Advanced Random Mix Augmentation: Data Augmentation Method for Improving Performance of Image Classification in Deep Learning Using Unduplicated Image Processing Combinations

被引：0
作者：
Im J.
Louhi Kasahara J.Y.
Maruyama H.
Asama H.
Yamashita A.
机构：
来源：
Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering | 2023年 / 89卷 / 01期
关键词：
data augmentation; deep learning; image classification; image processing;
D O I：
10.2493/jjspe.89.105
中图分类号：
学科分类号：
摘要：
Data augmentation is a commonly used method for improving deep learning models in image classification. By adding slightly modified images that do not change the label of the original image to the training data set, the trained model becomes more robust against diverse characteristics of the input image. In this study, we propose a new data augmentation method by improving a previously-known random augmentation method. Our method consists of three steps; 1) determine the set of image modification operators and the number of augmented images, 2) determine the sequence of the image modification operators so that no duplicated sequences are generated, and 3) apply the sequence to augment images. The variety of augmentation is further increased by randomly determining the level (intensity) and the weight of combining the sequences, We applied our method on the C1FAR dataset and show that our method outperforms existing methods. © 2023 Japan Society for Precision Engineering. All rights reserved.
引用
收藏
页码：105 / 112
页数：7
相关论文
共 25 条
[1]  
Vapnik V. N., ya A., Chervonenkis: On the Uniform Convergence: of Relative Frequencies of Events to their Probabilistic, Theory of Probability and its Applications, (1971)
[2]  
Chapelle O., Weston J., Bottou L., Vapnik V., Vicinal Risk Minimization, Proceedings of the 13th International Conference on Neural Information Processing Systems, (2000)
[3]  
Hendrycks D., Mu N., Cubuk E. D., 2oph B., Gilmer J., Lakshminarayanan B., Augmix
[4]  
A Simple Data Processing Method to improve Robustness and Uncertainty, Proceedings of the International Conference on learning Representations, (2020)
[5]  
Cubuk E. D., Zoph B., Mane D., Vasudevan V., AutoAugment: Learning Augmentation Policies from Data, (2018)
[6]  
Jadcrbcrg M., Dalibard V., Osindcro S., Czamccki W. M, Donahue J., Razavi A., Vinyals O., Green T., Dunning I., Simonyan K., Fernando C., Kavukcuoglu K., Population Based Training of Neural Networks, (2017)
[7]  
Ho D., Liang E., Chen X., Stoica I., Abbeel P., Population Based Aumentation: Efficient Learning of augmentation Policy Schedules, International Conference on Machine Learing, (2019)
[8]  
Bergslra J., Bardenet R., Bengio Y., Kegl B., Algorithms for Hyper-parameter Optimization, Advances in Neural Information Processing Systems, (2011)
[9]  
Lim S., Kim I., Kim T., Kim C., Kim S., Past Auto Augment, (2019)
[10]  
Goodfellow I., Pouget-Abadic J., Mirza M., Xu B., Warde-Farley D., Ozair S., Bengio Y, Generative Adversarial Nets, Advances in Neural Information Processing Systems, 27, (2014)
123