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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

152
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
152
Classification of Systems-II01:31

Classification of Systems-II

242
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,
242
Classification of Systems-I01:26

Classification of Systems-I

319
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:
319
What is a Mode?01:07

What is a Mode?

19.9K
The mode is one of the commonly used measures of a central tendency. It is defined as the most frequent value in a data set.
There can be more than one mode in a data set if multiple values have the same highest frequency. For instance, suppose that the Statistics exam scores of 20 students are: 50; 53; 59; 59; 63; 63; 72; 72; 72; 72; 72; 76; 78; 81; 83; 84; 84; 84; 90; 93. Here, the mode is 72, as it occurs most frequently, five times.
A data set with two modes is called bimodal. For example,...
19.9K
Classification of Signals01:30

Classification of Signals

915
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...
915
Force Classification01:22

Force Classification

1.7K
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,...
1.7K

You might also read

Related Articles

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

Sort by
Same author

Safe-RTSKF: A Safety-Constrained Recursive Two-Stage Kalman Filter for Robust Sensor State Estimation in Strongly Nonlinear Systems.

Sensors (Basel, Switzerland)·2026
Same author

Atmospheric pressure plasma promotes T lymphocytes activation.

Bioelectrochemistry (Amsterdam, Netherlands)·2026
Same author

An Extended Kalman Filter with Remainder Terms and Correlation Compensation for Nonlinear State Monitoring and Soft Sensing.

Sensors (Basel, Switzerland)·2026
Same author

Does genome size drive the pH-related shifts in bacterial biodiversity within forest soils?

Frontiers in microbiology·2026
Same author

A low-light image enhancement network with attention and cross-branch interaction for real-world low-illumination scenes.

Scientific reports·2026
Same author

Dual-Site Catalytic Interfaces Synergistically Boost Desolvation and Redox Kinetics in Zinc-Ion Batteries.

Advanced materials (Deerfield Beach, Fla.)·2026

Related Experiment Video

Updated: Sep 17, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

692

A new method of semi-supervised learning classification based on multi-mode augmentation in small labeled sample

Yuxuan Liu1, Chenglin Wen2

  • 1School of Automation, Guangdong University of Petrochemical Technology, Maoming, 510006, China.

Scientific Reports
|July 2, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel semi-supervised learning method for image classification. It enhances generalization performance with limited or low-quality unlabeled data using multi-mode augmentation and improved pseudo-labeling.

More Related Videos

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
07:31

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

6.7K
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.1K

Related Experiment Videos

Last Updated: Sep 17, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

692
Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
07:31

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

6.7K
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.1K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Semi-supervised learning (SSL) addresses labeled data scarcity by leveraging unlabeled data.
  • Existing SSL methods often struggle with generalization when unlabeled data is scarce or of poor quality.

Purpose of the Study:

  • To propose a novel semi-supervised image classification method robust to small-scale and low-quality unlabeled data.
  • To enhance the generalization capabilities of semi-supervised learning models under challenging data conditions.

Main Methods:

  • Utilizing uncertainty-based screening (prediction confidence and bias) for high-quality pseudo-label generation.
  • Implementing a multi-modal data augmentation strategy: intra-class random augmentation and inter-class mixed augmentation.
  • Introducing a pseudo-label consistency metric to refine model generalization.

Main Results:

  • The proposed method significantly outperforms existing mainstream methods on STL-10 and CIFAR-10 datasets.
  • Demonstrated superior generalization performance in scenarios with limited unlabeled data and mismatched samples.

Conclusions:

  • The developed multi-mode augmentation approach effectively mitigates the negative impact of insufficient unlabeled data quality and quantity.
  • The method offers a promising solution for robust semi-supervised image classification in practical, data-constrained environments.