Jove
Visualize
Contact Us

Related Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.1K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.1K
Stereotype Content Model02:16

Stereotype Content Model

14.9K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.9K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.4K
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...
6.4K
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
  1. Home
  2. Industrial Image Anomaly Detection Via Synthetic-anomaly Contrastive Distillation.
  1. Home
  2. Industrial Image Anomaly Detection Via Synthetic-anomaly Contrastive Distillation.

Related Experiment Video

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K

Industrial Image Anomaly Detection via Synthetic-Anomaly Contrastive Distillation.

Junxian Li1, Mingxing Li2, Shucheng Huang3

  • 1School of Information Engineering, Yangzhou Polytechnic College, Yangzhou 225009, China.

Sensors (Basel, Switzerland)
|June 27, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a Synthetic-Anomaly Contrastive Distillation (SACD) framework to improve industrial anomaly detection. SACD enhances feature discrimination and decoupling for more accurate identification of defective products in manufacturing.

Keywords:
abnormal synthesisanomaly detectionanomaly localizationfeature refinementknowledge distillation

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

650
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.5K

Related Experiment Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K
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

650
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.5K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Manufacturing Technology

Background:

  • Industrial image anomaly detection is crucial for intelligent manufacturing.
  • Unsupervised methods are preferred but current teacher-student frameworks struggle with structural anomalies and feature decoupling.
  • Existing methods lack sufficient discriminative capability and efficient anomaly feature decoupling.

Purpose of the Study:

  • To propose a novel Synthetic-Anomaly Contrastive Distillation (SACD) framework for industrial anomaly detection.
  • To address limitations in current teacher-student frameworks regarding structural anomalies and feature decoupling.
  • To enhance the accuracy and efficiency of unsupervised anomaly detection in manufacturing.

Main Methods:

  • Introduced a Synthetic-Anomaly Contrastive Distillation (SACD) framework.
  • Employed a reverse distillation (RD) paradigm for hierarchical feature alignment.
  • Utilized feature calibration (FeaCali) modules to refine student network outputs and eliminate anomalous responses.
  • Implemented a dual-branch strategy with defect-free and synthetically corrupted images.
  • Integrated cross-model distillation and intra-model contrastive loss for optimization.
  • Main Results:

    • The SACD framework demonstrated superior performance in industrial anomaly detection.
    • Achieved effective feature alignment and discrepancy amplification.
    • Successfully identified structural anomalies and improved feature decoupling efficiency.
    • Outperformed existing knowledge distillation-based approaches on MVTec AD and BTAD benchmarks.

    Conclusions:

    • The proposed SACD framework effectively enhances industrial anomaly detection capabilities.
    • SACD offers a robust solution for identifying defective products by improving feature discrimination and decoupling.
    • This method represents a significant advancement over current knowledge distillation techniques in unsupervised anomaly detection.