A survey on Image Data Augmentation for Deep Learning
A survey on Image Data Augmentation for Deep Learning
复制标题
DOI：
10.1186/s40537-019-0197-0
复制
发表时间：
2019-07-06
影响因子：
8.1
通讯作者：
Khoshgoftaar, Taghi M.
中科院分区：
文献类型：
--
作者：
Shorten, Connor;Khoshgoftaar, Taghi M.
深度卷积神经网络在许多计算机视觉任务中表现得非常好。然而，这些网络严重依赖大数据，以避免过度匹配。过拟合是指当网络学习具有很高方差的函数时的现象，例如对训练数据进行完美建模。不幸的是，许多应用领域无法访问大数据，例如医学图像分析。这项调查的重点是数据增强，这是一种针对数据有限问题的数据空间解决方案。数据增强包括一套增强训练数据集的大小和质量的技术，以便可以使用它们构建更好的深度学习模型。本文讨论的图像增强算法包括几何变换、颜色空间增强、核滤波、混合图像、随机擦除、特征空间增强、对抗性训练、生成性对抗性网络、神经风格转移和元学习。基于GANS的增强方法的应用在这次调查中有很大的覆盖。除了增强技术，本文还将简要讨论数据增强的其他特征，如测试时间增强、分辨率影响、最终数据集大小和课程学习。本调查将介绍现有的数据增强方法、有前景的发展，以及实施数据增强的元级决策。读者将了解数据增强如何提高其模型的性能，并扩展有限的数据集以利用大数据的功能。
Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem of limited data. Data Augmentation encompasses a suite of techniques that enhance the size and quality of training datasets such that better Deep Learning models can be built using them. The image augmentation algorithms discussed in this survey include geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks, neural style transfer, and meta-learning. The application of augmentation methods based on GANs are heavily covered in this survey. In addition to augmentation techniques, this paper will briefly discuss other characteristics of Data Augmentation such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. This survey will present existing methods for Data Augmentation, promising developments, and meta-level decisions for implementing Data Augmentation. Readers will understand how Data Augmentation can improve the performance of their models and expand limited datasets to take advantage of the capabilities of big data.