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

Force Classification01:22

Force Classification

1.3K
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,...
1.3K
Improving Translational Accuracy02:07

Improving Translational Accuracy

2.6K
2.6K
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

678
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...
678
Observational Learning01:12

Observational Learning

250
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
250
Aggregates Classification01:29

Aggregates Classification

354
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
354
Classification of Systems-I01:26

Classification of Systems-I

225
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:
225

You might also read

Related Articles

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

Sort by
Same author

Weapon operating pose detection and suspicious human activity classification using skeleton graphs.

Mathematical biosciences and engineering : MBE·2023
Same author

A systematic literature review and existing challenges toward fake news detection models.

Social network analysis and mining·2022
Same author

An amalgamation of YOLOv4 and XGBoost for next-gen smart traffic management system.

PeerJ. Computer science·2021
Same author

COVID-19 pulmonary consolidations detection in chest X-ray using progressive resizing and transfer learning techniques.

Heliyon·2021
Same author

Improvement of deep cross-modal retrieval by generating real-valued representation.

PeerJ. Computer science·2021
Same author

Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing.

PeerJ. Computer science·2021

Related Experiment Video

Updated: Jul 30, 2025

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

591

Unsupervised Domain Adaptation for Image Classification and Object Detection Using Guided Transfer Learning Approach

Parth Goel1,2, Amit Ganatra3,4

  • 1Computer Science & Engineering Department, Devang Patel Institute of Advance Technology and Research (DEPSTAR), Faculty of Technology & Engineering, Charotar University of Science and Technology (CHARUSAT), Changa 388421, Anand, India.

Sensors (Basel, Switzerland)
|May 13, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an efficient unsupervised domain adaptation network to improve deep learning models. The approach enhances feature transferability and minimizes domain shift for better image classification and object detection performance.

Keywords:
convolutional neural networkdeep learningdomain adaptationimage classificationobject detectiontransfer learning

More Related Videos

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.3K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

Related Experiment Videos

Last Updated: Jul 30, 2025

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

591
Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.3K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Unsupervised Domain Adaptation (UDA) is crucial for transfer learning, aiming to bridge distribution gaps between labeled source and unlabeled target domains.
  • Domain shift, caused by variations in data, hinders direct application of source-trained models to target domains, impacting generalization.
  • Existing UDA methods often assume identical categories and may not optimally adapt models when domain similarity varies.

Purpose of the Study:

  • To develop an efficient unsupervised domain adaptation network for image classification and object detection.
  • To learn transferable feature representations and mitigate domain shift within a unified framework.
  • To enhance model generalization across different domains without requiring target domain labels.

Main Methods:

  • Proposed a guided transfer learning approach to intelligently select layers for model fine-tuning, improving feature transferability.
  • Utilized Jensen-Shannon Divergence (JS-Divergence) to effectively minimize domain discrepancy between source and target datasets.
  • Developed a unified network architecture capable of addressing both image classification and object detection tasks.

Main Results:

  • Achieved 93.2% accuracy on the Office-31 and 75.3% accuracy on the Office-Home datasets for domain adaptive image classification.
  • Obtained 51.1% mAP on Foggy Cityscapes and 72.7% mAP on the Indian Vehicle dataset for domain adaptive object detection.
  • Demonstrated significant performance improvements over existing methods through extensive experiments and ablation studies.

Conclusions:

  • The proposed unsupervised domain adaptation network effectively reduces domain shift and enhances feature transferability.
  • The guided transfer learning and JS-Divergence minimization strategies prove efficient and effective for UDA tasks.
  • The unified approach shows superior performance in both image classification and object detection benchmarks, outperforming prior work.