An Embedded Continual Learning System for Facial Emotion Recognition - Université Grenoble Alpes Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

An Embedded Continual Learning System for Facial Emotion Recognition


While being a key element of human-human communication, face emotion recognition is an important challenge for human-computer interactions. Feature extraction and classification methods have been developed during the past decades in order to propose increasingly accurate emotion recognition algorithms. Nevertheless, in a changing environment where systems needs to be continually adapted, the issue of catastrophic forgetting becomes a major challenge. Based on the bio-inspired continual learning algorithm Dream Net, we propose an embedded system for face emotion recognition. This system is innovative in its ability to learn incrementally on a NVIDIA Jetson Nano platform without catastrophic forgetting while preserving privacy and being agnostic to data. Live demonstration of this system can be done and users can test it in several modes of operation: emotion recognition or learning of new emotions.
Fichier principal
Vignette du fichier
sub_1451.pdf (282.41 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04421327 , version 1 (05-02-2024)



Olivier Antoni, Marion Mainsant, Christelle Godin, Martial Mermillod, Marina Reyboz. An Embedded Continual Learning System for Facial Emotion Recognition. European Conference, ECML PKDD 2022, Sep 2022, Grenoble, France. pp.10.1007/978-3-031-26422-1_45, ⟨10.1007/978-3-031-26422-1_45⟩. ⟨hal-04421327⟩
128 Consultations
16 Téléchargements



Gmail Mastodon Facebook X LinkedIn More