A Survey on GAN-Based Data Augmentation for Hand Pose Estimation Problem

Abstract

Deep learning solutions for hand pose estimation are now very reliant on comprehensive datasets covering diverse camera perspectives, lighting conditions, shapes, and pose variations. While acquiring such datasets is a challenging task, several studies circumvent this problem by exploiting synthetic data, but this does not guarantee that they will work well in real situations mainly due to the gap between the distribution of synthetic and real data. One recent popular solution to the domain shift problem is learning the mapping function between different domains through generative adversarial networks. In this study, we present a comprehensive study on effective hand pose estimation approaches, which are comprised of the leveraged generative adversarial network (GAN), providing a comprehensive training dataset with different modalities. Benefiting from GAN, these algorithms can augment data to a variety of hand shapes and poses where data manipulation is intuitively controlled and greatly realistic. Next, we present related hand pose datasets and performance comparison of some of these methods for the hand pose estimation problem. The quantitative and qualitative results indicate that the state-of-the-art hand pose estimators can be greatly improved with the aid of the training data generated by these GAN-based data augmentation methods. These methods are able to beat the baseline approaches with better visual quality and higher values in most of the metrics (PCK and ME) on both the STB and NYU datasets. Finally, in conclusion, the limitation of the current methods and future directions are discussed.

Fast and Efficient Lung Abnormality Identification With Explainable AI: A Comprehensive Framework for Chest CT Scan and X-Ray Images

“…The system's training process is further enhanced by artificial data generated using a generative model which adds variety and enriches the dataset. As a result, CNN models have increased generalization capabilities, reducing overfitting problems [35]. DCGAN, an improved augmentation strategy that addresses the constraints of traditional data augmentation approaches, may deceive the generator into learning the distributions of the augmented data, which may diverge from the distribution of the source data [36].…”

A Sustainable Approach to Asthma Diagnosis: Classification with Data Augmentation, Feature Selection, and Boosting Algorithm

“…In the data on asthma symptoms, there is frequently an imbalance problem. Recently, generative adversarial networks (GANs) have been shown to provide new data augmentation solutions for the imbalance problem [10,11]. Moreover, there are numerous features for data on asthma.…”

A Hybrid Image Augmentation Technique for User- and Environment-Independent Hand Gesture Recognition Based on Deep Learning

“…Hand gestures now find applications in many real-world scenarios, each characterized by unique environmental conditions, including varying background colors, lighting conditions, and hand gesture positions [40]. These challenges are compounded by limitations in available datasets for real-world HGR, which often lack the variety and diversity essential for training robust models [42]. The scarcity of comprehensive and diverse real-world datasets hinders the development of accurate and adaptable hand gesture recognition systems.…”