数据增强

数据增强（英语：Data augmentation）是一种统计技术，允许从不完整数据中进行最大似然估计^[1]^[2]。数据增强在贝叶斯推断中有重要应用^[3]，并且在机器学习中广泛使用，通过训练模型使用已有数据的几个略微修改的副本在训练机器学习模型时减少过拟合^[4]。

图像分类中的数据增强

在20世纪90年代中期，当卷积神经网络变得更加复杂时，数据量不足成为一个问题，特别是考虑到需要留出一部分数据用于后续测试。为了解决这个问题，有研究提议使用仿射变换扰动现有数据，以创建带有相同标签的新示例^[5]。随后，2003年引入了所谓的弹性失真（英语：Elastic deformation）^[6]，到了2010年代，这些技术被广泛采用^[7]。数据增强可以提升卷积神经网络的性能，并且作为对抗卷积神经网络分析攻击的一种对策^[8]。

数据增强在图像分类中已成为一种基础工具，用来丰富训练数据集的多样性，以提升模型的泛化能力和性能。几何变换、颜色空间调整和噪声注入等是数据增强在图像分类中的常用工具^[9]。

参见

参考来源

^ Dempster, A.P.; Laird, N.M.; Rubin, D.B. Maximum Likelihood from Incomplete Data Via the EM Algorithm. Journal of the Royal Statistical Society. Series B (Methodological). 1977, 39 (1): 1–22 [2024-08-07]. doi:10.1111/j.2517-6161.1977.tb01600.x. （原始内容存档于2022-10-10）.
^ Rubin, Donald. Comment: The Calculation of Posterior Distributions by Data Augmentation. Journal of the American Statistical Association. 1987, 82 (398) [2024-08-07]. JSTOR 2289460. doi:10.2307/2289460. （原始内容存档于2024-08-07）.
^ Jackman, Simon. Bayesian Analysis for the Social Sciences. John Wiley & Sons. 2009: 236. ISBN 978-0-470-01154-6.
^ Shorten, Connor; Khoshgoftaar, Taghi M. A survey on Image Data Augmentation for Deep Learning. Mathematics and Computers in Simulation (springer). 2019, 6: 60. doi:10.1186/s40537-019-0197-0  .
^ Yann Lecun; et al. Learning algorithms for classification: A comparison on handwritten digit recognition (Conference paper). nyuscholars.nyu.edu (World Scientific). 1995: 261–276 [2023-05-14].
^ Simard, P.Y.; Steinkraus, D.; Platt, J.C. Best practices for convolutional neural networks applied to visual document analysis. Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. 1. 2003: 958–963. ISBN 0-7695-1960-1. S2CID 4659176. doi:10.1109/ICDAR.2003.1227801.
^ Hinton, Geoffrey E.; Srivastava, Nitish; Krizhevsky, Alex; Sutskever, Ilya; Salakhutdinov, Ruslan R. Improving neural networks by preventing co-adaptation of feature detectors. 2012. arXiv:1207.0580  [cs.NE].
^ Cagli, Eleonora; Dumas, Cécile; Prouff, Emmanuel. Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures: Profiling Attacks Without Pre-processing. Fischer, Wieland; Homma, Naofumi (编). Cryptographic Hardware and Embedded Systems – CHES 2017. Lecture Notes in Computer Science 10529. Cham: Springer International Publishing. 2017: 45–68. ISBN 978-3-319-66787-4. S2CID 54088207. doi:10.1007/978-3-319-66787-4_3 （英语）.
^ Shorten, Connor; Khoshgoftaar, Taghi M. A survey on Image Data Augmentation for Deep Learning. Journal of Big Data. 2019-07-06, 6 (1): 60. ISSN 2196-1115. doi:10.1186/s40537-019-0197-0  .

[1] Dempster, A.P.; Laird, N.M.; Rubin, D.B. Maximum Likelihood from Incomplete Data Via the EM Algorithm. Journal of the Royal Statistical Society. Series B (Methodological). 1977, 39 (1): 1–22 [2024-08-07]. doi:10.1111/j.2517-6161.1977.tb01600.x. （原始内容存档于2022-10-10）.

[2] Rubin, Donald. Comment: The Calculation of Posterior Distributions by Data Augmentation. Journal of the American Statistical Association. 1987, 82 (398) [2024-08-07]. JSTOR 2289460. doi:10.2307/2289460. （原始内容存档于2024-08-07）.

[3] Jackman, Simon. Bayesian Analysis for the Social Sciences. John Wiley & Sons. 2009: 236. ISBN 978-0-470-01154-6.

[Big_Data_2019_6:60-4] Shorten, Connor; Khoshgoftaar, Taghi M. A survey on Image Data Augmentation for Deep Learning. Mathematics and Computers in Simulation (springer). 2019, 6: 60. doi:10.1186/s40537-019-0197-0  .

[5] Yann Lecun; et al. Learning algorithms for classification: A comparison on handwritten digit recognition (Conference paper). nyuscholars.nyu.edu (World Scientific). 1995: 261–276 [2023-05-14].

[6] Simard, P.Y.; Steinkraus, D.; Platt, J.C. Best practices for convolutional neural networks applied to visual document analysis. Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. 1. 2003: 958–963. ISBN 0-7695-1960-1. S2CID 4659176. doi:10.1109/ICDAR.2003.1227801.

[7] Hinton, Geoffrey E.; Srivastava, Nitish; Krizhevsky, Alex; Sutskever, Ilya; Salakhutdinov, Ruslan R. Improving neural networks by preventing co-adaptation of feature detectors. 2012. arXiv:1207.0580  [cs.NE].

[8] Cagli, Eleonora; Dumas, Cécile; Prouff, Emmanuel. Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures: Profiling Attacks Without Pre-processing. Fischer, Wieland; Homma, Naofumi (编). Cryptographic Hardware and Embedded Systems – CHES 2017. Lecture Notes in Computer Science 10529. Cham: Springer International Publishing. 2017: 45–68. ISBN 978-3-319-66787-4. S2CID 54088207. doi:10.1007/978-3-319-66787-4_3 （英语）.

[9] Shorten, Connor; Khoshgoftaar, Taghi M. A survey on Image Data Augmentation for Deep Learning. Journal of Big Data. 2019-07-06, 6 (1): 60. ISSN 2196-1115. doi:10.1186/s40537-019-0197-0  .

[1]

[2]

[3]

[4]

[5]

[6]

[7]

[8]

[9]