EUVIMEDEUVIMED entdecken
Crossref

Rethinking Feature Mining for Light Field Salient Object Detection

Guibiao Liao, Wei Gao

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.10.2024 · 20 (10) · 1-24

DOI: 10.1145/3676967 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 29.10.2024. Verfasst von Guibiao Liao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 105 Literaturangaben. Gefördert von: The Major Key Project of PCL, Natural Science Foundation of China, Guangdong Province Pearl River Talent Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Light field salient object detection (LF SOD) has recently received increasing attention. However, most current works typically rely on an individual focal stack backbone for feature extraction. This manner ignores the characteristic of blurred saliency-related regions and contour within focal slices, resulting in insufficient or even inaccurate saliency responses. Aiming at addressing this issue, we rethink the feature mining (i.e., exploration) within focal slices and focus on exploiting informative focal slice features and fully leveraging contour information for accurate LF SOD. First, we observe that the geometric relation between different regions within the focal slices is conducive to useful saliency feature mining if utilized properly. In light of this, we propose an implicit graph learning (IGL) approach. The IGL constructs graph structures to propagate informative geometric relations within the focal slices and all-focus features, and promotes crucial and discriminative focal stack feature mining via graph feature distillation. Second, unlike previous works that rarely utilize contour information, we propose a reciprocal refinement fusion (RRF) strategy. This strategy encourages saliency features and object contour cues to effectively complement each other. Furthermore, a contour hint injection mechanism is introduced to refine the feature expressions. Extensive experiments showcase the superiority of our approach over previous state-of-the-art models with an efficient real-time inference speed. Codes are available at https://github.com/gbliao/IRNet and https://openi.pcl.ac.cn/OpenVision/IRNet .

Förderung

  • The Major Key Project of PCL
  • Natural Science Foundation of China
  • Guangdong Province Pearl River Talent Program
  • Guangdong Basic and Applied Basic Research Foundation
  • Shenzhen Science and Technology Program
  • CAAI-MindSpore Open Fund, developed on OpenI Community

Zitieren

APA

Liao, G., & Gao, W. (2024). Rethinking Feature Mining for Light Field Salient Object Detection. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(10), 1-24. https://doi.org/10.1145/3676967

Vancouver

Liao G, Gao W. Rethinking Feature Mining for Light Field Salient Object Detection. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(10):1-24. doi:10.1145/3676967

BibTeX
@article{Liao2024,
  author = {Liao, Guibiao and Gao, Wei},
  title = {Rethinking Feature Mining for Light Field Salient Object Detection},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2024},
  volume = {20},
  number = {10},
  pages = {1--24},
  doi = {10.1145/3676967}
}
Kostenlos starten →