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

Source Transformation01:15

Source Transformation

9.9K
Source transformation is a fundamental technique employed in circuit analysis, offering a valuable tool for simplifying complex electrical circuits. This technique involves the replacement of either a voltage source in series with a resistor by a current source in parallel with a resistor, or vice versa. The key concept here is that when the original sources are deactivated (turned off), the equivalent resistance at the circuit's end terminals remains the same.
It is essential to note that when...
9.9K
Conservation of Protein Domains Over Different Proteins02:26

Conservation of Protein Domains Over Different Proteins

11.5K
Protein domains are small structurally independent units that are part of a single amino acid chain.  Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
11.5K
Associative Learning01:27

Associative Learning

609
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
609
Self-Discrepancy Theory02:45

Self-Discrepancy Theory

18.5K
One influential perspective on what motivates people's behavior is detailed in Tory Higgin's self-discrepancy theory (Higgins, 1987). He proposed that people hold disagreeing internal representations of themselves that lead to different emotional states.  
18.5K
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
Introduction to Learning01:18

Introduction to Learning

555
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
555

You might also read

Related Articles

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

Sort by
Same author

Tumor stroma Siglec15 expression is a poor prognosis predictor in colon adenocarcinoma.

Journal of Cancer·2023
Same author

Capecitabine maintenance therapy in metastatic colorectal cancer patients with no evidence of disease: CAMCO trial.

Future oncology (London, England)·2023
Same author

Effectiveness of an online/offline mixed-mode Tai Chi cardiac rehabilitation program on microcirculation in patients with coronary artery disease: A randomized controlled study.

Clinical hemorheology and microcirculation·2023
Same author

Adverse effects of exposure to fine particles and ultrafine particles in the environment on different organs of organisms.

Journal of environmental sciences (China)·2023
Same author

Bipedicular percutaneous kyphoplasty versus unipedicular percutaneous kyphoplasty in the treatment of asymmetric osteoporotic vertebral compression fractures: a case control study.

BMC surgery·2023
Same author

Multimodality Driven Impedance-Based Sim2Real Transfer Learning for Robotic Multiple Peg-in-Hole Assembly.

IEEE transactions on cybernetics·2023

Related Experiment Video

Updated: Sep 21, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

694

Semantic consistency learning on manifold for source data-free unsupervised domain adaptation.

Song Tang1, Yan Zou2, Zihao Song2

  • 1Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology, Shanghai 200093, China; Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg D-22527, Germany; University of Electronic Science and Technology of China, Chengdu 611731, China.

Neural Networks : the Official Journal of the International Neural Network Society
|May 31, 2022
PubMed
Summary

This study introduces Semantic Consistency Learning on Manifold (SCLM), a novel approach for source data-free unsupervised domain adaptation (SFUDA). SCLM effectively captures target data geometry on manifolds, improving domain adaptation performance.

Keywords:
ManifoldSelf-supervised learningSemantic consistencyUnsupervised domain adaptation

More Related Videos

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

2.6K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Related Experiment Videos

Last Updated: Sep 21, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

694
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

2.6K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Source data-free unsupervised domain adaptation (SFUDA) is a growing research area.
  • Existing methods utilize target data geometry but are limited by Euclidean space assumptions.
  • Manifold geometry is crucial for capturing complex semantic relationships in target data.

Purpose of the Study:

  • To propose a novel SFUDA method, Semantic Consistency Learning on Manifold (SCLM).
  • To address limitations of Euclidean geometry in capturing target data manifold structures.
  • To enhance semantic understanding and consistency for improved domain adaptation.

Main Methods:

  • Developed EntMomClustering, an enhanced k-means method fusing entropy momentum for pseudo-label generation.
  • Constructed Semantic Neighbor Topology (SNT) using collaborative representation-based manifold projection and similarity comparison.
  • Implemented semantic consistency learning on SNT for deep clustering, incorporating entropy and self-supervised regulators.

Main Results:

  • SCLM demonstrates superior performance in capturing complete geometric information on manifolds.
  • The method effectively utilizes SNT as a basic clustering unit for deep clustering.
  • Achieved state-of-the-art results on three benchmark datasets.

Conclusions:

  • SCLM offers a significant advancement in SFUDA by leveraging manifold geometry.
  • The proposed method provides a robust framework for semantic consistency learning.
  • The findings suggest SCLM's potential for various domain adaptation applications.