A Directional Shape-Adaptive Convolutional Kernel Network for Small-Object Detection
Sensors · 11.11.2026 · 26 (22) · 7119
DOI: 10.3390/s26227119 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.11.2026. Verfasst von Dong Wang und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shaanxi Province.
Abstract (Originalsprache)
In object detection networks based on convolutional neural networks, the performance of small-object detection is affected by multiple factors. One key factor is that, due to the low resolution of small objects, their features are gradually diluted after multiple convolutional operations. Multi-scale pyramid features can alleviate this issue by performing prediction in shallow feature layers, but the improvement is still limited by the fixed sampling structure of convolution: each operation involves a fixed neighborhood, and the more convolutions are applied, the more the object’s own features are diluted by background pixels. This paper proposes a directional shape-adaptive convolution (DSAConv) for image feature extraction. Nine 3×3 kernels with directional displacement and different mask shapes are designed, and the maximum response is selected at each spatial position, providing a response-driven selection that is related to the object shape. The cascaded use of these kernels yields a variable receptive field that depends on the selected kernels, which is beneficial for small-object feature extraction. Integrated into the C3K2 Bottleneck blocks of YOLOv11s, DSAConv improves small-object APS by 2.7 and 3.2 points on COCO and VisDrone, respectively. Extensive experimental results demonstrate the effectiveness of the proposed method.
Förderung
- Natural Science Foundation of Shaanxi Province
Zitieren
APA
Wang, D., Zhu, H., Zhao, Y., Shi, J., & Xing, N. (2026). A Directional Shape-Adaptive Convolutional Kernel Network for Small-Object Detection. Sensors, 26(22), 7119. https://doi.org/10.3390/s26227119
Vancouver
Wang D, Zhu H, Zhao Y, Shi J, Xing N. A Directional Shape-Adaptive Convolutional Kernel Network for Small-Object Detection. Sensors. 2026;26(22):7119. doi:10.3390/s26227119
BibTeX
@article{Wang2026,
author = {Wang, Dong and Zhu, Hong and Zhao, Yue and Shi, Jing and Xing, Nan},
title = {A Directional Shape-Adaptive Convolutional Kernel Network for Small-Object Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {22},
pages = {7119},
doi = {10.3390/s26227119}
}
EUVIMED