Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Swayambhoo Jain"'
Autor:
Hamed Rezazadegan-Tavakoli, Wojciech Samek, Werner Bailer, Paul Haase, Karsten Muller, Swayambhoo Jain, Francesco Cricri, Miska Hannuksela, Shan Liu, Emre Aksu, Wei Jiang, Shahab Hamidi-Rad, Fabien Racape, Heiner Kirchhoffer, Wei Wang
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:3203-3216
Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea3cf414ea189bf657a4b5643281d50c
https://doi.org/10.1109/tcsvt.2021.3095970
https://doi.org/10.1109/tcsvt.2021.3095970
Autor:
Shahab Hamidi-Rad, Swayambhoo Jain
Publikováno v:
2021 IEEE Global Communications Conference (GLOBECOM).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::002a7af31e11952fc039781aa1fe55eb
https://doi.org/10.1109/globecom46510.2021.9685815
https://doi.org/10.1109/globecom46510.2021.9685815
Autor:
Sriram Ravula, Swayambhoo Jain
Publikováno v:
2021 IEEE Global Communications Conference (GLOBECOM).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b26ed2850e42a94ca14a2603e204af2
https://doi.org/10.1109/globecom46510.2021.9685912
https://doi.org/10.1109/globecom46510.2021.9685912
Despite many modern applications of Deep Neural Networks (DNNs), the large number of parameters in the hidden layers makes them unattractive for deployment on devices with storage capacity constraints. In this paper we propose a Data-Driven Low-rank
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d1a430255e40593f3ee182644596d31
http://arxiv.org/abs/2107.05787
http://arxiv.org/abs/2107.05787
Autor:
Swayambhoo Jain, Vineeth Rakesh
Publikováno v:
CVPR Workshops
Obtaining labeled data for machine learning tasks can be prohibitively expensive. Active learning mitigates this issue by exploring the unlabeled data space and prioritizing the selection of data that can best improve the model performance. A common
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::854e5965e6b9e15cc085f03bea84ffac
https://doi.org/10.1109/cvprw53098.2021.00294
https://doi.org/10.1109/cvprw53098.2021.00294
Publikováno v:
DCC
Deep neural networks (DNNs), despite their performance on a wide variety of tasks, are still out of reach for many applications as they require significant computational resources. In this paper, we present a low-rank based end-to-end deep neural net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::edd7d6bd97f6226badb9b7f0ea7d8f6e
https://doi.org/10.1109/dcc50243.2021.00031
https://doi.org/10.1109/dcc50243.2021.00031
Autor:
Swayambhoo Jain, Sriram Ravula
Publikováno v:
DCC
Many natural signals lie in a union of subspaces, which we can exploit when compressing these signals to maintain a high level of fidelity while significantly reducing the storage size. Standard compression techniques for natural signals such as imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::394aa6d84b34fd8b8f69cc73b73c1c93
https://doi.org/10.1109/dcc50243.2021.00076
https://doi.org/10.1109/dcc50243.2021.00076
Publikováno v:
IEEE Transactions on Biomedical Engineering. 64:2142-2151
The measurement and analysis of Electrodermal Activity (EDA) offers applications in diverse areas ranging from market research, to seizure detection, to human stress analysis. Unfortunately, the analysis of EDA signals is made difficult by the superp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83abe474ca94e32c2a9e9da1dbdc627e
https://doi.org/10.1109/tbme.2016.2632523
https://doi.org/10.1109/tbme.2016.2632523
Publikováno v:
ACSSC
Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the target distribution are easily av
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5504bb539d5ed881177ba59714686e18
https://doi.org/10.1109/ieeeconf44664.2019.9048875
https://doi.org/10.1109/ieeeconf44664.2019.9048875
Publikováno v:
ICASSP
Despite their well-documented learning capabilities in clean environments, deep convolutional neural networks (CNNs) are extremely fragile in adversarial settings, where carefully crafted perturbations created by an attacker can easily disrupt the ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa7a5a9e341283e35fbb2c7439f40bf6
https://doi.org/10.1109/icassp.2019.8683348
https://doi.org/10.1109/icassp.2019.8683348