Deep AutoAugment

2022-03-11 · Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang

While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA). DeepAA progressively builds a multi-layer data augmentation pipeline from scratch by stacking augmentation layers one at a time until reaching convergence. For each augmentation layer, the policy is optimized to maximize the cosine similarity between the gradients of the original and augmented data along the direction with low variance. Our experiments show that even without default augmentations, we can learn an augmentation policy that achieves strong performance with that of previous works. Extensive ablation studies show that the regularized gradient matching is an effective search method for data augmentation policies. Our code is available at: https://github.com/MSU-MLSys-Lab/DeepAA .

📄 PDF Abstract BibTeX arXiv:2203.06172

Code (1)

msu-mlsys-lab/deepaa 공식 구현 pytorch

Tasks

AutoML Data Augmentation Image Classification

Methods 이 논문이 사용한 방법론

RandAugment 설명 없음

Fast AutoAugment Fast AutoAugment is an image data augmentation algorithm that finds effective augmentation policies via a search strategy based on density matching, motivated by Bayesian DA.…

AutoAugment 설명 없음

Fast AutoAugment

2019-05-01 · NeurIPS 2019 12 · Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim 외

Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a d…

Data Augmentation GPU Image Augmentation Image Classification

Circumventing Outliers of AutoAugment with Knowledge Distillation

2020-03-25 · ECCV 2020 8 · Longhui Wei, An Xiao, Lingxi Xie, Xin Chen 외

AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimizatio…

Data Augmentation General Classification image-classification Image Classification+1

Learning data augmentation policies using augmented random search

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

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 lea…

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

Greedy AutoAugment

2019-08-02 · Alireza Naghizadeh, Mohammadsajad Abavisani, Dimitris N. Metaxas

A major problem in data augmentation is to ensure that the generated new samples cover the search space. This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness…

Data Augmentation

Adversarial AutoAugment

2019-12-24 · ICLR 2020 1 · Xin-Yu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong

Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data augmentation has been gradually replaced by automatically learned augmentation pol…

Data Augmentation image-classification Image Classification