The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition
This addresses data scarcity in spatiotemporal human motion recognition, offering a low-cost solution for small-scale datasets, though it is incremental as it builds on existing GAN-based augmentation approaches.
The paper tackles the problem of limited training data in skeleton-based hand gesture and human action recognition by proposing an automatic data augmentation model called the Imaginative GAN, which generates synthetic data to improve classification accuracy for both conventional and state-of-the-art methods.
Deep learning approaches deliver state-of-the-art performance in recognition of spatiotemporal human motion data. However, one of the main challenges in these recognition tasks is limited available training data. Insufficient training data results in over-fitting and data augmentation is one approach to address this challenge. Existing data augmentation strategies based on scaling, shifting and interpolating offer limited generalizability and typically require detailed inspection of the dataset as well as hundreds of GPU hours for hyperparameter optimization. In this paper, we present a novel automatic data augmentation model, the Imaginative Generative Adversarial Network (GAN), that approximates the distribution of the input data and samples new data from this distribution. It is automatic in that it requires no data inspection and little hyperparameter tuning and therefore it is a low-cost and low-effort approach to generate synthetic data. We demonstrate our approach on small-scale skeleton-based datasets with a comprehensive experimental analysis. Our results show that the augmentation strategy is fast to train and can improve classification accuracy for both conventional neural networks and state-of-the-art methods.