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

Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

445
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
445
Aggregates Classification01:29

Aggregates Classification

305
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...
305
Classification of Systems-I01:26

Classification of Systems-I

169
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:
169
How Data are Classified: Categorical Data01:11

How Data are Classified: Categorical Data

31.7K
A variable, usually notated by capital letters such as X and Y, is a characteristic or measurement that can be determined for each member of a population. Data are the actual values of variables. They may be numbers, or they may be words. Datum is a single value.
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
31.7K
Classification of Systems-II01:31

Classification of Systems-II

134
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,
134
Classification of Signals01:30

Classification of Signals

403
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...
403

You might also read

Related Articles

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

Sort by
Same author

Unsupervised feature selection via row-sparse local preserving projection.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

A Unified Framework for Pseudo-Supervised Clustering via Weighted Sample Aggregation.

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

Projection with mixed-size anchor graphs.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

SimMTC: Simple Multi-View Tensor Clustering.

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

Unsupervised fine-tuning of vision-language models by fusing classifier tuning and visual prompt tuning.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

IB2MC: Information Bottleneck Inspired Balanced Multiview Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Related Experiment Video

Updated: Jun 7, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.8K

Prototypical classifier with distribution consistency regularization for generalized category discovery: A strong

Zhanxuan Hu1, Yu Duan2, Yaming Zhang1

  • 1School of Information Science and Technology, Yunnan Normal University, Chenggong, Kunming, 650500, Yunnan, China.

Neural Networks : the Official Journal of the International Neural Network Society
|November 21, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces Distribution Consistency Regularization (DCR) to improve prototypical classifiers for Generalized Category Discovery (GCD). DCR enhances semantic understanding by ensuring consistent class distributions, leading to better performance on visual recognition tasks.

Keywords:
ClusteringGeneralized category discoverySemi-supervised learningUnsupervised learning

More Related Videos

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.1K
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

19.9K

Related Experiment Videos

Last Updated: Jun 7, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.8K
Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.1K
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

19.9K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Generalized Category Discovery (GCD) is a challenging semi-supervised visual recognition task.
  • Prototypical classifiers are effective for GCD but often use Softmax-based Cross-Entropy loss (SCE), which struggles with intraclass relationships and causes semantic ambiguity.

Purpose of the Study:

  • To propose Distribution Consistency Regularization (DCR) to enhance prototypical classifiers for GCD.
  • To improve the ability of classifiers to capture local structures and reduce semantic ambiguity in unlabeled data.

Main Methods:

  • Introduced Distribution Consistency Regularization (DCR) as an intraclass consistency loss for prototypical classifiers.
  • Employed partial labels instead of hard pseudo labels to mitigate noisy supervisory signals from unlabeled data.
  • Developed a concise and efficient method requiring no external sophisticated modules.

Main Results:

  • DCR consistently improved performance across six benchmarks.
  • The proposed method achieved competitive or superior results compared to existing approaches.
  • The enhanced model demonstrated better capture of local structures and alleviated semantic ambiguity.

Conclusions:

  • Distribution Consistency Regularization (DCR) is an effective method for improving prototypical classifiers in Generalized Category Discovery (GCD).
  • The approach offers a strong, efficient, and concise baseline for GCD tasks.
  • The use of partial labels further enhances robustness against noisy data.