Fisher-DARTS: A Neural Architecture Search Framework with Fisher Information Optimization
Applied Sciences · 14.04.2026 · 16 (8) · 3808
DOI: 10.3390/app16083808 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 14.04.2026. Verfasst von Yu Zhang und 1 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Differentiable Neural Architecture Search has emerged as a powerful paradigm for automated network design, yet it suffers from a fundamental optimization inconsistency problem: Architectures optimized under continuous relaxation often fail to maintain their performance after discretization. To address this challenge, we propose Fisher-DARTS—a Fisher information-driven differentiable NAS framework. The proposed method introduces three key innovations: (1) a Fisher information-based momentum update mechanism that guides architectural parameters toward statistically significant operations, aligning the search objective with discrete deployment; (2) a progressive three-region pruning strategy that adaptively eliminates redundant operations with low Fisher information, ensuring architectural compactness; and (3) a cell-weighted fusion module that preserves multi-scale features across stacked cells. Additionally, the search space is expanded by incorporating attention mechanisms to enhance feature representation capability. The proposed framework is generic and applicable to a wide range of vision tasks. To validate its effectiveness, we apply it to gaze estimation—a core technology in multimodal human–computer interaction. Experimental results on three public datasets, MPIIFaceGaze, RT-GENE, and ETH-XGaze, demonstrate that Fisher-DARTS achieves mean angular errors of 3.22°, 5.45°, and 4.12°, respectively, outperforming hand-designed networks and existing NAS-based gaze estimation models. These results validate the effectiveness of the proposed Fisher-driven NAS framework and its generalization capability across diverse scenarios.
Zitieren
APA
Zhang, Y., & Wang, C. (2026). Fisher-DARTS: A Neural Architecture Search Framework with Fisher Information Optimization. Applied Sciences, 16(8), 3808. https://doi.org/10.3390/app16083808
Vancouver
Zhang Y, Wang C. Fisher-DARTS: A Neural Architecture Search Framework with Fisher Information Optimization. Applied Sciences. 2026;16(8):3808. doi:10.3390/app16083808
BibTeX
@article{Zhang2026,
author = {Zhang, Yu and Wang, Changyuan},
title = {Fisher-DARTS: A Neural Architecture Search Framework with Fisher Information Optimization},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {8},
pages = {3808},
doi = {10.3390/app16083808}
}
EUVIMED