AI Paper Atlas

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

Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation

Ruijia Xu, Guanbin Li, Jihan Yang, Liang Lin

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 548 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 stepwise feature norm enlargement (SAFN) instead of hard norm target (HAFN)AFN · Office-Home (vanilla)accuracy (%): 65.4 -> 67.3Improved
use SAFN instead of HAFNAFN · VisDA2017 (vanilla)per-class accuracy (%): 73.9 -> 76.1Improved
use SAFN instead of HAFNAFN · Office-31accuracy (%): 83.9 -> 85.7Improved
use SAFN instead of HAFNAFN · Office-Home (partial)accuracy (%): 67.51 -> 71.83Improved
add entropy minimization (ENT) to SAFN (ablation)SAFN · ImageCLEF-DAaccuracy (%): 88.1 -> 88.9Improved
add entropy minimization (ENT) to SAFN (ablation)SAFN · Office-31accuracy (%): 85.7 -> 87.1Improved
increase unlabeled target data from 25% to 100% (ablation)SAFN · VisDA2017target accuracyImproved
increase feature-norm limit R beyond optimum (ablation)HAFN · VisDA2017 and Office-31 A to WaccuracyMixed
vary step size delta r (0.2-0.5 on VisDA, 0.5-2.0 on A to W) (ablation)SAFN · VisDA2017 and Office-31 A to WaccuracyNo clear effect
vary embedding size from 500 to 2000 (ablation)SAFN · VisDA2017 and Office-31 A to WaccuracyNo clear effect
use SAFN instead of adversarial DANN under partial settingSAFN · Office-Home (partial)accuracy (%): 47.39 -> 71.83Improved
use SAFN instead of best baseline on robustness metricsSAFN · Ar to Rw (5%) partialPNG (lower is better): SAFN -9.6 vs DAN -0.8 and DANN 4.7Improved

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