AI Paper Atlas

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

Domain Generalization by Learning and Removing Domain-specific Features

Yu Ding, Lei Wang, Bin Liang, Shuming Liang, Yang Wang, Fang Chen

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 22 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
Explicitly remove learned domain-specific image features using LRDGPACS (AlexNet) · PACS Avg.accuracy: 76.05 -> 77.33Improved
Explicitly remove learned domain-specific image features using LRDGPACS (ResNet18) · PACS Avg.accuracy: 85.15 -> 85.48Improved
Explicitly remove learned domain-specific image features using LRDGPACS (ResNet50) · PACS Avg.accuracy: 88.10 -> 88.63Improved
Explicitly remove learned domain-specific image features using LRDGVLCS (AlexNet) · VLCS Avg.accuracy: 75.43 -> 75.15Hurt
Explicitly remove learned domain-specific image features using LRDGOffice-Home (ResNet18) · Office-Home Avg.accuracy: 65.50 -> 65.75Improved
Use entropy uncertainty loss instead of least-likely loss (ablation)LRDG domain-specific classifiers · Source-domain classification randomnessclassification randomnessImproved
Map source and target images to remove domain-specific featuresPACS domain pairs · Pairwise source-domain divergenceProxy A-distanceImproved
Map source and target images to remove domain-specific featuresPACS source-target pairs · Closest mixture source-target domain pairsProxy A-distanceImproved

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