EUVIMEDEUVIMED entdecken
Crossref

Multiscale Attentive Image De-Raining Networks via Neural Architecture Search

Lei Cai, Yuli Fu, Wanliang Huo, Youjun Xiang, Tao Zhu, Ying Zhang, Huanqiang Zeng, Delu Zeng

IEEE Transactions on Circuits and Systems for Video Technology · 2023-02 · 33 (2) · 618-633

DOI: 10.1109/tcsvt.2022.3207516 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-02. Verfasst von Lei Cai und 7 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Natural Science Foundation of Guangdong Province, Guangzhou Technical Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-scale architectures and attention modules have shown effectiveness in many deep learning-based image de-raining methods. However, manually designing and integrating these two components into a neural network requires a bulk of labor and extensive expertise. In this article, a high-performance multi-scale attentive neural architecture search (MANAS) framework is technically developed for image de-raining. The proposed method formulates a new multi-scale attention search space with multiple flexible modules that are favorite to the image de-raining task. Under the search space, multi-scale attentive cells are built, which are further used to construct a powerful image de-raining network. The internal multi-scale attentive architecture of the de-raining network is searched automatically through a gradient-based search algorithm, which avoids the daunting procedure of the manual design to some extent. Moreover, in order to obtain a robust image de-raining model, a practical and effective multi-to- one training strategy is also presented to allow the de-raining network to get sufficient background information from multiple rainy images with the same background scene, and meanwhile, multiple loss functions including external loss, internal loss, architecture regularization loss, and model complexity loss are jointly optimized to achieve robust de-raining performance and controllable model complexity. Extensive experimental results on both synthetic and realistic rainy images, as well as the down-stream vision applications (i.e., objection detection and segmentation) consistently demonstrate the superiority of our proposed method. The code is publicly available at https://github.com/lcai-gz/MANAS.

Förderung

  • National Key Research and Development Program of China
  • Natural Science Foundation of Guangdong Province
  • Guangzhou Technical Project
  • NSFC
  • Fundamental Research Program of Guangdong

Zitieren

APA

Cai, L., Fu, Y., Huo, W., Xiang, Y., Zhu, T., Zhang, Y., Zeng, H., & Zeng, D. (2023). Multiscale Attentive Image De-Raining Networks via Neural Architecture Search. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 618-633. https://doi.org/10.1109/tcsvt.2022.3207516

Vancouver

Cai L, Fu Y, Huo W, Xiang Y, Zhu T, Zhang Y, et al. Multiscale Attentive Image De-Raining Networks via Neural Architecture Search. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(2):618-633. doi:10.1109/tcsvt.2022.3207516

BibTeX
@article{Cai2023,
  author = {Cai, Lei and Fu, Yuli and Huo, Wanliang and Xiang, Youjun and Zhu, Tao and Zhang, Ying and Zeng, Huanqiang and Zeng, Delu},
  title = {Multiscale Attentive Image De-Raining Networks via Neural Architecture Search},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {2},
  pages = {618--633},
  doi = {10.1109/tcsvt.2022.3207516}
}
Kostenlos starten →