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

96
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...
96
Calibration Curves: Linear Least Squares01:20

Calibration Curves: Linear Least Squares

1.2K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
1.2K
Calibration Curves: Correlation Coefficient01:10

Calibration Curves: Correlation Coefficient

1.5K
In a linear calibration curve, there is a value called the calibration coefficient, denoted by 'r,' which measures the strength and the direction of association between two variables. The correlation coefficient value ranges from −1 to +1. A value of +1 indicates a perfect positive linear correlation, −1 denotes a perfect negative correlation, and 0 implies no correlation between the two variables. A positive correlation value establishes that as one variable increases, the...
1.5K
Modeling and Similitude01:12

Modeling and Similitude

245
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
245
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

440
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...
440
Stereotype Content Model02:16

Stereotype Content Model

14.0K
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...
14.0K

You might also read

Related Articles

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

Sort by
Same author

Machine learning modeling to predict HCC locations in cirrhotic patients undergoing MRI - a proof-of-concept study.

Abdominal radiology (New York)·2026
Same author

Imaging foundation model for universal enhancement of non-ideal measurement CT.

Nature communications·2026
Same author

STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC.

Proceedings of machine learning research·2026
Same author

HYPERBOLIC MODEL AGGREGATION FOR FEDERATED LEARNING IN FMRI.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Recent Advancements of Transcranial Direct Current Stimulation and Machine Learning: Methods, Challenges, and Opportunities.

Transactions on artificial intelligence·2026

Related Experiment Video

Updated: Jun 5, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K

Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations.

Chenyu You1, Yifei Min1, Weicheng Dai1

  • 1Yale University.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition
|December 6, 2024
PubMed
Summary

This study introduces a lightweight method to fine-tune CLIP models, reducing reliance on spurious features for better generalization without needing group labels. This approach enhances model robustness for real-world applications.

More Related Videos

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

19.9K
A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.4K

Related Experiment Videos

Last Updated: Jun 5, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

19.9K
A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.4K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Pre-trained vision-language models like CLIP are effective but face challenges with computational cost, specialization, and reliance on spurious features.
  • Spurious features, which correlate with labels but aren't causally related, hinder model generalization and real-world deployment.
  • Existing methods to mitigate spurious features often require identifying these features, lacking definitive assurance for practical use.

Purpose of the Study:

  • To explore methods for mitigating reliance on spurious features in CLIP models without requiring group annotations.
  • To systematically investigate the presence of spurious correlations in CLIP and CLIP with Empirical Risk Minimization (ERM).
  • To propose and validate a lightweight representation calibration method for fine-tuning CLIP.

Main Methods:

  • Verified that last-layer retraining improves group robustness on pre-trained CLIP, following Deep Feature Reweighting (DFR) principles.
  • Developed a novel, lightweight representation calibration method for fine-tuning CLIP.
  • Generated a calibration set using pre-trained CLIP and employed contrastive learning to calibrate sample representations, all without group labels.

Main Results:

  • Demonstrated significant reduction in reliance on spurious features for CLIP models.
  • Achieved substantial improvements in model generalization across various benchmarks.
  • Validated the effectiveness of the proposed representation calibration method through extensive experiments and visualizations.

Conclusions:

  • The proposed lightweight representation calibration method effectively mitigates spurious feature reliance in CLIP.
  • This approach enhances model generalization and robustness, making it more suitable for real-world applications.
  • The method offers a practical solution for fine-tuning vision-language models without the need for costly group annotations.