Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Tony Lindeberg"'
Autor:
Tony Lindeberg
Publikováno v:
Frontiers in Computational Neuroscience, Vol 17 (2023)
The property of covariance, also referred to as equivariance, means that an image operator is well-behaved under image transformations, in the sense that the result of applying the image operator to a transformed input image gives essentially a simil
Externí odkaz:
https://doaj.org/article/7ae911714ddf47f6adcbf065a6b32698
Autor:
Tony Lindeberg
Publikováno v:
Heliyon, Vol 7, Iss 1, Pp e05897- (2021)
This article gives an overview of a normative theory of visual receptive fields. We describe how idealized functional models of early spatial, spatio-chromatic and spatio-temporal receptive fields can be derived in a principled way, based on a set of
Externí odkaz:
https://doaj.org/article/f702fe695563489b9a30adc8bd3517b3
Autor:
Tony Lindeberg, Anders Friberg
Publikováno v:
PLoS ONE, Vol 10, Iss 3, p e0119032 (2015)
We present a theory by which idealized models of auditory receptive fields can be derived in a principled axiomatic manner, from a set of structural properties to (i) enable invariance of receptive field responses under natural sound transformations
Externí odkaz:
https://doaj.org/article/630acc1e0d314af1902372fbe8621d5c
Autor:
Tony Lindeberg
Publikováno v:
PLoS ONE, Vol 8, Iss 7, p e66990 (2013)
The brain is able to maintain a stable perception although the visual stimuli vary substantially on the retina due to geometric transformations and lighting variations in the environment. This paper presents a theory for achieving basic invariance pr
Externí odkaz:
https://doaj.org/article/705a41d921d04ebaaf5d653b1b3706f5
Autor:
Tony Lindeberg
This article presents an overview of a theory for performing temporal smoothing on temporal signals in such a way that: (i) temporally smoothed signals at coarser temporal scales are guaranteed to constitute simplifications of corresponding temporall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1cfdaec53e335bbd8519fd3b4afab69
http://arxiv.org/abs/2202.09209
http://arxiv.org/abs/2202.09209
Autor:
Atsuto Maki, Danica Kragic, Hedvig Kjellstrom, Hossein Azizpour, Josephine Sullivan, Marten Bjorkman, Patric Jensfelt, Stefan Carlsson, Tony Lindeberg, Yngve Sundblad
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:4488-4489
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a31e3fbd6d4521c59f3067f6bbf73a1
https://doi.org/10.1109/tpami.2022.3183266
https://doi.org/10.1109/tpami.2022.3183266
Autor:
Tony Lindeberg, Ylva Jansson
Publikováno v:
ICPR
The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. Scale invari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08281e858a04efe80f7ecdbf88155bd9
https://doi.org/10.1109/icpr48806.2021.9413276
https://doi.org/10.1109/icpr48806.2021.9413276
Autor:
Tony Lindeberg, Ylva Jansson
The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. Scale invari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::415c55e2d5e7c5452014e5da07e80116
Publikováno v:
ICPR
Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables the use o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2454ddefc69af1e56514afc881bfb494
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-288723
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-288723
Autor:
Tony Lindeberg
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030755485
SSVM
SSVM
This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4736379bed84f62b2953d5a716d497b2
http://arxiv.org/abs/2011.14759
http://arxiv.org/abs/2011.14759