Adaptive Data Augmentation with Deep Parallel Generative Models

Boli Fang, Miao Jiang, Abhirag Nagpure, Jerry Shen

TL;DR: We propose an adaptive DA strategy based on generative models that improves model performances across machine learning and computer vision tasks.

Abstract: Data augmentation(DA) is a useful technique to enlarge the size of the training set and prevent overfitting for different machine learning tasks when training data is scarce. However, current data augmentation techniques rely heavily on human design and domain knowledge, and existing automated approaches are yet to fully exploit the latent features in the training dataset. In this paper we propose an adaptive DA strategy based on generative models, where the training set adaptively enriches itself with sample images automatically constructed from deep generative models trained in parallel. We demonstrate by experiments that our data augmentation strategy, with little model-specific considerations, can be easily adapted to cross-domain deep learning/machine learning tasks such as image classification and image inpainting, while significantly improving model performance in both tasks.

Code: https://github.com/anonymizedsubmssion/ICLR_2020_anonymized_code