.is work introduces an ultra-low-power visual sensor node coupling event-based binary acquisition with Binarized Neural Networks (BNNs) to deal with the stringent power requirements of always-on vision systems for IoT applications. By exploiting insensor mixed-signal processing, an ultra-low-power imager generates a sparse visual signal of binary spatial-gradient features. .e sensor output, packed as a stream of events corresponding to the asserted gradient binary values, is transferred to a 4-core processor when the amount of data detected a.er frame di.erence surpasses a given threshold. .en, a BNN trained with binary gradients as input runs on the parallel processor if a meaningful activity is detected in a pre-processing stage. During the BNN computation, the proposed Event-based Binarized Neural Network model achieves a system energy saving of 17.8% with respect to a baseline system including a low-power RGB imager and a Binarized Neural Network, while paying a classi.cation performance drop of only 3% for a real-life 3-classes classi.cation scenario. .e energy reduction increases up to 8x when considering a long-term always-on monitoring scenario, thanks to the event-driven behavior of the processing sub-system.
Titolo: | Always-ON visual node with a hardware-software event-based binarized neural network inference engine | |
Autore/i: | Rusci, Manuele; Rossi, Davide; Flamand, Eric; Gottardi, Massimo; Farella, Elisabetta; Benini, Luca | |
Autore/i Unibo: | ||
Anno: | 2018 | |
Titolo del libro: | 2018 ACM International Conference on Computing Frontiers, CF 2018 - Proceedings | |
Pagina iniziale: | 314 | |
Pagina finale: | 319 | |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1145/3203217.3204463 | |
Abstract: | .is work introduces an ultra-low-power visual sensor node coupling event-based binary acquisition with Binarized Neural Networks (BNNs) to deal with the stringent power requirements of always-on vision systems for IoT applications. By exploiting insensor mixed-signal processing, an ultra-low-power imager generates a sparse visual signal of binary spatial-gradient features. .e sensor output, packed as a stream of events corresponding to the asserted gradient binary values, is transferred to a 4-core processor when the amount of data detected a.er frame di.erence surpasses a given threshold. .en, a BNN trained with binary gradients as input runs on the parallel processor if a meaningful activity is detected in a pre-processing stage. During the BNN computation, the proposed Event-based Binarized Neural Network model achieves a system energy saving of 17.8% with respect to a baseline system including a low-power RGB imager and a Binarized Neural Network, while paying a classi.cation performance drop of only 3% for a real-life 3-classes classi.cation scenario. .e energy reduction increases up to 8x when considering a long-term always-on monitoring scenario, thanks to the event-driven behavior of the processing sub-system. | |
Data stato definitivo: | 4-set-2019 | |
Appare nelle tipologie: | 4.01 Contributo in Atti di convegno |
File in questo prodotto:
File | Descrizione | Tipo | Licenza | |
---|---|---|---|---|
Always-ON Visual node.pdf | Articolo Postprint | Postprint | Licenza per accesso libero gratuito | Open Access Visualizza/Apri |