Learning data augmentation policies using augmented random search

2018-11-12 · Mingyang Geng, Kele Xu, Bo Ding, Huaimin Wang, Lei Zhang

Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment searches for the augmentation polices in the discrete search space, which may lead to a sub-optimal solution. In this paper, we employ the Augmented Random Search method (ARS) to improve the performance of AutoAugment. Our key contribution is to change the discrete search space to continuous space, which will improve the searching performance and maintain the diversities between sub-policies. With the proposed method, state-of-the-art accuracies are achieved on CIFAR-10, CIFAR-100, and ImageNet (without additional data). Our code is available at https://github.com/gmy2013/ARS-Aug.

📄 PDF Abstract BibTeX arXiv:1811.04768

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Random Search Random Search replaces the exhaustive enumeration of all combinations by selecting them randomly. This can be simply applied to the discrete setting described above, but also…

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

AutoAugment 설명 없음

Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture

2022-07-21 · Jianwei Zhang, Dong Li, Lituan Wang, Lei Zhang

Automated data augmentation, which aims at engineering augmentation policy automatically, recently draw a growing research interest. Many previous auto-augmentation methods utilized a Density Matching strategy by evaluat…

AutoML Data Augmentation Medical Image Analysis

G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR

2022-10-19 · Gary Wang, Ekin D. Cubuk, Andrew Rosenberg, Shuyang Cheng 외

Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training. However, even as so much of the ASR training process has become automated and more "end-to-end", the …

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation speech-recognition+1

Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning

2023-10-27 · Nicholas E. Corrado, Yuxiao Qu, John U. Balis, Adam Labiosa 외

In offline reinforcement learning (RL), an RL agent learns to solve a task using only a fixed dataset of previously collected data. While offline RL has been successful in learning real-world robot control policies, it t…

Autonomous Driving D4RL Data Augmentation Imitation Learning+4

Augmentation Pathways Network for Visual Recognition

2021-07-26 · Yalong Bai, Mohan Zhou, Wei zhang, BoWen Zhou 외

Data augmentation is practically helpful for visual recognition, especially at the time of data scarcity. However, such success is only limited to quite a few light augmentations (e.g., random crop, flip). Heavy augmenta…

Data Augmentation

Generalization in Reinforcement Learning by Soft Data Augmentation

2020-11-26 · Nicklas Hansen, Xiaolong Wang

Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during tr…