Token Entropy Regularization for Multi-modal Antenna Affiliation Identification

TL;DR

This paper introduces a multi-modal classification approach for antenna affiliation identification using video, geometric features, and PCI signals, with a novel Token Entropy Regularization to improve model training.

Contribution

It proposes a new training framework and a Token Entropy Regularization module to enhance multi-modal alignment and classification accuracy in antenna identification.

Findings

TER accelerates convergence

Significant performance improvements observed

Entropy of first token is modality-dependent

Abstract

Accurate antenna affiliation identification is crucial for optimizing and maintaining communication networks. Current practice, however, relies on the cumbersome and error-prone process of manual tower inspections. We propose a novel paradigm shift that fuses video footage of base stations, antenna geometric features, and Physical Cell Identity (PCI) signals, transforming antenna affiliation identification into multi-modal classification and matching tasks. Publicly available pretrained transformers struggle with this unique task due to a lack of analogous data in the communications domain, which hampers cross-modal alignment. To address this, we introduce a dedicated training framework that aligns antenna images with corresponding PCI signals. To tackle the representation alignment challenge, we propose a novel Token Entropy Regularization module in the pretraining stage. Our experiments demonstrate that TER accelerates convergence and yields significant performance gains. Further analysis reveals that the entropy of the first token is modality-dependent. Code will be made available upon publication.