Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 27, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Lightweight Spatial-Frequency Collaborative Interaction Network for RGB-D Salient Object Detection.

Yitong Lu1, Ziguan Cui2

  • 1Portland Institute, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.

Sensors (Basel, Switzerland)
|June 26, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Salient Object Detection with Semantic-Aware Edge Refinement and Edge-Guided Cross-Attention Feature Aggregation.

Sensors (Basel, Switzerland)·2026
Same author

Three-Dimensional ResNeXt Network Using Feature Fusion and Label Smoothing for Hyperspectral Image Classification.

Sensors (Basel, Switzerland)·2020
See all related articles

We introduce SFCINet, a lightweight network for RGB-D salient object detection. It efficiently fuses spatial and frequency domain information, outperforming existing methods without heavy computational cost.

Area of Science:

  • Computer Vision
  • Image Processing
  • Deep Learning

Background:

  • RGB-D salient object detection (SOD) aims to segment prominent objects using RGB and depth data.
  • Existing methods face a trade-off between accuracy and model complexity.
  • Lightweight methods often struggle to achieve competitive performance.

Purpose of the Study:

  • To propose a lightweight yet effective framework for RGB-D salient object detection.
  • To break the trade-off between model effectiveness and complexity.
  • To enhance feature fusion and global-local consistency in SOD.

Main Methods:

  • Developed the Lightweight Spatial-Frequency Collaborative Interaction Network (SFCINet).
  • Introduced the Spatial-Frequency Synergy (SFS) module for joint spatial-frequency domain analysis.
Keywords:
RGB-D imagesfrequency domainlightweightsalient object detection

Related Experiment Videos

Last Updated: Jun 27, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Designed the Cross-Guidance Interaction (CMGI) module for efficient cross-modal feature fusion.
  • Implemented a Calibrated Hierarchical Decoder (CHD) for integrating frequency priors.

    • Main Results:

    • SFCINet achieves superior performance compared to state-of-the-art methods.
    • The proposed modules effectively address cross-modal discrepancies and enhance feature fusion.
    • The framework demonstrates high efficiency and competitive accuracy.

    Conclusions:

    • SFCINet offers an efficient and effective solution for RGB-D salient object detection.
    • The synergy between spatial and frequency domains is crucial for robust SOD.
    • The proposed approach balances model complexity and performance effectively.