Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Class-Sensitive TPB-Guided Memory Refinement for Online Zero-Shot Anomaly Detection.

Zhen Zhao¹, Fan Song², Xinyun Wang²

¹School of Intelligent Manufacturing, Zhejiang Polytechnic University of Mechanical and Electrical Engineering, Hangzhou 310053, China.

Sensors (Basel, Switzerland)

|June 12, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

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...

You might also read

Related Articles

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

Sort by

Same author

Clinical features, outcome and HLA subtypes in Eastern patients with anti-IgLON5 disease: a multicenter study.

Orphanet journal of rare diseases·2026

Same author

Predictive value of N-terminal Pro-brain Natriuretic Peptide combined with High-sensitivity Troponin-I for progression to high-risk status in acute pulmonary embolism.

Cardiology·2026

Same author

Analysis of factors associated with severity categories of fall-related injuries among inpatients at a tertiary grade A hospital in Zhejiang province from 2015 to 2025: a retrospective observational study.

BMJ open·2026

Same author

Measuring health-related quality of life in sepsis survivors and caregivers: a mapping review and a preliminary conceptual framework.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2026

Same author

160 W direct-emission LG<sub>01</sub> vortex beam from a thin-disk laser by synergistic thermal and loss management.

Optics letters·2026

Same author

Ferroptosis in Septic Cardiomyopathy Is Alleviated by Ondansetron: The Critical Role of the HTR3A-ATF3 Axis in Mitochondrial and Oxidative Homeostasis.

Biomedicines·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

TSMR enhances zero-shot anomaly detection by selectively updating memory, improving reliability for industrial inspection without needing target-domain data. This method boosts performance on challenging datasets like VisA.

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Zero-shot anomaly detection is crucial for industrial inspection, especially for new products lacking training data.
CLIP-based methods offer generalization, and online memory improves adaptability but risks incorporating unreliable data.
Existing methods struggle with weak or unstable visual categories due to memory update issues.

Purpose of the Study:

To propose TSMR, a lightweight extension of RareCLIP for reliable online zero-shot anomaly detection.
To enhance test-time memory evolution through a class-sensitive selective update strategy.
To improve anomaly detection performance without altering the backbone or scoring pipeline.

Main Methods:

TSMR employs a class-sensitive selective update strategy for test-time memory evolution.

Keywords:

CLIP online memory refinement test-time adaptation vision–language models zero-shot anomaly detection

Related Experiment Videos

Key components include a confidence quantile gate, text-prior reliability check, and weak-class selective activation.

A frame-level memory-update decision is made during online inference.

Main Results:

TSMR significantly improves performance on the VisA dataset across image-level AUROC, pixel-level AUROC, and PRO metrics.
It maintains competitive results on the MVTec AD dataset.
Selective memory refinement proves especially beneficial for weak categories and is stable across different evaluation orders.

Conclusions:

Reliable online memory evolution is an effective strategy for CLIP-based zero-shot anomaly detection.
TSMR offers a robust approach to handling unreliable or ambiguous evidence in online updates.
The proposed method enhances adaptability and performance in industrial inspection scenarios.