Cross-Scale Multi-Task Lightweight Hyper-Network Model for Remote Sensing Target Classification
Remote Sensing · 10.03.2026 · 18 (6) · 844
DOI: 10.3390/rs18060844 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.03.2026. Verfasst von Shiming Xu und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xiaofan Liu, National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper presents a lightweight hyper-network architecture for cross-scale multi-task object classification, addressing the critical challenge of gradient interference in joint learning scenarios. We propose a HyperConv module integrated into a slim ResNet-12 backbone, which dynamically generates task-adaptive 3 × 3 convolutional kernels from compact two-dimensional latent vectors. This design allows explicit control over gradient flows for different tasks with minimal parameter overhead (only 3.2% additional parameters). Our framework incorporates adversarial regularization via a Gradient Reversal Layer (GRL) and dynamic task-weight scheduling to mitigate gradient conflicts across domains. Experiments on both natural image datasets (Mini-ImageNet and CIFAR-100) and remote sensing benchmarks (EuroSat and UCMerced_LandUse) demonstrate statistically significant improvements over conventional shared-parameter baselines. The proposed method effectively reduces negative transfer, enhances feature representation, and offers a practical solution for on-device multi-task learning in resource-constrained remote sensing applications such as UAVs and edge satellites.
Förderung
- Xiaofan Liu, National Natural Science Foundation of China
Zitieren
APA
Xu, S., Hu, S., Liao, N., Yuan, Z., Sun, X., Zhuang, J., & Yan, Y. (2026). Cross-Scale Multi-Task Lightweight Hyper-Network Model for Remote Sensing Target Classification. Remote Sensing, 18(6), 844. https://doi.org/10.3390/rs18060844
Vancouver
Xu S, Hu S, Liao N, Yuan Z, Sun X, Zhuang J, et al. Cross-Scale Multi-Task Lightweight Hyper-Network Model for Remote Sensing Target Classification. Remote Sensing. 2026;18(6):844. doi:10.3390/rs18060844
BibTeX
@article{Xu2026,
author = {Xu, Shiming and Hu, Shuaijiang and Liao, Nannan and Yuan, Zhe and Sun, Xiqiao and Zhuang, Junbin and Yan, Yunyi},
title = {Cross-Scale Multi-Task Lightweight Hyper-Network Model for Remote Sensing Target Classification},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {6},
pages = {844},
doi = {10.3390/rs18060844}
}
EUVIMED