1 code implementation • 17 Apr 2024 • Luca Bompani, Manuele Rusci, Daniele Palossi, Francesco Conti, Luca Benini
This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors.
no code implementations • 12 Mar 2024 • Cristian Cioflan, Lukas Cavigelli, Manuele Rusci, Miguel de Prado, Luca Benini
Keyword spotting accuracy degrades when neural networks are exposed to noisy environments.
no code implementations • 6 Mar 2024 • Elia Cereda, Manuele Rusci, Alessandro Giusti, Daniele Palossi
Sub-\SI{50}{\gram} nano-drones are gaining momentum in both academia and industry.
1 code implementation • 3 Jun 2023 • Manuele Rusci, Tinne Tuytelaars
A personalized KeyWord Spotting (KWS) pipeline typically requires the training of a Deep Learning model on a large set of user-defined speech utterances, preventing fast customization directly applied on-device.
1 code implementation • 30 May 2023 • Davide Nadalini, Manuele Rusci, Luca Benini, Francesco Conti
Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications.
no code implementations • 14 Oct 2022 • Manuele Rusci, Marco Fariselli, Martin Croome, Francesco Paci, Eric Flamand
Differently from a uniform 8-bit quantization that degrades the PESQ score by 0. 3 on average, the Mixed-Precision PTQ scheme leads to a low-degradation of only 0. 06, while achieving a 1. 4-1. 7x memory saving.
1 code implementation • IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) 2022 • Cristian Cioflan, Lukas Cavigelli, Manuele Rusci, Miguel de Prado, Luca Benini
The accuracy of a keyword spotting model deployed on embedded devices often degrades when the system is exposed to real environments with significant noise.
no code implementations • 20 Oct 2021 • Leonardo Ravaglia, Manuele Rusci, Davide Nadalini, Alessandro Capotondi, Francesco Conti, Luca Benini
In this work, we introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power (PULP) processor.
no code implementations • 12 Aug 2020 • Manuele Rusci, Marco Fariselli, Alessandro Capotondi, Luca Benini
The severe on-chip memory limitations are currently preventing the deployment of the most accurate Deep Neural Network (DNN) models on tiny MicroController Units (MCUs), even if leveraging an effective 8-bit quantization scheme.
no code implementations • 1 Jul 2020 • Miguel de Prado, Manuele Rusci, Romain Donze, Alessandro Capotondi, Serge Monnerat, Luca Benini and, Nuria Pazos
We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle, which learn in the target environment by imitating a computer vision algorithm, i. e., the expert.
1 code implementation • 29 Aug 2019 • Angelo Garofalo, Manuele Rusci, Francesco Conti, Davide Rossi, Luca Benini
We present PULP-NN, an optimized computing library for a parallel ultra-low-power tightly coupled cluster of RISC-V processors.
2 code implementations • 30 May 2019 • Manuele Rusci, Alessandro Capotondi, Luca Benini
To fit the memory and computational limitations of resource-constrained edge-devices, we exploit mixed low-bitwidth compression, featuring 8, 4 or 2-bit uniform quantization, and we model the inference graph with integer-only operations.
no code implementations • 21 Nov 2017 • Manuele Rusci, Lukas Cavigelli, Luca Benini
Design automation in general, and in particular logic synthesis, can play a key role in enabling the design of application-specific Binarized Neural Networks (BNN).