Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Phase Contrast and Differential Interference Contrast Microscopy

Phase Contrast and Differential Interference Contrast Microscopy

Phase-Contrast Microscopes
In-phase-contrast microscopes, interference between light directly passing through a cell and light refracted by cellular components is used to create high-contrast, high-resolution images without staining. It is the oldest and simplest type of microscope that creates an image by altering the wavelengths of light rays passing through the specimen. Altered wavelength paths are created using an annular stop in the condenser. The annular stop produces a hollow cone of...

You might also read

Related Articles

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

Sort by

Same author

Tumor suppressor role of sFRP‑4 in hepatocellular carcinoma via the Wnt/β‑catenin signaling pathway.

Molecular medicine reports·2021

Same author

Preliminary clinical experience of robot-assisted surgery in treatment with genioplasty.

Scientific reports·2021

Same author

Merging Annulation with Ring Deconstruction: Synthesis of (<i>E</i>)-3-(2-Acyl-1<i>H</i>-benzo[<i>d</i>]imidazol-4-yl)acrylaldehyde Derivatives via I<sub>2</sub>/FeCl<sub>3</sub>-Promoted Dual C(sp<sup>3</sup>)-H Amination/C-N Bond Cleavage.

Organic letters·2021

Same author

MassARRAY multigene screening combined with LDL-C and sdLDL-C detection for more favorable outcomes in type 2 diabetes mellitus therapy.

BMC medical genomics·2021

Same author

Nidogen-1 expression is associated with overall survival and temozolomide sensitivity in low-grade glioma patients.

Aging·2021

Same author

Deep learning-based methods may minimize GBCA dosage in brain MRI.

European radiology·2021

Search research articles

Related Experiment Video

Updated: May 21, 2025

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

Unambiguous granularity distillation for asymmetric image retrieval.

Hongrui Zhang¹, Yi Xie¹, Haoquan Zhang¹

¹School of Future Technology, South China University of Technology, Guangzhou, China.

Neural Networks : the Official Journal of the International Neural Network Society

|March 19, 2025

Summary

Layered-Granularity Localized Distillation (GranDist) improves asymmetric image retrieval by effectively transferring local semantic information. This method enhances feature representation alignment, outperforming existing techniques on benchmark datasets.

Keywords:

Asymmetric image retrieval Knowledge distillation

More Related Videos

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

Quantifying Intermembrane Distances with Serial Image Dilations

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

Related Experiment Videos

Last Updated: May 21, 2025

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

Quantifying Intermembrane Distances with Serial Image Dilations

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Asymmetric image retrieval methods often struggle to transfer local semantic information effectively.
Existing knowledge distillation techniques focus on global feature alignment, limiting fine-grained representation space matching.

Purpose of the Study:

To propose a novel approach, Layered-Granularity Localized Distillation (GranDist), for enhanced asymmetric image retrieval.
To address the limitations of transferring local semantic information in previous methods.

Main Methods:

GranDist constructs layered feature representations balancing contextual richness and local feature granularity.
Decouples feature maps to capture local features at different granularities and establishes focused distillation pipelines.
Introduces Unambiguous Localized Feature Selection (UnamSel) to discard ambiguous features, preventing irrelevant information transfer.

Main Results:

GranDist effectively transfers contextualized local features across network layers.
UnamSel successfully filters out ambiguous features, improving retrieval accuracy.
Extensive experiments show GranDist outperforms state-of-the-art asymmetric retrieval methods.

Conclusions:

GranDist significantly enhances asymmetric image retrieval by enabling effective local feature transfer.
The proposed method improves fine-grained alignment of feature representation spaces.
GranDist offers a more robust and accurate solution for asymmetric image retrieval tasks.