Bringing Balance to Hand Shape Classification: Mitigating Data Imbalance Through Generative Models

TL;DR

This paper enhances sign language handshape classification by using GAN-based data augmentation to address dataset imbalance, leading to improved accuracy and generalization across datasets.

Contribution

It introduces a novel data augmentation approach using ReACGAN and SPADE GANs to improve handshape classification accuracy on unbalanced datasets.

Findings

Achieved a 5% accuracy improvement on the RWTH dataset.

Demonstrated cross-dataset generalization with pose-based generation.

Outperformed previous methods in handling data imbalance.

Abstract

Most sign language handshape datasets are severely limited and unbalanced, posing significant challenges to effective model training. In this paper, we explore the effectiveness of augmenting the training data of a handshape classifier by generating synthetic data. We use an EfficientNet classifier trained on the RWTH German sign language handshape dataset, which is small and heavily unbalanced, applying different strategies to combine generated and real images. We compare two Generative Adversarial Networks (GAN) architectures for data generation: ReACGAN, which uses label information to condition the data generation process through an auxiliary classifier, and SPADE, which utilizes spatially-adaptive normalization to condition the generation on pose information. ReACGAN allows for the generation of realistic images that align with specific handshape labels, while SPADE focuses on generating images with accurate spatial handshape configurations. Our proposed techniques improve the current state-of-the-art accuracy on the RWTH dataset by 5%, addressing the limitations of small and unbalanced datasets. Additionally, our method demonstrates the capability to generalize across different sign language datasets by leveraging pose-based generation trained on the extensive HaGRID dataset. We achieve comparable performance to single-source trained classifiers without the need for retraining the generator.