A robust event-driven approach to always-on object recognition - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

A robust event-driven approach to always-on object recognition

Antoine Grimaldi
Victor Boutin
Sio-Hoi Ieng
Ryad Benosman

Résumé

We propose a neuromimetic architecture that can perform always-on pattern recognition. To achieve this, we have extended an existing event-based algorithm (Lagorce et al., 2017), which introduced novel spatio-temporal features as a Hierarchy Of Time-Surfaces (HOTS). Built from asynchronous events captured by a neuromorphic camera, these time surfaces allow to encode the local dynamics of a visual scene and to create an efficient event-based pattern recognition architecture. Inspired by neuroscience, we have extended this method to improve its performance. First, we add a homeostatic gain control on the activity of neurons to improve the learning of spatio-temporal patterns (Grimaldi et al., 2021). We also provide a new mathematical formalism that allows an analogy to be drawn between the HOTS algorithm and Spiking Neural Networks (SNN). Following this analogy, we transform the offline pattern categorization method into an online and event-driven layer. This classifier uses the spiking output of the network to define new time surfaces and we then perform the online classification with a neuromimetic implementation of a multinomial logistic regression. These improvements not only consistently increase the performance of the network, but also bring this event-driven pattern recognition algorithm fully online. The results have been validated on different datasets: Poker-DVS (Serrano-Gotarredona and Linares-Barranco, 2015), N-MNIST (Orchard et al., 2015a) and DVS Gesture (Amir et al., 2017). This demonstrates the efficiency of this bio-realistic SNN for ultra-fast object categorization through an event-by-event decision making process.
Fichier principal
Vignette du fichier
grimaldi-24.pdf (1.86 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04694717 , version 1 (11-09-2024)

Licence

Identifiants

Citer

Antoine Grimaldi, Victor Boutin, Sio-Hoi Ieng, Ryad Benosman, Laurent U Perrinet. A robust event-driven approach to always-on object recognition. 2024. ⟨hal-04694717⟩
43 Consultations
14 Téléchargements

Altmetric

Partager

More