A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

Abstract

Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms have been proposed as effective and efficient strategies. Understanding current algorithms is essential to find suitable methods or develop novel techniques for given tasks. In this paper, we perform a comprehensive survey on image augmentation for deep learning with a novel informative taxonomy. To get the basic idea why we need image augmentation, we introduce the challenges in computer vision tasks and vicinity distribution. Then, the algorithms are split into three categories; model-free, model-based, and optimizing policy-based. The model-free category employs image processing methods while the model-based method leverages trainable image generation models. In contrast, the optimizing policy-based approach aims to find the optimal operations or their combinations. Furthermore, we discuss the current trend of common applications with two more active topics, leveraging different ways to understand image augmentation, such as group and kernel theory, and deploying image augmentation for unsupervised learning. Based on the analysis, we believe that our survey gives a better understanding helpful to choose suitable methods or design novel algorithms for practical applications.

Revision

References in corpus (9)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Conditional Generative Adversarial Nets
• Bootstrap your own latent: A new approach to self-supervised Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• A Learned Representation For Artistic Style
• A Bayesian Data Augmentation Approach for Learning Deep Models
• Adversarial AutoAugment
• Deep Feature Augmentation for Occluded Image Classification
• Data Augmentation with norm-VAE for Unsupervised Domain Adaptation

Cited by in corpus (12)

• Self-Training: A Survey
• Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learning
• Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
• Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods
• TEGLIE: Transformer encoders as strong gravitational lens finders in KiDS
• Local and Global Context-and-Object-part-Aware Superpixel-based Data Augmentation for Deep Visual Recognition
• Evaluating the Efficacy of Cut-and-Paste Data Augmentation in Semantic Segmentation for Satellite Imagery
• CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
• Tabular Image: a method to convert tabular data to images for convolutional neural networks
• Deep Learning Methods for Detecting Thermal Runaway Events in Battery Production Lines
• A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects
• OA-CutMix: Correcting the Label Bias of CutMix