Robust Lightweight Mode Decomposition Based on Geometric Normalization and Multi-Scale Feature Extraction
Photonics · 12.11.2026 · 13 (11) · 1072
DOI: 10.3390/photonics13111072 ↗Kurz gefasst
Fachartikel in der Zeitschrift Photonics, online erschienen am 12.11.2026. Verfasst von Qingqiang Xiong und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanghai Education Development Foundation, Shanghai Science & Technology Development Foundation.
Abstract (Originalsprache)
Mode Decomposition (MD) is an important tool for characterizing the modal energy composition and mode states. However, existing deep learning-based approaches have primarily focused on prediction accuracy under ideal conditions, while the stability of their performance under varying input conditions has received considerably less attention. To address non-ideal perturbations, including translation, scaling, rotation, blur, and noise, we propose a lightweight and robust MD method based on RepViT. Several robustness-oriented feature extraction modules are introduced to enhance local–global spatial, frequency-domain, multi-scale, and spatial-channel representations. Moment-Based Geometric Normalization and BlurPool are further introduced to improve the stability of the model against geometric variations and downsampling-induced sampling sensitivity. In addition, a robustness evaluation framework is established using a Clean test set and five graded composite perturbation levels, together with individual-perturbation tests, the mean composite–perturbation correlation coefficient, and the relative correlation degradation rate. Experimental results show that the proposed method achieves a Pearson correlation coefficient of R=0.9317 even under the strongest composite perturbation. Across the five composite perturbation levels, the mean correlation coefficient reaches 0.9728, while the relative correlation degradation rate is only 2.66%. These results demonstrate that the proposed method substantially improves the stability of mode purity prediction under diverse perturbation conditions while maintaining a lightweight architecture, providing a practical reference for robust MD and deployment in fiber-optic systems.
Förderung
- National Natural Science Foundation of China
- Shanghai Education Development Foundation
- Shanghai Science & Technology Development Foundation
Zitieren
APA
Xiong, Q., Wang, H., Liu, Z., Jing, L., Yang, B., Wen, Y., Wang, T., & Zuo, J. (2026). Robust Lightweight Mode Decomposition Based on Geometric Normalization and Multi-Scale Feature Extraction. Photonics, 13(11), 1072. https://doi.org/10.3390/photonics13111072
Vancouver
Xiong Q, Wang H, Liu Z, Jing L, Yang B, Wen Y, et al. Robust Lightweight Mode Decomposition Based on Geometric Normalization and Multi-Scale Feature Extraction. Photonics. 2026;13(11):1072. doi:10.3390/photonics13111072
BibTeX
@article{Xiong2026,
author = {Xiong, Qingqiang and Wang, Haoyu and Liu, Zhiyong and Jing, Linya and Yang, Binlei and Wen, Yalong and Wang, Teng and Zuo, Jiancun},
title = {Robust Lightweight Mode Decomposition Based on Geometric Normalization and Multi-Scale Feature Extraction},
journal = {Photonics},
year = {2026},
volume = {13},
number = {11},
pages = {1072},
doi = {10.3390/photonics13111072}
}
EUVIMED