Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Antonio Cipolletta"'
Publikováno v:
Il Foro Italiano, 1914 Jan 01. 39, 1301/1302-1307/1308.
Externí odkaz:
https://www.jstor.org/stable/23115421
Autor:
Valentino Peluso, Fabio Tosi, Stefano Mattoccia, Antonio Cipolletta, Andrea Calimera, Filippo Aleotti, Matteo Poggi
Publikováno v:
IEEE Internet of Things Journal. 9:25-36
The recent advancements in deep learning have demonstrated that inferring high-quality depth maps from a single image has become feasible and accurate, thanks to convolutional neural networks (CNNs), but how to process such compute- and memory-intens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::98ae051e5ec3633e3fcda51d4c7d8716
https://doi.org/10.1109/jiot.2021.3080827
https://doi.org/10.1109/jiot.2021.3080827
Most of today's computer vision pipelines are built around deep neural networks, where convolution operations require most of the generally high compute effort. The Winograd convolution algorithm computes convolutions with fewer MACs compared to the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d9cefb03e24cd921a32774bada908fd
http://arxiv.org/abs/2209.12982
http://arxiv.org/abs/2209.12982
This work introduces a new training and compression pipeline to build Nested Sparse ConvNets, a class of dynamic Convolutional Neural Networks (ConvNets) suited for inference tasks deployed on resource-constrained devices at the edge of the Internet-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16487ac678f6419eaff4e8ffb22a9bed
http://arxiv.org/abs/2203.03324
http://arxiv.org/abs/2203.03324
Autor:
Fabio Tosi, Matteo Poggi, Valentino Peluso, Antonio Cipolletta, Filippo Aleotti, Stefano Mattoccia, Andrea Calimera
Depth estimation is crucial in several computer vision applications, and a recent trend in this field aims at inferring such a cue from a single camera. Unfortunately, despite the compelling results achieved, state-of-the-art monocular depth estimati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef0b09223bf4fb6df76a5d9f01865c57
http://hdl.handle.net/11583/2903754
http://hdl.handle.net/11583/2903754
Autor:
Andrea Calimera, Antonio Cipolletta
Publikováno v:
DAC
The memory space taken to host and process large tensor graphs is a limiting factor for embedded ConvNets. Even though many data-driven compression pipelines have proven their efficacy, this work shows there is still room for optimization at the inte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33665aa3f27ad261e78979a1372ca1c4
http://hdl.handle.net/11583/2961251
http://hdl.handle.net/11583/2961251
Autor:
Andrea Calimera, Antonio Cipolletta
Publikováno v:
DATE
The volume reduction of the activation maps produced by the hidden layers of a Deep Neural Network (DNN) is a critical aspect in modern applications as it affects the on-chip memory utilization, the most limited and costly hardware resource. Despite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3fc86a7911d7578354538ce7e301575
http://hdl.handle.net/11583/2921765
http://hdl.handle.net/11583/2921765
Autor:
Valentino Peluso, Matteo Poggi, Filippo Aleotti, Stefano Mattoccia, Antonio Cipolletta, Andrea Calimera, Fabio Tosi
Publikováno v:
CVPR Workshops
Depth estimation is crucial in several computer vision applications, and a recent trend aims at inferring such a cue from a single camera through computationally demanding CNNs — precluding their practical deployment in several application contexts
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c9da9a1ed3d8358a12ae313c1d69ce7
https://hdl.handle.net/11585/771841
https://hdl.handle.net/11585/771841
Publikováno v:
SNAMS
The portability of Convolutional Neural Networks (ConvNets) on the mobile edge of the Internet has proven extremely challenging. Embedded CPUs commonly adopted on portable devices were designed and optimized for different kinds of applications, hence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6eb5b96f6ad270ac739b06408126e5c7
https://doi.org/10.1109/snams.2019.8931889
https://doi.org/10.1109/snams.2019.8931889
Autor:
Matteo Poggi, Fabio Tosi, Stefano Mattoccia, Valentino Peluso, Antonio Cipolletta, Andrea Calimera
Publikováno v:
DATE
This work deals with the implementation of energy-efficient monocular depth estimation using a low-cost CPU for low-power embedded systems. It first describes the PyD-Net depth estimation network, which consists of a lightweight CNN able to approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04556bac469dde0c459a9061d70438ac
https://doi.org/10.23919/date.2019.8714893
https://doi.org/10.23919/date.2019.8714893