Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data - Université de Picardie Jules Verne Accéder directement au contenu
Article Dans Une Revue Journal of Imaging Année : 2021

Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data


Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or lack of data-sharing incentives. Such challenges have attached significance to the application of generative modeling and data augmentation in that domain. In this context, this study explores a machine learning-based approach for generating synthetic eye-tracking data. We explore a novel application of variational autoencoders (VAEs) in this regard. More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths. Overall, our results validate that the VAE model could generate a plausible output from a limited dataset. Finally, it is empirically demonstrated that such approach could be employed as a mechanism for data augmentation to improve the performance in classification tasks.



Dates et versions

hal-03601452 , version 1 (08-03-2022)




Mahmoud Elbattah, Colm Loughnane, Jean-Luc Guérin, Romuald Carette, Federica Cilia, et al.. Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data. Journal of Imaging, 2021, 7 (5), pp.83. ⟨10.3390/jimaging7050083⟩. ⟨hal-03601452⟩
42 Consultations
0 Téléchargements



Gmail Mastodon Facebook X LinkedIn More