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 Experiment Video

Updated: Jan 4, 2026

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

950

Improved Techniques for Adversarial Discriminative Domain Adaptation.

Aaron Chadha, Yiannis Andreopoulos

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 13, 2019
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Generalization, Discrimination, and Extinction01:24

    Generalization, Discrimination, and Extinction

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

    Improving Translational Accuracy

    14.0K
    Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
    14.0K
    Improving Translational Accuracy02:07

    Improving Translational Accuracy

    3.5K
    3.5K

    You might also read

    Related Articles

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

    Sort by
    Same author

    Volumetric lattice Boltzmann method for wall stresses of image-based pulsatile flows.

    Scientific reports·2022
    Same author

    Graph-based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2020
    Same author

    Software designs of image processing tasks with incremental refinement of computation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2010
    Same author

    Comments on "phase-shifting for nonseparable 2-D Haar wavelets".

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2009
    Same author

    Incremental refinement of image salient-point detection.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
    Same author

    Lift mechanics of downhill skiing and snowboarding.

    Medicine and science in sports and exercise·2006

    This study enhances adversarial discriminative domain adaptation (ADDA) for image classification by introducing new loss functions and a novel framework. The improved ADDA framework achieves state-of-the-art performance in unsupervised domain adaptation tasks.

    Area of Science:

    • Computer Science
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Unsupervised domain adaptation (UDA) is crucial for leveraging labeled source data with unlabeled target data in machine learning.
    • Adversarial Discriminative Domain Adaptation (ADDA) is an efficient UDA framework for image classification, but its performance can be further improved.
    • Existing adversarial methods often lack efficiency or competitive accuracy in UDA tasks.

    Purpose of the Study:

    • To enhance the performance of ADDA by proposing a new framework and novel loss formulations for unsupervised domain adaptation.
    • To model the joint distribution over domain and task by extending the discriminator output over source classes.
    • To align target encoder distributions with the source domain using Maximum Mean Discrepancy (MMD) and reconstruction-based losses.

    Related Experiment Videos

    Last Updated: Jan 4, 2026

    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

    950

    Main Methods:

    • Extended ADDA framework using semi-supervised Generative Adversarial Networks (GANs) to model joint domain and task distributions.
    • Proposed Maximum Mean Discrepancy (MMD) and reconstruction-based loss functions for aligning target encoder distributions.
    • Introduced regularization techniques, including denoising autoencoder for the discriminator and source example regularization for the target encoder, to stabilize training and reduce overfitting.

    Main Results:

    • The proposed framework and loss formulations demonstrated competitive or superior performance compared to state-of-the-art UDA methods like DIFA and MCDDA across various datasets (MNIST, USPS, SVHN, MNIST-M, Office-31).
    • Achieved lower complexity than other recent adversarial methods while maintaining high performance.
    • Successfully applied and validated the framework on a challenging neuromorphic vision sensing (NVS) sign language recognition dataset, demonstrating its effectiveness in data-scarce sensing modalities.

    Conclusions:

    • The enhanced ADDA framework offers a simple yet efficient approach to unsupervised domain adaptation.
    • The novel loss functions and regularization techniques effectively improve performance and stability in UDA tasks.
    • The framework shows significant promise for real-world applications, particularly in domains with limited labeled data, such as neuromorphic sensing.