Pith. sign in

REVIEW

Circular-Symmetric Correlation Layer based on FFT

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

arxiv 2107.12480 v1 pith:XXMWU6RO submitted 2021-07-26 cs.CV cs.LG

classification cs.CVcs.LG
keywords correlationcircular-symmetriclayerplanarsignalsalgorithmanalysisanalyzing
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Despite the vast success of standard planar convolutional neural networks, they are not the most efficient choice for analyzing signals that lie on an arbitrarily curved manifold, such as a cylinder. The problem arises when one performs a planar projection of these signals and inevitably causes them to be distorted or broken where there is valuable information. We propose a Circular-symmetric Correlation Layer (CCL) based on the formalism of roto-translation equivariant correlation on the continuous group $S^1 \times \mathbb{R}$, and implement it efficiently using the well-known Fast Fourier Transform (FFT) algorithm. We showcase the performance analysis of a general network equipped with CCL on various recognition and classification tasks and datasets. The PyTorch package implementation of CCL is provided online.

Discussion (0). Continue with ORCID to comment.

Pith tools