Research map / Label-efficient and robust learning / Domain adaptation and generalization
Causality Inspired Representation Learning for Domain Generalization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use CIRL instead of FACT | Digits-DG · Digits-DG | average accuracy: +1.0% | Helped |
| Use CIRL instead of MatchDG | PACS, ResNet-18 · PACS | average accuracy: 1.76% | Helped |
| Use CIRL instead of MatchDG | PACS, ResNet-50 · PACS | average accuracy: 4.01% | Helped |
| Use CIRL instead of FACT | Office-Home · Office-Home | average accuracy: 0.56% | Helped |
| Add causal factorization and adversarial mask modules to intervention-only CIRL (ablation) | CIRL · PACS, ResNet-18 | average accuracy: 84.99 vs 86.32 | Helped |
| Add causal intervention and adversarial mask modules to factorization-only CIRL (ablation) | CIRL · PACS, ResNet-18 | average accuracy: 83.05 vs 86.32 | Helped |
| Add the adversarial mask module (ablation) | CIRL with causal intervention and factorization · PACS, ResNet-18 | average accuracy: 85.43 vs 86.32 | Helped |
| Add the causal intervention module (ablation) | CIRL with factorization and adversarial mask · PACS, ResNet-18 | average accuracy: 84.64 vs 86.32 | Helped |
Closest papers by meaning
- Do causal predictors generalize better to new domains? (NeurIPS 2024 · similarity 0.90)
- Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains (ICML 2025 · similarity 0.90)
- Transportable Representations for Domain Generalization (AAAI 2024 · similarity 0.88)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.88)
- Causal Representation Learning Made Identifiable by Grouping of Observational Variables (ICML 2024 · similarity 0.88)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.87)
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.