Lightweight Object Detection in Complex Scenarios via Structural Reparameterization and Multi-Scale Adaptive Fusion
Applied Sciences · 17.11.2026 · 16 (22) · 11404
DOI: 10.3390/app162211404 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 17.11.2026. Verfasst von Linan Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Due to adverse factors such as dense target distributions, mutual occlusion, illumination variations, and complex background clutter, existing object detection networks still face challenges in balancing detection accuracy and model complexity within real-world scenarios. To address these issues, this paper explores a lightweight multi-scale object detection architecture based on structural reparameterization and dynamic feature fusion by adapting and integrating several complementary mechanisms into the YOLO11s baseline. First, a two-column lightweight reversible backbone network (Dbb_RevCol) is constructed by combining Reversible Column Networks (RevCol) with the Diverse Branch Block (DBB). This design facilitates the preservation of shallow spatial details during forward propagation while compressing inference parameters via structural reparameterization. Second, Depthwise Separable Convolutions (DSConv) and the Content-Aware ReAssembly of FEatures (CARAFE) upsampling operator are incorporated into a streamlined four-level Bidirectional Feature Pyramid Network (DS-BiFPN) to reduce multi-scale fusion overhead and alleviate detail loss during spatial upsampling. Finally, a high-resolution detection branch (160 × 160) cascaded with the Multi-scale Attention (EMA) module is introduced to enhance feature discrimination for small and partially occluded targets in cluttered scenes. Experimental evaluations on the PASCAL VOC 2012 benchmark demonstrate that the proposed model achieves a Precision of 78.1% and an mAP@0.5 of 78.8%, representing improvements of 0.7% and 2.9% over the baseline YOLO11s, respectively, though its strict-threshold mAP@0.5:0.95 (50.8%) remains comparable to the baseline (51.0%). Meanwhile, the model requires 6.4 M parameters and 24.6 GFLOPs, reducing parameter count by 42.3% and computational cost by 12.8% relative to YOLO11s. The proposed architectural integration provides a practical trade-off between model compression and detection sensitivity at standard IoU thresholds.
Zitieren
APA
Zhang, L., Qiao, J., & Jin, J. (2026). Lightweight Object Detection in Complex Scenarios via Structural Reparameterization and Multi-Scale Adaptive Fusion. Applied Sciences, 16(22), 11404. https://doi.org/10.3390/app162211404
Vancouver
Zhang L, Qiao J, Jin J. Lightweight Object Detection in Complex Scenarios via Structural Reparameterization and Multi-Scale Adaptive Fusion. Applied Sciences. 2026;16(22):11404. doi:10.3390/app162211404
BibTeX
@article{Zhang2026,
author = {Zhang, Linan and Qiao, Jinghui and Jin, Junjie},
title = {Lightweight Object Detection in Complex Scenarios via Structural Reparameterization and Multi-Scale Adaptive Fusion},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {22},
pages = {11404},
doi = {10.3390/app162211404}
}
EUVIMED