StereoSpike: Depth Learning With a Spiking Neural Network - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Access Année : 2022

StereoSpike: Depth Learning With a Spiking Neural Network

Résumé

Depth estimation is an important computer vision task, useful in particular for navigation in autonomous vehicles, or for object manipulation in robotics. Here, we propose to solve it using StereoSpike, an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Network (SNN) with a modified U-Net-like encoder-decoder architecture. More specifically, we used the Multi Vehicle Stereo Event Camera Dataset (MVSEC). It provides a depth ground-truth, which was used to train StereoSpike in a supervised manner, using surrogate gradient descent. We propose a novel readout paradigm to obtain a dense analog prediction-the depth of each pixel-from the spikes of the decoder. We demonstrate that this architecture generalizes very well, even better than its non-spiking counterparts, leading to near stateof-the-art test accuracy. To the best of our knowledge, it is the first time that such a large-scale regression problem is solved by a fully spiking neural network. Finally, we show that very low firing rates (< 5%) can be obtained via regularization, with a minimal cost in accuracy. This means that StereoSpike could be efficiently implemented on neuromorphic chips, opening the door for low power and real time embedded systems. INDEX TERMS Computer vision, bio-inspired learning, deep neural architectures, neuromorphic computing, spiking neural networks, stereo depth regression.
Fichier principal
Vignette du fichier
Rancon et al. - 2022 - StereoSpike Depth Learning With a Spiking Neural Network(2).pdf (1.68 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03906970 , version 1 (19-12-2022)

Identifiants

Citer

Ulysse Rancon, Javier Cuadrado-Anibarro, Benoit R Cottereau, Timothee Masquelier. StereoSpike: Depth Learning With a Spiking Neural Network. IEEE Access, 2022, 10, pp.127428-127439. ⟨10.1109/ACCESS.2022.3226484⟩. ⟨hal-03906970⟩
89 Consultations
94 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More