AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Causal Balancing for Domain Generalization

Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 4 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
Use balanced mini-batch sampling with CORALCORAL · DomainBed averageaccuracy: 67.5 -> 69.7Improved
Use balanced mini-batch sampling with CORALCORAL · ColoredMNISTaccuracy: 51.5 -> 66.6Improved
Use balanced mini-batch sampling with ERMERM · ColoredMNISTaccuracy: 51.5 -> 60.1Improved
Use balanced mini-batch sampling with IRMIRM · ColoredMNISTaccuracy: 52.0 -> 59.2Improved
Use balanced mini-batch sampling with GroupDROGroupDRO · ColoredMNISTaccuracy: 52.1 -> 53.9Improved
Use balanced mini-batch sampling with ERMERM · RotatedMNISTaccuracy: 98.0 -> 97.7Hurt
Use balanced mini-batch sampling with IRMIRM · VLCSaccuracy: 78.5 -> 76.5Hurt
Use balanced mini-batch sampling with CORALCORAL · PACSaccuracy: 86.2 -> 86.7Improved
Use balanced mini-batch sampling with CORALCORAL · Office-Homeaccuracy: 68.7 -> 69.6Improved
Use balanced mini-batch sampling with ERMERM · TerraIncognitaaccuracy: 46.1 -> 48.0Improved
Use balanced mini-batch sampling with CORALCORAL · DomainNetaccuracy: 41.5 -> 43.9Improved
Increase the fraction of balanced examples in a mini-batch (ablation)ERM with oracle color matching · ColoredMNIST¹⁰accuracyImproved

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