AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Domain-Shared Group-Sparse Dictionary Learning for Unsupervised Domain Adaptation

Baoyao Yang, Andy Ma, Pong Yuen

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 14 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add target-specific information (graph label propagation with target features) to the classifier (ablation)DsGsDLNT · Office+Caltech (DeCAF6) averageaccuracy (%): 90.29 -> 92.38Improved
add target-specific information (ablation)DsGsDLNT · CMU-PIE source illumination, target blur sigma=3accuracy (%): 86.47 -> 88.82Improved
add target-specific information (ablation)DsGsDLNT · CMU-PIE source illumination, target motion blur L=11accuracy (%): 77.74 -> 80.29Improved
add target-specific information (ablation)DsGsDLNT · CMU-PIE source blur, target illuminationaccuracy (%): 98.04 -> 98.82Improved
apply domain-shared group-sparse dictionary learning (without target-specific info) instead of source-only SVM (ablation)SVM classifier · Office+Caltech (DeCAF6) averageaccuracy (%): 84.73 -> 90.29Improved
estimate/align conditional distributions via label estimation or source selection (JDA, TJM) rather than nonedomain adaptation on CMU-PIE · CMU-PIE face recognitionaccuracy (%): TJM 59.71 vs SVMScr 73.82 (sigma=3)Mixed
use domain-shared group-sparse alignment instead of JDAdomain adaptation · Office+Caltech (DeCAF6) averageaccuracy (%): 85.45 -> 92.38Improved
use DsGsDL instead of deep DA methodsdomain adaptation · Office+Caltech averageaccuracy (%): 91.18 -> 92.38Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy