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 Videos

Progressive Hybrid Pseudo-Labeling for Unsupervised Domain Adaptation With Ascending Low-Rank Adaptation.

Yangtao Wang, Mingxin Huang, Xingwei Deng

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |July 9, 2026
    PubMed
    Summary

    This study introduces Progressive Hybrid Pseudo-Labeling with Ascending Low-Rank Adaptation (PHPL) for unsupervised domain adaptation (UDA) using vision-language models (VLMs). PHPL effectively reduces noisy pseudo-labels and improves adaptation efficiency, especially under large domain shifts.

    Related Concept Videos

    Improving Translational Accuracy02:07

    Improving Translational Accuracy

    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...
    Improving Translational Accuracy02:07

    Improving Translational Accuracy

    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...

    You might also read

    Related Articles

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

    Sort by
    Same author

    Achieving near-theoretical strength and high elasticity in micrometer scale TiB<sub>2</sub> ceramics.

    Nature communications·2026
    Same author

    Complete genome sequence of <i>Dehalococcoides mccartyi</i> strain Y2, a tetrachloroethene-dechlorinating anaerobe isolated from river sediment.

    Microbiology resource announcements·2026
    Same author

    Impact of liposomal bupivacaine parasternal block combined with rectus sheath block on postoperative pain in patients undergoing sternotomy for cardiac surgery: a randomized controlled trial.

    BMC anesthesiology·2026
    Same author

    Resolving intrinsic dislocation structure in perovskite crystals using pulsed electron beam with atomic resolution.

    Nature communications·2026
    Same author

    Fermi-level depinning achieved by high-work-function Au<sub>1-x</sub>Se<sub>x</sub> alloy contacts for high-performance p-type WSe<sub>2</sub> transistors.

    Nature communications·2026
    Same author

    Multi-omics Mendelian randomization integrating metabolism, microbiome and immunity supports a putative gut-immune-pelvic pathway in deep infiltrating endometriosis.

    Frontiers in endocrinology·2026

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Unsupervised domain adaptation (UDA) using large vision-language models (VLMs) shows promise but struggles with noisy pseudo-labels and inefficient adaptation.
    • Large domain shifts pose significant challenges to the generalization ability of current UDA methods.

    Purpose of the Study:

    • To propose a novel parameter-efficient paradigm, Progressive Hybrid Pseudo-Labeling with Ascending Low-Rank Adaptation (PHPL), for UDA.
    • To address the challenges of noisy pseudo-labels and inefficient adaptation in large VLMs under significant domain shifts.

    Main Methods:

    • Introduced a progressive hybrid pseudo-labeling strategy with a teacher-student model and a weighting scheme to mitigate label noise.
    • Developed an ascending low-rank adaptation (LoRA) strategy that allocates capacity depth-wise for efficient VLM adaptation.

    Related Experiment Videos

  • Implemented a progressive weighting scheme to transfer predictive responsibility from teacher to student, stabilizing self-training.

    • Main Results:

    • PHPL achieved superior performance across five UDA benchmarks (Office-Home, Office-31, VisDA-2017, Mini-DomainNet, DomainNet).
    • Demonstrated strong robustness and effectiveness on large-scale, challenging domain shift scenarios.
    • Showcased significant reductions in computational overhead compared to existing solutions.

    Conclusions:

    • PHPL offers an effective and scalable lightweight adaptation paradigm for UDA with VLMs.
    • The proposed methods successfully mitigate pseudo-label noise and enhance adaptation efficiency.
    • PHPL represents a significant advancement in parameter-efficient UDA for large models.