EUVIMEDEUVIMED entdecken
Crossref

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

Bin Tang, Zhengyi Liu, Yacheng Tan, Qian He

IEEE Transactions on Circuits and Systems for Video Technology · 2023-02 · 33 (2) · 728-742

DOI: 10.1109/tcsvt.2022.3202563 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-02. Verfasst von Bin Tang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 151-mal zitiert (Crossref) und nennt 134 Literaturangaben. Gefördert von: Natural Science Foundation of Anhui Province, Science Research Project for Graduate Student of Anhui Provincial Education Department, Talent Research Fund Project of Hefei University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output’s fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level. The proposed model, named HRTransNet, first introduces an auxiliary stream for feature extraction of supplementary modality. Then, features are injected into the primary modality at the beginning of each multi-resolution branch. Next, HRFormer is applied to achieve forwarding propagation. Finally, all the output features with different resolutions are aggregated by intra-feature and inter-feature interactive transformers. Application of the proposed model results in impressive improvement for driving two-modality SOD tasks, e.g., RGB-D, RGB-T, and light field SOD.https://github.com/liuzywen/HRTransNet

Förderung

  • Natural Science Foundation of Anhui Province
  • Science Research Project for Graduate Student of Anhui Provincial Education Department
  • Talent Research Fund Project of Hefei University

Zitieren

APA

Tang, B., Liu, Z., Tan, Y., & He, Q. (2023). HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 728-742. https://doi.org/10.1109/tcsvt.2022.3202563

Vancouver

Tang B, Liu Z, Tan Y, He Q. HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(2):728-742. doi:10.1109/tcsvt.2022.3202563

BibTeX
@article{Tang2023,
  author = {Tang, Bin and Liu, Zhengyi and Tan, Yacheng and He, Qian},
  title = {HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {2},
  pages = {728--742},
  doi = {10.1109/tcsvt.2022.3202563}
}
Kostenlos starten →