A survey on Image Data Augmentation for Deep Learning

• Published in: Journal of big data Vol. 6; no. 1; pp. 1 - 48
• Main Authors: Shorten, Connor, Khoshgoftaar, Taghi M.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 06.07.2019; Springer Nature B.V; SpringerOpen
• Subjects: Algorithms; Artificial neural networks; Big Data; Communications Engineering; Computational Science and Engineering; Computer Science; Computer vision; Curricula; Data Augmentation; Data management; Data Mining and Knowledge Discovery; Database Management; Datasets; Deep Learning; Domains; GANs; Image analysis; Image data; Image filters; Information Storage and Retrieval; Machine learning; Mathematical Applications in Computer Science; Medical imaging; Networks; Performance enhancement; Survey Paper; Training; Big data; Data Augmentation; Image data; Deep Learning; GANs

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...