Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups

Autor: Knigge, D.M., Romero, D.W., Bekkers, E.J.

Publikováno v: Proceedings of Machine Learning Research, 162, 11359-11386

Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular G-CNNs, an

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::622e45638a5a01e30be1d0860e233be2
https://dare.uva.nl/personal/pure/en/publications/exploiting-redundancy-separable-group-convolutional-networks-on-lie-groups(4e31ff45-ad82-42af-a4d8-24f2ef8bbee0).html

Attentive group equivariant convolutional networks

Autor: Romero, D.W., Bekkers, E.J., Tomczak, J.M., Hoogendoorn, M.

Publikováno v: Proceedings of Machine Learning Research, 119, 8188-8199

Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we present attenti

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::827be0c50cf5dc1266874e91af1e969a
https://dare.uva.nl/personal/pure/en/publications/attentive-group-equivariant-convolutional-networks(7302a700-9e70-4389-b8b3-41442d1dcea4).html

Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images

Autor: Bekkers, E.J., Duits, R., Loog, M., Tai, X.C., Bae, E., Chan, T.F., Lysaker, M.

Publikováno v: Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings), 464-477
STARTPAGE=464;ENDPAGE=477;TITLE=Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings)
Lecture Notes in Computer Science ISBN: 9783319146119
EMMCVPR

A new template matching scheme for the detection of objects on the basis of orientations is proposed. The matching scheme is based on correlations in the domain \(\mathbb{R}^2 \rtimes S^1\) of complex valued invertible orientation scores. In invertib

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5ff035acf0ae8470bdb360fe1ece51a
https://doi.org/10.1007/978-3-319-14612-6_34

Tracking of lines in spherical images via sub-Riemannian geodesics in SO(3)

Autor: Mashtakov, A., Duits, R., Sachkov, Y., Bekkers, E.J., Beschastnyi, I.

Publikováno v: Journal of Mathematical Imaging and Vision, 58(2). Springer

In order to detect salient lines in spherical images, we consider the problem of minimizing the functional ∫0lC(γ(s))ξ2+kg2(s)ds for a curve γ on a sphere with fixed boundary points and directions. The total length l is free, s denotes the spher

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::1caae2dab189f7126472fba59f4a298f
https://research.tue.nl/nl/publications/cc131f0d-c8aa-4729-878d-3206089f5570