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

Cluster Sampling Method

Cluster Sampling Method

Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...

Confocal Fluorescence Microscopy

Confocal Fluorescence Microscopy

Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...

You might also read

Related Articles

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

Sort by

Same author

Advances in Ophthalmic Optogenetics: Approaches and Applications.

Biomolecules·2022

Same author

A Scoping Review of Drug Epidemic Models.

International journal of environmental research and public health·2022

Same author

Evaluation of reconstructed auricles by convolutional neural networks.

Journal of plastic, reconstructive & aesthetic surgery : JPRAS·2022

Same author

Facial expression recognition based on deep learning.

Computer methods and programs in biomedicine·2022

Same author

Glucagon-Like Peptide-1 Receptor Regulates Macrophage Migration in Monosodium Urate-Induced Peritoneal Inflammation.

Frontiers in immunology·2022

Same author

Targeting HNRNPM Inhibits Cancer Stemness and Enhances Antitumor Immunity in Wnt-activated Hepatocellular Carcinoma.

Cellular and molecular gastroenterology and hepatology·2022

Search research articles

Related Experiment Video

Updated: Sep 4, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Confusion-Based Metric Learning for Regularizing Zero-Shot Image Retrieval and Clustering.

Binghui Chen, Weihong Deng, Biao Wang

IEEE Transactions on Neural Networks and Learning Systems

|July 14, 2022

Summary

This study introduces confusion-based metric learning (CML) to improve zero-shot retrieval and clustering by enhancing generalization. CML uses novel regularization terms to create robust embeddings, achieving state-of-the-art results.

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Related Experiment Videos

Last Updated: Sep 4, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Deep metric learning is crucial for zero-shot image retrieval and clustering (ZSRC).
Existing methods focus on discriminative embeddings, often neglecting generalization.
Generalization is vital for metric performance in zero-shot scenarios.

Purpose of the Study:

To propose a novel framework, confusion-based metric learning (CML), for robust metric optimization.
To emphasize the importance of generalization ability in deep metric learning for ZSRC tasks.
To introduce regularization terms that enhance metric robustness.

Main Methods:

Developed the confusion-based metric learning (CML) framework.
Introduced energy confusion (EC) and diversity confusion (DC) regularization terms.
Trained confusion terms adversarially with conventional deep metric objectives.

Main Results:

Demonstrated that CML enhances generalization ability in deep metric learning.
Achieved state-of-the-art performance on CUB, CARS, Stanford Online Products, and In-Shop datasets.
Showcased CML's applicability to various conventional metric learning methods.

Conclusions:

Generalization is a core ingredient for effective zero-shot image retrieval and clustering.
The proposed CML framework serves as an efficient regularization technique.
CML improves deep metric learning by explicitly optimizing for robustness and generalization.