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: Mar 6, 2026

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

1.2K

Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs.

Limin Wang, Sheng Guo, Weilin Huang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |March 3, 2017
    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

    Effects of Pre-Hospital Antiplatelet Therapy on the Incidence of ARDS.

    Respiratory care·2020
    Same author

    The involvement of oxytocin in the effects of chronic social defeat stress on emotional behaviours in adult female mandarin voles.

    The European journal of neuroscience·2020
    Same author

    Mobile Application Interventions and Weight Loss in Type 2 Diabetes: A Meta-Analysis.

    Obesity (Silver Spring, Md.)·2020
    Same author

    Functional characterization and physiological roles of the single Shaker outward K<sup>+</sup> channel in Medicago truncatula.

    The Plant journal : for cell and molecular biology·2020
    Same author

    The effects of job characteristics, organizational justice and work engagement on nursing care quality in China: A mediated effects analysis.

    Journal of nursing management·2020
    Same author

    Economic evaluation of cervical cancer screening strategies in urban China.

    Chinese journal of cancer research = Chung-kuo yen cheng yen chiu·2020
    Same journal

    SinColor: Uncertainty-Guided Single-Step Diffusion for Image Colorization.

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

    Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation.

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

    Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

    Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

    Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

    Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a novel multi-resolution Convolutional Neural Network (CNN) architecture and knowledge-guided disambiguation techniques for large-scale scene recognition. The approach effectively addresses intra-class variations and label ambiguity, achieving state-of-the-art results on benchmark datasets.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Deep Learning

    Background:

    • Large-scale scene recognition faces challenges due to multi-level scene information, leading to significant intra-class variations.
    • Increasing numbers of scene categories introduce label ambiguity, complicating accurate classification.
    • Existing Convolutional Neural Networks (CNNs) struggle to capture the full spectrum of visual information for complex scenes.

    Purpose of the Study:

    • To develop an advanced CNN architecture for enhanced large-scale scene recognition.
    • To introduce novel techniques for mitigating label ambiguity in scene classification.
    • To improve the accuracy and robustness of scene recognition models on large datasets.

    Main Methods:

    • A multi-resolution CNN architecture combining coarse and fine resolution networks is proposed.

    More Related Videos

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.1K

    Related Experiment Videos

    Last Updated: Mar 6, 2026

    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

    1.2K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.1K
  • Two knowledge-guided disambiguation techniques are introduced: confusion matrix-based class merging and extra network-based soft labeling.
  • These techniques are applied to train CNNs on the Places2 dataset, leveraging super categories or soft labels.

    • Main Results:

    • The multi-resolution CNN architecture effectively captures visual content and structure at multiple levels.
    • Knowledge-guided disambiguation techniques successfully address label ambiguity issues.
    • The approach achieved state-of-the-art results on MIT Indoor67 (86.7%) and SUN397 (72.0%) benchmarks.
    • The method secured second place in the Places2 challenge (ILSVRC 2015) and first place in the LSUN challenge (CVPR 2016).

    Conclusions:

    • The proposed multi-resolution CNN architecture and disambiguation methods significantly advance large-scale scene recognition.
    • The approach demonstrates superior performance in handling complex scene variations and ambiguous labels.
    • The developed techniques offer a robust solution for large-scale image classification tasks.