Data Augmentation Using GANs
By Fabio Tanaka, Claus de Castro Aranha. 2019
234 citations recorded by the source corpus.
In this paper we propose the use of Generative Adversarial Networks (GAN) to generate artificial training data for machine learning tasks. The generation of artificial training data can be extremely useful in situations such as imbalanced data sets, performing a role similar to SMOTE or ADASYN. It is also useful when the data contains sensitive information, and it is desirable to avoid using the original data set as much as possible (example: medical data). We test our proposal on benchmark data sets using different network architectures, and show that a Decision Tree (DT) classifier trained using the training data generated by the GAN reached the same, (and surprisingly sometimes better), accuracy and recall than a DT trained on the original data set.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Antonio Torralba
- Iryna Gurevych
- Jun-Yan Zhu
- Alexei A. Efros
- Richard Zhang
- Mohit Bansal
- Eli Shechtman
- Trevor Darrell
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Eli Shechtman
- Alexei A. Efros
- Antonio Torralba
- Ming-Hsuan Yang
- Jun-Yan Zhu
- Trevor Darrell
- Dacheng Tao
In Generative Models
- Eli Shechtman
- Richard Zhang
- Jun-Yan Zhu
- Alexei A. Efros
- Daniel Cohen-Or
- Antonio Torralba
- Yotam Nitzan
- Rinon Gal
Citations in the corpus
- Do Not Have Enough Data? Deep Learning to the Rescue! (2019, methodology): “The approaches include using variational autoencoding (VAE) (Kingma and Welling 2014), round-trip translation (Yu et al. 2018), paraphrasing (Kumar et al. 2019), and methods based on generative adversarial networks (Tanaka and Aranha 2019).”
- Large image datasets: A pyrrhic win for computer vision? (2020, methodology): “Approaches include using hand-drawn sketch images (ImageNet-Sketch [82]), using GAN generated images [26] and techniques such as Dataset distillation [83],where a dataset or a subset of a dataset is distilled down to a few representative synthetic samples.”
- GAN-Supervised Dense Visual Alignment (2021, methodology): “Prior work has explored the use of GANs [27, 65] in vision tasks such as classification [10,12,54,71,81], segmentation [55,76,79,87] and representation learning [7,20,21,23,35].”
- LARGE: Latent-Based Regression through GAN Semantics (2021, background): “While this approach appears promising on paper [4,32,48,61], this simple idea has enjoyed limited success [10,45].”
- A Comprehensive Survey of Image Augmentation Techniques for Deep Learning (2022, background): “Likewise, we consider many types of image augmentation algorithms, including generative adversarial networks [9] and image mixing [10].”
- Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks (2020, methodology): “Other approaches generate synthetic data by using generative adversarial networks (Tanaka and Aranha, 2019), by using a language model to replace certain words (Wu et al., 2019) or to generate complete sentences (AnabyTavor et al., 2019).”