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 Video

Updated: Apr 26, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Unsupervised Domain Adaptation-Based Cross-Type Deepfake Image Detection.

Qin Wang, Xiaofeng Wang, Zinian Liu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|April 24, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Adipocyte-specific ablation of Gadd45b exacerbates obesity-associated cellular senescence and metabolic disorders via Fgf1b promoter hypermethylation.

Cell death and differentiation·2026

Same author

IDH3A Deficiency Compromises Adaptive Thermogenesis and Exacerbates Obesity-Induced Metabolic Dysfunction via Impaired BCKDHA-Dependent BCAA Catabolism.

Diabetes·2026

Same author

Surgical treatment of hourglass-like nerve constrictions with allogeneic nerve: a series report of 4 cases.

Journal of hand and microsurgery·2026

Same author

Wine-Processed Cornus officinalis Ameliorates Osteoarthritis via Modulating M1/M2 Macrophage Polarization.

Journal of cellular and molecular medicine·2026

Same author

Molecular Mechanisms Underlying the Anti-Tumor Activity of Lotus-Derived Alkaloids in Breast Cancer.

Molecules (Basel, Switzerland)·2026

Same author

Iontronic tip-sensing guidewires.

Nature biomedical engineering·2025

Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

Same journal

Semantic Frame Interpolation.

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

Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

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

Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

See all related articles

This study introduces a new deepfake detection method using unsupervised domain adaptation for extra-type cross-domain scenarios. The DTA-DFA model significantly improves detecting deepfakes across different data types and sample sizes.

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Deepfake face image detection faces challenges with numerous unlabeled samples in practical applications.
Domain adaptation techniques are crucial for leveraging labeled data to identify unlabeled deepfakes across different domains.
Existing methods predominantly address intra-type cross-domain scenarios, leaving a gap in extra-type detection.

Purpose of the Study:

To propose an unsupervised domain adaptation method for deepfake face image detection in extra-type cross-domain settings.
To develop a novel domain adaptation model, DTA-DFA, enhancing cross-domain detection capabilities.
To address the challenge of detecting deepfakes when source and target domains have different characteristics.

Main Methods:

Related Experiment Videos

Last Updated: Apr 26, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Developed a domain adaptation model named DTA-DFA, integrating Domain Tag Adversarial (DTA) and Domain Feature Alignment (DFA) algorithms.
DTA algorithm weakens domain-specific features, while DFA aligns feature distributions between source and target domains.
Employed an unsupervised learning approach for domain adaptation in deepfake detection.

Main Results:

The proposed DTA-DFA method significantly enhances deepfake detection performance in extra-type cross-domain scenarios compared to existing methods.
Demonstrated strong cross-domain capability by successfully detecting deepfakes from large-shot to few-shot labeled samples.
Experimental results validate the model's effectiveness in generalizing across diverse and dissimilar datasets.

Conclusions:

The DTA-DFA model offers a powerful solution for unsupervised deepfake detection in challenging extra-type cross-domain scenarios.
The method shows significant promise for real-world applications where labeled data is scarce or domains differ substantially.
This research advances the field of domain adaptation for robust and generalized deepfake identification.