An overview of mixing augmentation methods and augmentation strategies

Abstract

Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017-2021.

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
• Fast is better than free: Revisiting adversarial training
• Population Based Training of Neural Networks
• Regularization for Deep Learning: A Taxonomy
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
• SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
• Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
• Adversarial AutoAugment
• Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
• FedMix: Approximation of Mixup under Mean Augmented Federated Learning
• Dataset Augmentation in Feature Space
• Domain Generalization with MixStyle
• DADA: Differentiable Automatic Data Augmentation
• Fair Mixup: Fairness via Interpolation