Search Results for author:
Found 13 papers, 6 papers with code
Multi-resolution Rescored ByteTrack for Video Object Detection on Ultra-low-power Embedded Systems
This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors.
On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systems
Keyword spotting accuracy degrades when neural networks are exposed to noisy environments.
On-device Self-supervised Learning of Visual Perception Tasks aboard Hardware-limited Nano-quadrotors
Sub-\SI{50}{\gram} nano-drones are gaining momentum in both academia and industry.
Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems
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.
Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers
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.
Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization
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.
Towards On-device Domain Adaptation for Noise-Robust Keyword Spotting
The accuracy of a keyword spotting model deployed on embedded devices often degrades when the system is exposed to real environments with significant noise.
A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
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.
Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers
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.
Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles
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.
PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors
We present PULP-NN, an optimized computing library for a parallel ultra-low-power tightly coupled cluster of RISC-V processors.
Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers
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.
Design Automation for Binarized Neural Networks: A Quantum Leap Opportunity?
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).
