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 Concept Videos

Reducing Line Loss01:18

Reducing Line Loss

141
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
141
Improving Translational Accuracy02:07

Improving Translational Accuracy

2.5K
2.5K
Force Classification01:22

Force Classification

1.1K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.1K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

5.2K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
5.2K
Mean Absolute Deviation01:13

Mean Absolute Deviation

2.6K
The mean absolute deviation is also a measure of the variability of data in a sample. It is the absolute value of the average difference between the data values and the mean.
Let us consider a dataset containing the number of unsold cupcakes in five shops: 10, 15, 8, 7, and 10. Initially, calculate the sample mean. Then calculate the deviation, or the difference, between each data value and the mean. Next, the absolute values of these deviations are added and divided by the sample size to...
2.6K
Regression Toward the Mean01:52

Regression Toward the Mean

6.3K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.3K

You might also read

Related Articles

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

Sort by
Same author

[Prenatal genetic diagnosis and analysis of ten fetuses with Wolf-Hirschhorn syndrome].

Zhonghua yi xue yi chuan xue za zhi = Zhonghua yixue yichuanxue zazhi = Chinese journal of medical genetics·2026
Same author

Network-Texture-Induced Uniform Nucleation: Controllable Preparation and Application of High-Performance CsPbI<sub>3</sub> Nanocrystals in Al<sup>3+</sup>/Gd<sup>3+</sup> Co-Doped Glass.

Inorganic chemistry·2026
Same author

An SMC-domain protein regulates eupyrene spermiogenesis and sperm migration in a cosmopolitan insect, Plutella xylostella.

Journal of insect physiology·2026
Same author

Anomalous luminescence properties in Dy<sup>3+</sup>-doped Bi<sub>2</sub>O<sub>3</sub>-B<sub>2</sub>O<sub>3</sub>-SiO<sub>2</sub> glasses at high silver concentrations.

Applied optics·2026
Same author

Is Coffee Consumption Associated With Increased Risk of Atrial Fibrillation: A Systematic Review and a Meta-Analysis.

Pacing and clinical electrophysiology : PACE·2026
Same author

A Synthetic Data-Augmented Deep Learning Framework for Robust Segmentation and Quantification of the Carotid Artery in Ultrasound Images.

Ultrasound in medicine & biology·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
Same journal

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

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

Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

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

Related Experiment Video

Updated: May 24, 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

451

Global Cross-Entropy Loss for Deep Face Recognition.

Weisong Zhao, Xiangyu Zhu, Haichao Shi

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |March 5, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces Global Cross-Entropy loss (GCE) to improve deep face recognition by enhancing similarity distinctions. The proposed GFace model demonstrates superior performance across multiple benchmarks.

    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

    8.9K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.6K

    Related Experiment Videos

    Last Updated: May 24, 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

    451
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.6K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Biometrics

    Background:

    • Deep face recognition commonly uses Softmax loss, which focuses on sample-class prototype similarities.
    • Softmax loss overlooks the interplay between in-sample and out-sample similarities, potentially limiting model discrimination.
    • Existing methods primarily enhance in-sample target similarity over in-sample non-target similarity.

    Purpose of the Study:

    • To propose a novel loss function, Global Cross-Entropy (GCE), that addresses the limitations of Softmax loss in deep face recognition.
    • To improve the discrimination and generalization capabilities of deep face recognition models.
    • To bridge the gap between training and testing phases in face recognition systems.

    Main Methods:

    • Introduced Global Cross-Entropy (GCE) loss, promoting greater in-sample target similarity over all non-target similarities and smaller in-sample non-target similarity to all target similarities.
    • Implemented a bilateral margin penalty for both in-sample target and non-target similarities to boost model discrimination and generalization.
    • Adapted GCE loss into a pairwise framework by substituting class prototypes with sample features to align training and testing.
    • Developed the GFace model utilizing the proposed GCE loss.

    Main Results:

    • GFace achieved superior performance compared to existing methods on multiple public face recognition benchmarks (LFW, CALFW, CPLFW, CFP-FP, AgeDB, IJB-C, IJB-B, MFR-Ongoing, MegaFace).
    • The proposed GCE loss effectively enhances both discrimination and generalization in deep face models.
    • GFace demonstrated robust performance in general visual recognition tasks beyond face recognition.

    Conclusions:

    • The Global Cross-Entropy loss function offers a significant advancement over traditional Softmax loss for deep face recognition.
    • The GFace model, empowered by GCE, establishes a new state-of-the-art in face recognition accuracy and robustness.
    • The proposed approach shows promise for broader applications in visual recognition tasks.