EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Combining transformer global and local feature extraction for object detection

Tianping Li, Zhenyi Zhang, Mengdi Zhu, Zhaotong Cui, Dongmei Wei

Complex & Intelligent Systems · 2024-08 · 10 (4) · 4897-4920

DOI: 10.1007/s40747-024-01409-z ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 15.04.2024. Verfasst von Tianping Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China-Shandong Joint Fund for Marine Science Research Centers.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional neural network (CNN)-based object detectors perform excellently but lack global feature extraction and cannot establish global dependencies between object pixels. Although the Transformer is able to compensate for this, it does not incorporate the advantages of convolution, which results in insufficient information being obtained about the details of local features, as well as slow speed and large computational parameters. In addition, Feature Pyramid Network (FPN) lacks information interaction across layers, which can reduce the acquisition of feature context information. To solve the above problems, this paper proposes a CNN-based anchor-free object detector that combines transformer global and local feature extraction (GLFT) to enhance the extraction of semantic information from images. First, the segmented channel extraction feature attention (SCEFA) module was designed to improve the extraction of local multiscale channel features from the model and enhance the discrimination of pixels in the object region. Second, the aggregated feature hybrid transformer (AFHTrans) module combined with convolution is designed to enhance the extraction of global and local feature information from the model and to establish the dependency of the pixels of distant objects. This approach compensates for the shortcomings of the FPN by means of multilayer information aggregation transmission. Compared with a transformer, these methods have obvious advantages. Finally, the feature extraction head (FE-Head) was designed to extract full-text information based on the features of different tasks. An accuracy of 47.0% and 82.76% was achieved on the COCO2017 and PASCAL VOC2007 + 2012 datasets, respectively, and the experimental results validate the effectiveness of our method.

Förderung

  • National Natural Science Foundation of China-Shandong Joint Fund for Marine Science Research Centers

Zitieren

APA

Li, T., Zhang, Z., Zhu, M., Cui, Z., & Wei, D. (2024). Combining transformer global and local feature extraction for object detection. Complex & Intelligent Systems, 10(4), 4897-4920. https://doi.org/10.1007/s40747-024-01409-z

Vancouver

Li T, Zhang Z, Zhu M, Cui Z, Wei D. Combining transformer global and local feature extraction for object detection. Complex & Intelligent Systems. 2024;10(4):4897-4920. doi:10.1007/s40747-024-01409-z

BibTeX
@article{Li2024,
  author = {Li, Tianping and Zhang, Zhenyi and Zhu, Mengdi and Cui, Zhaotong and Wei, Dongmei},
  title = {Combining transformer global and local feature extraction for object detection},
  journal = {Complex & Intelligent Systems},
  year = {2024},
  volume = {10},
  number = {4},
  pages = {4897--4920},
  doi = {10.1007/s40747-024-01409-z}
}
Kostenlos starten →