Weighted Copula Entropy for Structural Pruning in Long-Tailed Autonomous Driving Object Detection
Entropy · 17.03.2026 · 28 (3) · 336
DOI: 10.3390/e28030336 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 17.03.2026. Verfasst von Yue Zhou und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shangyuancun, Haidian District, Beijing 100044, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities of Beijing Jiaotong University, National Key Research and Development Program.
Abstract (Originalsprache)
In autonomous driving, deep convolutional neural networks face a core conflict between computational efficiency and safety-critical robustness on resource-constrained onboard computing units. Dominant structural pruning, based on weight magnitude or geometric statistics, fails in long-tailed traffic scenarios by equating parameter magnitude with feature importance and pruning critical filters in the tail classes. To address this, we propose a structural pruning framework that evaluates the semantic utility of features using weighted copula entropy rather than relying solely on their magnitude. Our novel approach integrates Elastic Net regularization for inducing sparsity and weighted copula entropy for unbiased information-theoretic feature selection. By incorporating inverse class frequency weighting into empirical Copula estimation, we decouple feature relevance from sample abundance, ensuring the preservation of rare-class discriminators based on their information content rather than occurrence frequency. Furthermore, this metric is embedded into an enhanced max-relevance and min-redundancy algorithm to eliminate semantic redundancy while maintaining representational diversity. Extensive experiments on the BDD100K dataset with YOLOv5l and YOLOv8l architectures demonstrate that, at a 50% pruning rate, the proposed method reduces FLOPs and parameters by nearly 50%, with only 0.09% mAP@0.5 loss for YOLOv5l and 0.14% mAP@0.5 loss for YOLOv8l, while significantly improving the mAP of the extreme tail class Train from 0% to 3.84% and 2.76% to 5.12%, respectively. It achieves a more favorable trade-off between detection accuracy and computational efficiency than mainstream pruning approaches. This work provides a lightweight scheme for autonomous driving perception models and a new information-theoretic perspective for structured network pruning.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shangyuancun, Haidian District, Beijing 100044, China.
- State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, No. 3 Shangyuancun, Haidian District, Beijing 100044, China.
- The Beijing Research Center of Urban Traffic Information Intelligent Sensing and Service Technologies, Beijing Jiaotong University, No. 3 Shangyuancun, Haidian District, Beijing 100044, China.
ORCID-Profile: Yue Zhou
Förderung
- Fundamental Research Funds for the Central Universities of Beijing Jiaotong University
- National Key Research and Development Program
Zitieren
APA
Zhou, Y., Ma, J., & Dong, H. (2026). Weighted Copula Entropy for Structural Pruning in Long-Tailed Autonomous Driving Object Detection. Entropy, 28(3), 336. https://doi.org/10.3390/e28030336
Vancouver
Zhou Y, Ma J, Dong H. Weighted Copula Entropy for Structural Pruning in Long-Tailed Autonomous Driving Object Detection. Entropy. 2026;28(3):336. doi:10.3390/e28030336
BibTeX
@article{Zhou2026,
author = {Zhou, Yue and Ma, Jihui and Dong, Honghui},
title = {Weighted Copula Entropy for Structural Pruning in Long-Tailed Autonomous Driving Object Detection},
journal = {Entropy},
year = {2026},
volume = {28},
number = {3},
pages = {336},
doi = {10.3390/e28030336}
}
EUVIMED