AI Paper Atlas

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

Geometric Rate–Distortion Invariance for Domain Generalization

Tong Liu, Sen Liang, Shuo Bai

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization

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 geometric distortion term (ablation)RDI · PACSaverage accuracy: 86.4 -> 87.4Improved
add aggregated rate term (ablation)RDI · PACSaverage accuracy: 86.5 -> 87.4Improved
add geometric projection head alone to ERM (ablation)ERM · PACSaverage accuracy: 80.0 -> 82.6Improved
add rate-distortion objectives on top of projection head (ablation)ERM+g · PACSaverage accuracy: 82.6 -> 87.4Improved
add both RDI losses to ERM+g (ablation)ERM+g · PACS Sketchaccuracy: 74.4 -> 82.3Improved
add projection head to baselines (ERM, CORAL, VREx, IB ERM) (ablation)DomainBed baselines · DomainBedaccuracy: -2.16% to +0.69%No clear effect
use RDI instead of ERMResNet-50 · DomainBed averageaccuracy: 63.3 -> 65.7Improved
use RDI instead of GGAResNet-50 · PACSaccuracy: 86.4 -> 87.4Improved
use RDI instead of GGAResNet-50 · DomainNetaccuracy: 44.4 -> 44.2Hurt
use RDI instead of CORALResNet-50 · VLCSaccuracy: 78.8 -> 78.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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