AI Paper Atlas

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

Active Universal Domain Adaptation

Xinhong Ma, Junyu Gao, Changsheng Xu

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 32 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 adversarial curriculum loss Ladv (instead of naive adversarial loss) (ablation)AUAN · Office-Home (6 challenging tasks)avg class accuracy: 56.57 -> 58.91Improved
add diverse curriculum loss Ldiv (ablation)AUAN · Office-Home (6 challenging tasks)avg class accuracy: 49.61 -> 58.91Improved
add prototype classification loss Lp (ablation)AUAN · Office-Home (6 challenging tasks)avg class accuracy: 55.71 -> 58.91Improved
add self-supervised cluster loss Lnc (ablation)AUAN · Office-Home (6 challenging tasks)avg class accuracy: 56.95 -> 58.91Improved
use labeled target data DLT during adaptation (ablation)AUAN · Office-Home (6 challenging tasks)avg class accuracy: 54.70 -> 58.91Improved
use pseudo-labeled DPLT when learning Gp (ablation)AUAN · Office-Home (6 challenging tasks)avg class accuracy: 57.67 -> 58.91Improved
use ADCL instead of UAN as domain adaptation methodactive learning pipeline · Office-Home (avg over 4 AL strategies)avg class accuracy: 32.95 -> 47.33Improved
use ADCL instead of UANactive learning pipeline · Office-31 (avg over 4 AL strategies)avg class accuracy: 63.13 -> 79.75Improved
use CNTGE instead of BADGE active learningADCL · VisDA S->R (15th round)avg class accuracy: 64.00 -> 73.91Improved
use CNTGE instead of BADGE active learningADCL · Office-31 (avg, 15th round)avg class accuracy: 80.51 -> 81.18Improved
use Coreset instead of CNTGE active learningADCL · Office-31 (avg, 15th round)avg class accuracy: 81.18 vs 80.79No clear effect
use Entropy instead of Random active learningADCL · VisDA S->R (15th round)avg class accuracy: 63.15 -> 60.06Hurt

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