Pith. sign in

REVIEW 2 cited by

High-Capacity Complex Convolutional Neural Networks For I/Q Modulation Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2010.10717 v1 pith:4H6R5LSC submitted 2020-10-21 cs.CV

Jakob Krzyston , Rajib Bhattacharjea , Andrew Stark This is my paper · ORCID
classification cs.CV
keywords classificationconvolutionsarchitecturescomparablecomplexcomplex-valuedmodulationhigh-capacity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

I/Q modulation classification is a unique pattern recognition problem as the data for each class varies in quality, quantified by signal to noise ratio (SNR), and has structure in the complex-plane. Previous work shows treating these samples as complex-valued signals and computing complex-valued convolutions within deep learning frameworks significantly increases the performance over comparable shallow CNN architectures. In this work, we claim state of the art performance by enabling high-capacity architectures containing residual and/or dense connections to compute complex-valued convolutions, with peak classification accuracy of 92.4% on a benchmark classification problem, the RadioML 2016.10a dataset. We show statistically significant improvements in all networks with complex convolutions for I/Q modulation classification. Complexity and inference speed analyses show models with complex convolutions substantially outperform architectures with a comparable number of parameters and comparable speed by over 10% in each case.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A compact transformer trained with adversarial attention-map distillation achieves higher accuracy under white-box FGM and PGD attacks than existing adversarial distillation baselines.

  2. Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications

    cs.LG 2025-06 reject novelty 4.0 of 10

    A vision transformer with an additional adversarial indicator token detects and withstands white-box adversarial attacks on radio signal modulation classification better than several prior defenses.

Pith tools