AI Paper Atlas

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

Combating Label Distribution Shift for Active Domain Adaptation

Sehyun Hwang, Sohyun Lee, Sungyeon Kim, Jungseul Ok, Suha Kwak

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 25 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 MMD prototype sampling instead of random sampling (ablation)DANN · OfficeHomeaccuracy (%): 73.3 -> 77.1Improved
add label distribution matching (ablation)LAMDA (prototype, linear) · OfficeHome-RSUTaccuracy (%): 67.3 -> 74.1Improved
add label distribution matching (ablation)LAMDA (prototype, linear) · OfficeHomeaccuracy (%): 77.1 -> 79.8Improved
add cosine classifier (ablation)LAMDA · OfficeHomeaccuracy (%): 79.8 -> 81.9Improved
add cosine classifier (ablation)LAMDA · OfficeHome-RSUTaccuracy (%): 74.1 -> 75.8Improved
add cosine classifier (ablation)LAMDA · VisDA-2017accuracy (%): 92.3 -> 91.8Hurt
add cosine classifier (ablation)LAMDA · DomainNetaccuracy (%): 57.1 -> 57.0No clear effect
add uncertainty-based labeling of hard prototypes only (ablation)LAMDA sampling · OfficeHomeaccuracy (%): 77.9 -> 80.3Improved
use pseudo-labeled prototypes in label distribution estimation (ablation)LAMDA sampling · OfficeHomeaccuracy (%): 80.3 -> 82.0Improved
add MMD density-aware sampling instead of random (ablation)DANN · OfficeHomeaccuracy (%): 73.3 -> 77.9Improved
use pseudo labels (Delta below 1) instead of Delta = 1 (ablation)LAMDA · OfficeHome and OfficeHome-RSUTaccuracy (%): drops 4% and 1.1%Improved
use LAMDA sampling instead of CLUE under MCCMCC · OfficeHomeaccuracy (%): 83.2 -> 84.2Improved

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