AI Paper Atlas

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

Graphical Modeling for Multi-Source Domain Adaptation

Minghao Xu, Hang Wang, Bingbing Ni

TPAMI 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 33 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 global alignment loss L_global (ablation)CRF-MSDA · Digits-five avgaccuracy: 86.90 -> 90.57Improved
add local alignment loss L_local (ablation)CRF-MSDA · Digits-five avgaccuracy: 86.90 -> 89.02Improved
add both L_global and L_local (ablation)CRF-MSDA · Digits-five avgaccuracy: 86.90 -> 91.83Improved
add MLE-based loss L_MLE to classification loss (ablation)MRF-MSDA · Digits-five avgaccuracy: 91.93 -> 93.74Improved
add classification loss L_cls to MLE loss (ablation)MRF-MSDA · Digits-five avgaccuracy: 91.11 -> 93.74Improved
use MRF-MSDA instead of CRF-MSDAMSDA graphical model · Digits-five avgaccuracy: 91.8 -> 93.7Improved
use MRF-MSDA instead of CRF-MSDAMSDA graphical model · PACS avgaccuracy: 89.9 -> 92.6Improved
use MRF-MSDA instead of CRF-MSDAMSDA graphical model · Office-31 avgaccuracy: 84.6 -> 84.7No clear effect
use MRF-MSDA instead of CRF-MSDAMSDA graphical model · DomainNet avgaccuracy: 47.4 -> 47.9No clear effect
use MRF-MSDA instead of CRF-MSDA for training speedMSDA graphical model · Digits-five training time (100 iterations)training time (s): 17.41 -> 16.54Improved
raise temperature tau to 0.4 from 0.1 (ablation)MRF-MSDA · Digits-five ->mmaccuracy: nearly 15% decrease at tau = 0.4Hurt
make adjacency too dense or sparse (sigma > 0.05 or < 0.0005 vs 0.005) (ablation)CRF-MSDA · Digits-fiveaccuracy: best at sigma around 0.005Hurt

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