheon Kim (Kakao Brain)
Sungwoong Kim (Kakao Brain)
More from the Same Authors
-
2023 Poster: Locality-Aware Generalizable Implicit Neural Representation »
Doyup Lee · Chiheon Kim · Minsu Cho · WOOK SHIN HAN -
2023 Poster: Score-based Generative Modeling through Stochastic Evolution Equations »
Sungbin Lim · Eunbi Yoon · Taehyun Byun · Taewon Kang · Seungwoo Kim · Kyungjae Lee · Sungjoon Choi -
2023 Poster: Score-based Generative Models with Lévy Processes »
Eunbi Yoon · Keehun Park · Sungwoong Kim · Sungbin Lim -
2022 Poster: Locally Hierarchical Auto-Regressive Modeling for Image Generation »
Tackgeun You · Saehoon Kim · Chiheon Kim · Doyup Lee · Bohyung Han -
2022 Poster: Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer »
Doyup Lee · Chiheon Kim · Saehoon Kim · Minsu Cho · WOOK SHIN HAN -
2022 Poster: LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward »
Daejin Jo · Sungwoong Kim · Daniel Nam · Taehwan Kwon · Seungeun Rho · Jongmin Kim · Donghoon Lee -
2021 Poster: Neural Bootstrapper »
Minsuk Shin · Hyungjoo Cho · Hyun-seok Min · Sungbin Lim -
2020 Poster: Learning Loss for Test-Time Augmentation »
Ildoo Kim · Younghoon Kim · Sungwoong Kim -
2020 Poster: Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards »
Kyungjae Lee · Hongjun Yang · Sungbin Lim · Songhwai Oh -
2019 : The AutoDL Challenge »
Sébastien Treguer · Ildoo Kim · Ruirui Guo · Zhipeng Luo · Minghui Zhao · Yazhou Li · Xiawei Guo · Wenpeng Zhang · Noriaki Ota -
2019 Poster: Variational Temporal Abstraction »
Taesup Kim · Sungjin Ahn · Yoshua Bengio -
2019 Poster: Mining GOLD Samples for Conditional GANs »
Sangwoo Mo · Chiheon Kim · Sungwoong Kim · Minsu Cho · Jinwoo Shin -
2018 Poster: Bayesian Model-Agnostic Meta-Learning »
Jaesik Yoon · Taesup Kim · Ousmane Dia · Sungwoong Kim · Yoshua Bengio · Sungjin Ahn -
2018 Spotlight: Bayesian Model-Agnostic Meta-Learning »
Jaesik Yoon · Taesup Kim · Ousmane Dia · Sungwoong Kim · Yoshua Bengio · Sungjin Ahn