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: Dec 31, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

957

A Multistage Refinement Network for Salient Object Detection.

Lihe Zhang, Jie Wu, Tiantian Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 7, 2020
    PubMed
    Summary

    Deep convolutional neural networks struggle with salient object detection due to feature resolution loss. This study introduces a multistage refinement mechanism to improve detail preservation and accuracy in saliency maps.

    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

    Aggregating global-scale pixel-wise forgery cues within a graph.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    DiMuS: Disentangled Multi-Signal Learning for Weakly Supervised Point-Based 3D Object Detection.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Visual-Textual Information-Driven Tactile Data Generation Method.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Class Sensitive Calibration and Discrepancy-Aware Synthesis for Semi-Supervised Medical Image Segmentation.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Diffusion-based cross-staining feature transformation for whole slide image analysis: From H&E to IHC representation learning.

    Medical image analysis·2026
    Same author

    SD-ReID: View-Aware Stable Diffusion for Aerial-Ground Person Re-Identification.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

    Area of Science:

    • Computer Vision
    • Artificial Intelligence

    Background:

    • Deep convolutional neural networks (CNNs) are widely used in computer vision tasks.
    • Accurate salient object detection requires integrating high-level semantic features with low-level details.
    • Standard CNNs often lose spatial details due to subsampling operations like pooling and convolution.

    Purpose of the Study:

    • To address the challenge of detail loss in CNN-based salient object detection.
    • To propose a novel multistage refinement mechanism for enhancing feature resolution and accuracy.
    • To improve the performance of salient object detection by preserving fine structures.

    Main Methods:

    • Augmenting feedforward neural networks with a multistage refinement mechanism.
    • Utilizing a master net for initial coarse prediction and refinement nets for progressive enhancement.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    707

    Related Experiment Videos

    Last Updated: Dec 31, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    957
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    707
  • Incorporating layerwise recurrent connections for cross-stage information fusion.
  • Applying pyramid pooling and channel attention modules for global context aggregation.

    • Main Results:

    • The proposed method successfully refines saliency maps by progressively combining local context information.
    • The integration of pyramid pooling and channel attention modules effectively aggregates global contexts.
    • Extensive evaluations on six benchmark datasets demonstrate superior performance compared to state-of-the-art methods.

    Conclusions:

    • The multistage refinement mechanism effectively overcomes the limitations of standard CNNs in preserving spatial details for salient object detection.
    • The proposed approach achieves state-of-the-art results in salient object detection.
    • This method offers a promising direction for improving fine-grained feature extraction in deep learning models.