AI Paper Atlas

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

Generalized Domain Adaptation

Yu Mitsuzumi, Go Irie, Daiki Ikami, Takashi Shibata

CVPR 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 17 citations (OpenAlex)

Check 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
Use class-destructive self-supervised domain estimation followed by domain-adversarial classifier learningGDA1 · Digits (Avg.)HOS: 80.07 vs 37.46Improved
Use class-destructive self-supervised domain estimation followed by domain-adversarial classifier learningGDA1 · Office-31 (Avg.)HOS: 81.02 vs 64.31Improved
Use class-destructive self-supervised domain estimation followed by domain-adversarial classifier learningGDA2 · Digits (Avg.)HOS: 76.70 vs 51.74Improved
Use class-destructive self-supervised domain estimation followed by domain-adversarial classifier learningGDA2 · Office-31 (Avg.)HOS: 79.49 vs 71.19Improved
Apply the general GDA method rather than an OSDA-specific baselineOffice-31 OSDA · Office-31 (Avg.)HOS: 85.9 vs 85.3Hurt
Apply the general GDA method rather than an OSDA-specific baselineOffice-Home OSDA · Office-Home (Avg.)HOS: 66.2 vs 65.8Hurt
Apply the general GDA method rather than the specialized MS-OSDA baselineOffice-31 MS-OSDA · Office-31 (Avg.)OS*: 93.1 vs 88.3Hurt
Apply the general GDA method rather than the specialized BTDA baselineOffice-31 BTDA · Office-31 (Avg.)accuracy: 80.2 vs 78.8Hurt
Increase the number of grid partitions in the class-destructive image transformation (ablation)GDA domain-label estimation · Digits: sv(0-4), sy(4-7)accuracyHurt
Use more clusters than the true number of domains (ablation)GDA domain-label estimation · Digits: sv(0,1), sy(2,3), mt(4,5), mm(6,7)HOSNo clear effect

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