EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Gaussian Adaptive Pooling: A Cross-Task Generalized Module for Robust Image Processing

Yi Zhang, Shaoqi Dai, Cheng Wang, Xiuhe Li, Jinhe Ran, Guoqiang Zhu, Wenbo Liu, Shuyun Shi

AI · 17.06.2026 · 7 (6) · 226

DOI: 10.3390/ai7060226 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 17.06.2026. Verfasst von Yi Zhang und 7 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The introduction of noise during image acquisition and transmission is inevitable, leading to a significant reduction in the accuracy of image processing tasks, such as target classification, localization, and recognition. To address this issue, this paper proposes a novel robustness-oriented pooling module called Gaussian adaptive pooling. Drawing on the principles of Gaussian filters, the method introduces a Gaussian weight for feature values in the pooling operation, thus integrating filtering and pooling in a novel manner. This approach is both lightweight and versatile, requiring no additional learnable parameters, and enables seamless integration into neural network architectures with pooling layers. Rigorous mathematical derivations and simulation experiments show that our proposed Gaussian adaptive pooling method surpasses conventional methods (average-pooling and max-pooling) in noise handling. Furthermore, its robustness is comparable to traditional pooling methods in addressing challenges such as rotations, scalings, and translations. Extensive evaluations across multiple computer vision tasks—including image classification (CIFAR-10/100), object detection (MS COCO and RTTS), and semantic segmentation (CamVid)—confirm its effectiveness. Specifically, under varying levels of noise and degraded conditions, Gaussian adaptive pooling achieves significant improvements in standard performance metrics compared to conventional pooling methods. For instance, it delivers notable quantitative gains across different tasks including up to a 12.67% increase in mean intersection over union on the CamVid dataset for semantic segmentation and a 1.1% mAP50 enhancement on the real-world RTTS dataset for object detection.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, Y., Dai, S., Wang, C., Li, X., Ran, J., Zhu, G., Liu, W., & Shi, S. (2026). Gaussian Adaptive Pooling: A Cross-Task Generalized Module for Robust Image Processing. AI, 7(6), 226. https://doi.org/10.3390/ai7060226

Vancouver

Zhang Y, Dai S, Wang C, Li X, Ran J, Zhu G, et al. Gaussian Adaptive Pooling: A Cross-Task Generalized Module for Robust Image Processing. AI. 2026;7(6):226. doi:10.3390/ai7060226

BibTeX
@article{Zhang2026,
  author = {Zhang, Yi and Dai, Shaoqi and Wang, Cheng and Li, Xiuhe and Ran, Jinhe and Zhu, Guoqiang and Liu, Wenbo and Shi, Shuyun},
  title = {Gaussian Adaptive Pooling: A Cross-Task Generalized Module for Robust Image Processing},
  journal = {AI},
  year = {2026},
  volume = {7},
  number = {6},
  pages = {226},
  doi = {10.3390/ai7060226}
}
Kostenlos starten →