REVIEW 5 cited by
HexaConv
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
HexaConv
read the original abstract
The effectiveness of Convolutional Neural Networks stems in large part from their ability to exploit the translation invariance that is inherent in many learning problems. Recently, it was shown that CNNs can exploit other invariances, such as rotation invariance, by using group convolutions instead of planar convolutions. However, for reasons of performance and ease of implementation, it has been necessary to limit the group convolution to transformations that can be applied to the filters without interpolation. Thus, for images with square pixels, only integer translations, rotations by multiples of 90 degrees, and reflections are admissible. Whereas the square tiling provides a 4-fold rotational symmetry, a hexagonal tiling of the plane has a 6-fold rotational symmetry. In this paper we show how one can efficiently implement planar convolution and group convolution over hexagonal lattices, by re-using existing highly optimized convolution routines. 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. Furthermore, we find that the increased degree of symmetry of the hexagonal grid increases the effectiveness of group convolutions, by allowing for more parameter sharing. We show that our method significantly outperforms conventional CNNs on the AID aerial scene classification dataset, even outperforming ImageNet pre-trained models.
Forward citations
Cited by 5 Pith papers
-
Rotation Equivariant Mamba for Vision Tasks
EQ-VMamba adds rotation-equivariant cross-scan and group Mamba blocks to enforce end-to-end rotation equivariance, yielding better rotation robustness, competitive accuracy, and roughly 50% fewer parameters than non-e...
-
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
A unified family of vision transformers equivariant to arbitrary discrete subgroups of O(2), with embedding and expressivity theorems, a D6 construction using hexagonal patches, and experiments on aerial images in low...
-
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
Constructs G-equivariant ViTs for arbitrary discrete G ≤ O(2), proves H ≤ G implies G-models embed into H-models and single-head equivariant attention realizes all ordinary G-equivariant maps, introduces D6 hexagonal ...
-
Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors
Rotation-equivariant convolutions and adaptive TL-Conv layers are added to I2I networks to preserve rotation symmetry and improve translation quality across domains.
-
What exactly did the Transformer learn from our physics data?
Transformers trained on cosmic ray simulations learn physically plausible features in positional encodings for symmetric air showers and in attention mechanisms for galaxy-origin particles.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.