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

Classification of Systems-I01:26

Classification of Systems-I

225
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
225
Aggregates Classification01:29

Aggregates Classification

354
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
354
Classification of Systems-II01:31

Classification of Systems-II

186
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
186
Classification of Signals01:30

Classification of Signals

566
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
566
Associative Learning01:27

Associative Learning

469
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
469
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.5K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.5K

You might also read

Related Articles

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

Sort by
Same author

Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs.

Diagnostics (Basel, Switzerland)·2026
Same author

ReHeartNet: Reconstruct Electrocardiogram From Photoplethysmography by Using Dense Connected Deep Learning Model.

IEEE open journal of engineering in medicine and biology·2026
Same author

Using Class and Domain Information to Address Domain Shift in Federated Learning.

IEEE transactions on neural networks and learning systems·2026
Same author

NLSTseg: A Pixel-level Lung Cancer Dataset Based on NLST LDCT Images.

Scientific data·2025
Same author

Build an Open Standard Comprehensive Cancer Cohort Research Database.

Studies in health technology and informatics·2025
Same author

Cross-Scale Guidance Integration Transformer for Instance Segmentation in Pathology Images.

IEEE open journal of engineering in medicine and biology·2025

Related Experiment Video

Updated: Jul 30, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

457

ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class

Chien-Yu Chiou, Kuang-Ting Lee, Chun-Rong Huang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |May 12, 2023
    PubMed
    Summary

    This study introduces ADMM-SRNet, a novel deep learning approach for one-class classification that overcomes feature collapse using heterogeneous contrastive features and sparse dictionaries. The method effectively learns discriminative models from in-class data alone.

    More Related Videos

    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

    591
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

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

    Published on: February 15, 2017

    7.0K

    Related Experiment Videos

    Last Updated: Jul 30, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    457
    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

    591
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

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

    Published on: February 15, 2017

    7.0K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • One-class classification trains models using only in-class samples, posing challenges for conventional deep learning due to the lack of out-of-class data.
    • Feature collapse is a common issue in deep learning for one-class classification when only in-class samples are available.
    • Existing contrastive learning methods can learn from in-class data but are difficult to integrate end-to-end with one-class models.

    Purpose of the Study:

    • To propose a novel deep learning framework, ADMM-SRNet, that addresses the limitations of existing one-class classification methods.
    • To enable end-to-end training of one-class models by effectively learning discriminative features from in-class samples.
    • To improve the performance of one-class classification by combining heterogeneous contrastive learning with sparse representation.

    Main Methods:

    • Developed the Alternating Direction Method of Multipliers based Sparse Representation Network (ADMM-SRNet).
    • Introduced a Heterogeneous Contrastive Feature (HCF) network utilizing contrastive learning with diverse data augmentations.
    • Incorporated a Sparse Dictionary (SD) network that models in-class sample distributions using ADMM-computed dictionaries.
    • Coupled the HCF and SD networks with novel loss functions for end-to-end training.

    Main Results:

    • The proposed ADMM-SRNet effectively learns discriminative features and robust one-class models.
    • The method demonstrates superior performance compared to state-of-the-art techniques on benchmark datasets (CIFAR-10, CIFAR-100, ImageNet-30).
    • Achieved significant improvements in one-class classification tasks by mitigating feature collapse and enhancing feature representation.

    Conclusions:

    • ADMM-SRNet provides an effective end-to-end trainable solution for one-class classification problems.
    • The integration of heterogeneous contrastive learning and sparse representation offers a powerful approach for learning from limited data.
    • The proposed method advances the field of one-class classification, offering a promising direction for future research and applications.