Token Entropy Regularization for Multi-modal Antenna Affiliation Identification
This addresses the cumbersome and error-prone manual tower inspections in communication network optimization, representing a novel paradigm shift rather than an incremental improvement.
The paper tackles the problem of antenna affiliation identification by fusing video, geometric features, and PCI signals into a multi-modal classification task, achieving significant performance gains and accelerated convergence with their proposed Token Entropy Regularization module.
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.