AI Paper Atlas

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

Domain-Specific Bias Filtering for Single Labeled Domain Generalization

Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Qing Wu, Lanfen Lin

IJCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 26 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 feature extractor debiasing (L_IM and L_CU) and classifier rectification to ERM (ablation)DSBF · PACS SLDGaverage accuracy (%): 61.11 -> 67.12Improved
add feature extractor debiasing (L_IM and L_CU) and classifier rectification to ERM (ablation)DSBF · Office-Home SLDGaverage accuracy (%): 53.62 -> 56.40Improved
add classifier rectification only (no debiasing) (ablation)DSBF · PACS SLDGaverage accuracy (%): 61.11 -> 61.47No clear effect
add L_CU to rectification (ablation)DSBF · PACS SLDGaverage accuracy (%): 61.47 -> 65.34Improved
add L_IM to rectification (ablation)DSBF · PACS SLDGaverage accuracy (%): 61.47 -> 65.75Improved
add classifier rectification losses L_FP and L_BF on top of debiasing (ablation)DSBF · PACS SLDGaverage accuracy (%): 65.99 -> 66.99Improved
add inter-domain attention module (ablation)DSBF · PACS SLDGaverage accuracy (%): 66.99 -> 67.12Improved
add inter-domain attention module (ablation)DSBF · Office-Home SLDGaverage accuracy (%): 55.97 -> 56.40Improved
use clustering pseudo labels instead of direct model predictions (ablation)DSBF · PACS SLDGaverage accuracy (%): 58.28 -> 67.12Improved
increase clustering iterations from 1 to 3 (ablation)DSBF · PACS SLDGaverage accuracy (%): 67.12 -> 67.51No clear effect
increase clustering iterations from 1 to 3 (ablation)DSBF · Office-Home SLDGaverage accuracy (%): 56.40 -> 56.02Hurt
add unlabeled source domains rather than using only labeled source (DSBF vs ERM)DSBF · DomainNet SLDGaverage accuracy (%): 34.45 -> 38.15Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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