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 Videos

Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval.

Xiu-Shen Wei, Jian-Hao Luo, Jianxin Wu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 4, 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

    <i>LsToll</i> Gene Mediates Antibacterial Immunity and Developmental Regulation in <i>Loxostege sticticalis</i>.

    Insects·2026
    Same author

    Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    Long-Term Outcomes From a Decade of Donation After Circulatory Death Heart Transplantation in Australia.

    JACC. Heart failure·2026
    Same author

    Coarse Labels Matter: Revisiting the Role of Coarse-Grained Supervision in Fine-Grained Learning.

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

    Rapid Determination of Several Biogenic Amines in Cold-Chain Fish Samples by Portable Ion Trap Mass Spectrometry with Nano-Electrospray Ionization.

    Foods (Basel, Switzerland)·2026
    Same author

    Aerosol Inhalation of a Recombinant H7N9 Hemagglutinin Antigen Elicits Systemic and Mucosal Immune Responses in Mice.

    Viruses·2026
    Same journal

    Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

    Semantic Frame Interpolation.

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

    Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

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

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

    This study introduces a new unsupervised method for fine-grained image retrieval. The selective convolutional descriptor aggregation (SCDA) method effectively retrieves images without needing any labels or annotations.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Deep convolutional neural networks (CNNs) pre-trained on ImageNet are widely used in various domains.
    • Existing methods often require domain-specific annotations, limiting their application.
    • Fine-grained image retrieval, especially in an unsupervised setting, remains a challenging task.

    Purpose of the Study:

    • To propose a novel unsupervised method for fine-grained image retrieval.
    • To address the difficulty of classifying and retrieving fine-grained images without labels.
    • To develop a method that effectively utilizes deep features for retrieval.

    Main Methods:

    • Selective Convolutional Descriptor Aggregation (SCDA) method.
    • Object localization to discard background noise and retain relevant deep descriptors.

    Related Experiment Videos

  • Aggregation and dimensionality reduction of selected descriptors into a compact feature vector.
  • Unsupervised approach requiring no image labels or bounding box annotations.

    • Main Results:

    • Demonstrated effectiveness of SCDA on six fine-grained datasets for image retrieval.
    • Visualizations show SCDA features correspond to subtle visual attributes.
    • Achieved high-mean average precision in fine-grained retrieval tasks.
    • Obtained comparable results to state-of-the-art methods on general image retrieval datasets.

    Conclusions:

    • SCDA is a highly effective unsupervised method for fine-grained image retrieval.
    • The method's ability to capture subtle visual attributes contributes to its high performance.
    • SCDA shows promise for both specialized fine-grained and general image retrieval applications.