EUVIMEDEUVIMED entdecken
Crossref

UEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection

Ziteng Qiao, Dianxi Shi, Xiaodong Yi, Yanyan Shi, Yuhui Zhang, Yangyang Liu

ACM Transactions on Multimedia Computing, Communications, and Applications · 30.06.2023 · 19 (2s) · 1-21

DOI: 10.1145/3561824 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 17.02.2023. Verfasst von Ziteng Qiao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 49 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection models based on feature pyramid networks have made significant progress in general object detection. However, small object detection is still a challenge for the existing models. In this paper, we think that two factors in the existing feature pyramid networks inhibit the performance of small object detection. The first one is that the different feature domains of shallow and deep layer features inhibit the model performance. The second one is that the accumulation of upper layer features leads to feature aliasing effect on the lower layer features, which interferes with the representations of small object features. Therefore, we propose Unified and Enhanced Feature Pyramid Networks (UEFPN) to improve the APs and ARs of small object detection. It has the following three characteristics: (1) Using the deep features of high-resolution image and original image to form the multi-scale features of unified domain. (2) In multi-scale features fusion, we learn the importance of upper layer features with the Channel Attention Fusion module (CAF) , to optimize feature aliasing effect and enhance the context information of shallow layer features. (3) UEFPN can be quickly applied to different models. The results of many experiments show that the models with UEFPN achieve significant performance improvement in small object detection compared with the baseline models.

Zitieren

APA

Qiao, Z., Shi, D., Yi, X., Shi, Y., Zhang, Y., & Liu, Y. (2023). UEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(2s), 1-21. https://doi.org/10.1145/3561824

Vancouver

Qiao Z, Shi D, Yi X, Shi Y, Zhang Y, Liu Y. UEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(2s):1-21. doi:10.1145/3561824

BibTeX
@article{Qiao2023,
  author = {Qiao, Ziteng and Shi, Dianxi and Yi, Xiaodong and Shi, Yanyan and Zhang, Yuhui and Liu, Yangyang},
  title = {UEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2023},
  volume = {19},
  number = {2s},
  pages = {1--21},
  doi = {10.1145/3561824}
}
Kostenlos starten →