AI Paper Atlas

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

Domain Generalization without Excess Empirical Risk

Ozan Sener, Vladlen Koltun

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 3 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
Apply SDG instead of standard optimization to CORALCORAL · iWildCamMacro-F1: 32.8 \pm 0.1 -> 34.6 \pm 1.2Improved
Apply SDG instead of standard optimization to CORALCORAL · Camelyon17Avg Acc: 59.5 \pm 7.7 -> 75.2 \pm 4.4Improved
Apply SDG instead of standard optimization to CORALCORAL · OGB-MolPCBAAP: 17.9 \pm 0.5 -> 25.8 \pm 0.1Improved
Apply SDG instead of standard optimization to CORALCORAL · FMoWWorstR Acc: 31.0 \pm 0.4 -> 33.9 \pm 0.9Improved
Apply SDG instead of standard optimization to CORALCORAL · Amazon10th-tile Acc: 52.9 \pm 0.8 -> 53.7 \pm 0.6Improved
Apply SDG instead of standard optimization to CORALCORAL · py150MethodClass: 65.9 \pm 0.1 -> 68.3 \pm 0.1Improved
Apply SDG instead of standard optimization to CORALCORAL · PovertyMapWstPearsonR: 0.44 \pm 0.06 -> 0.49 \pm 0.05Improved
Apply SDG to FISHFISH · iWildCamMacro-F1: 22.0 \pm 1.8 -> 32.9 \pm 0.2Improved
Apply SDG to FISHFISH · Camelyon17Avg Acc: 74.7 \pm 7.1 -> 76.2 \pm 8.4Improved
Apply SDG to FISHFISH · OGB-MolPCBAAP: 22.6 \pm 0.3 -> 26.1 \pm 0.5Improved
Apply SDG to FISHFISH · FMoWWorstR Acc: 34.6 \pm 0.2 -> 34.6 \pm 0.3No clear effect
Apply SDG to FISHFISH · PovertyMapWstPearsonR: 0.35 \pm 0.03 -> 0.46 \pm 0.03Improved

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