A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
HexaConv
[article]
2018
arXiv
pre-print
Preserved Fulltext
We find that, due to the reduced anisotropy of hexagonal filters, planar HexaConv provides better accuracy than planar convolution with square filters, given a fixed parameter budget. ...
CONCLUSION We have introduced G-HexaConv, an extension of group convolutions for hexagonal pixelations. Hexagonal grids allow 6-fold rotations without the need for interpolation. ...
Source code of G-HexaConvs is available on Github: https://github.com/ehoogeboom/hexaconv. ...
arXiv:1803.02108v1
fatcat:eyb4bblayjeyjporwhoidcgt4q
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In addition, Hoogeboom et al. (2018) proposed HexaConv and showed how one can implement planar convolutions and group convolutions over hexagonal lattices, instead of square ones. ...
Using comparable numbers of parameters, our methods perform significantly better than HexaConv (5.38% vs. 8.64% on C10). ...
Following HexaConv, we use our PDO-eConvs to establish models that are equivariant to group p6 (p6m), where n = 4 and k i = 6, 13, 26 (k i = 6, 9, 18). ...
arXiv:2007.10408v2
fatcat:idm5xfehgza3few352p4ul7uoq
Invariant Tensor Feature Coding
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To obtain the local feature that D6 acts orthogonally, we pretrained the CNN with hexaconv [13] . ...
Hexaconv models the input images in the hexagonal axis and applies D6 group-equivariant convolutional layers to construct the CNN. ...
arXiv:1906.01857v2
fatcat:oubgq3jwivawvhbfwgbtuh2f2y
Indexed Operations for Non-rectangular Lattices Applied to Convolutional Neural Networks
2019
Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
For this experiment and the one on the AID dataset (see Sec. 5 .3), we compare our results with the two baseline networks of HexaConv paper (Hoogeboom et al., 2018) . ...
doi:10.5220/0007364303620371
dblp:conf/visapp/JacquemontAVSBL19
fatcat:dlht6xpqmradbkmynpkelzr6f4
Natural Graph Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2007.08349v1 fatcat:qf57kwxc4rb7rjl4vbb4fsq74y
Hexaconv. arXiv preprint
arXiv:1803.02108, 2018.
Urs Schreiber and Konrad Waldorf. Parallel transport and functors. arXiv preprint arXiv:0705.0452,
2007.
. ...
A Natural Graph Network on these reduced features is exactly equivalent to HexaConv [Hoogeboom et al., 2018]
D Category-theoretical formalization Our goal is to define a general construction for equivariant ...
arXiv:2007.08349v2
fatcat:bble7vlwiza77k7i2jv3tvvcce
Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior
2021
Transactions of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Because the CEREALBAR environment is a grid of hexagons, we use HEXACONV (Hoogeboom et al., 2018) . ...
doi:10.1162/tacl_a_00428
fatcat:b7h6q4qpf5btdggoqu3x6xmlhq
Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
By replacing the commonly used square lattices with hexagonal lattices, HexaConv succeeded in expanding rotation equivariant to π /3 degree rotation (p6m) [7] . ...
Afterwards, HexaConv [7] expanded rotation equivariant to π /3 degree rotations (i.e., p6 and p6m group equivariant) by replacing the commonly used square lattices with hexagonal lattices. ...
arXiv:2107.14519v1
fatcat:uspkp2dlmfeavezvehuibpuoiu
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Gauge Equivariant Icosahedral Convolution Gauge equivariant convolution on the icosahedron is implemented in three steps: G-Padding, kernel expansion, and 2d convolution / HexaConv (Hoogeboom et al., ...
arXiv:1902.04615v3
fatcat:o7rb4j7nhjee7bfiatarn7gnsm
Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Because the CERE-ALBAR environment is a grid of hexagons, we use HEXACONV (Hoogeboom et al., 2018) . ...
arXiv:2108.04812v1
fatcat:cbxm3rwqjrbsplanc3ew43fkvy