aiqbench analysis
This research proposes a novel sigmoid labeling technique for CNN-Transformer networks to overcome grid quantization limits in direction-of-arrival estimation, achieving sub-degree accuracy without increasing computational complexity. By differentiating the network output, the method generates sharp spectral peaks that significantly outperform traditional Gaussian or hard-label baselines in high-resolution scenarios. The work represents a meaningful advancement in deep learning architectures for signal processing tasks where angular precision is critical.
CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
arXiv:2610.13433v1 Announce Type: cross Abstract: This paper addresses the grid quantization error of deep-learning (DL)-based direction-of-arrival (DOA) estimation. Classification- based DOA methods discretize the continuous angular space into a grid, so that with a peak-based read-out, the accuracy and resolution are limited by the grid step and by the width of the label peak. To address this issue, we propose a sigmoid label that encodes the sources' DOAs as the sum of angle-shifted monotonic sigmoid functions. Differentiating the output of a CNN-Transformer network trained with the sigmoid label produces sharp spectral peaks at the source DOAs. Combined with a moderately refined grid step of 0.25 degrees, the CNN-Transformer with the proposed sigmoid label attains sub-degree accuracy and a 1-degree resolution, breaking the limit of the grid quantization error. Under the unified CNN-Transformer backbone, we compare the proposed Sigmoid label with the Gaussian label, the 0-1 hard label, and the binary cross-entropy (BCE) baseline. Numerical results demonstrate that the Sigmoid label attains the highest accuracy and superior resolution compared to other labels.
Abstract:This paper addresses the grid quantization error of deep-learning (DL)-based direction-of-arrival (DOA) estimation. Classification- based DOA methods discretize the continuous angular space into a grid, so that with a peak-based read-out, the accuracy and resolution are limited by the grid step and by the width of the label peak. To address this issue, we propose a sigmoid label that encodes the sources' DOAs as the sum of angle-shifted monotonic sigmoid functions. Differentiating the output of a CNN-Transformer network trained with the sigmoid label produces sharp spectral peaks at the source DOAs. Combined with a moderately refined grid step of 0.25 degrees, the CNN-Transformer with the proposed sigmoid label attains sub-degree accuracy and a 1-degree resolution, breaking the limit of the grid quantization error. Under the unified CNN-Transformer backbone, we compare the proposed Sigmoid label with the Gaussian label, the 0-1 hard label, and the binary cross-entropy (BCE) baseline. Numerical results demonstrate that the Sigmoid label attains the highest accuracy and superior resolution compared to other labels.
Signal Processing (eess.SP); Artificial Intelligence (cs.AI)
arXiv:2610.13433 [eess.SP]
(or arXiv:2610.13433v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2610.13433 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 263 words
Related coverage
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
Does preservation make sense before we know how to revive?
LessWrong · Jun 15, 2026
Value Leakage: An LLM’s Answers Are Silently Shaped by Its Own Values
AI Alignment Forum · Jul 31, 2026
When they can perform a task, AIs are much cheaper than humans
LessWrong · Sep 27, 2026