Research map / Label-efficient and robust learning / OOD and anomaly detection
Out-of-Distribution Generalization With Causal Invariant Transformations
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 |
|---|---|---|---|
| Regularize predictions to agree between colored images and original MNIST images | RICE · C-MNIST test | accuracy (%): 13.3 -> 96.9 | Helped |
| Apply causal-invariant transformations and penalize prediction disagreement | RICE · PACS | Avg accuracy (%): 85.5 -> 88.4 | Helped |
| Apply causal-invariant transformations and penalize prediction disagreement | RICE · PACS | Min accuracy (%): 79.3 -> 84.3 | Helped |
| Apply causal-invariant transformations and penalize prediction disagreement | RICE · VLCS | Avg accuracy (%): 78.6 -> 79.3 | Helped |
| Apply causal-invariant transformations and penalize prediction disagreement | RICE · VLCS | Min accuracy (%): 64.3 -> 69.2 | Helped |
| Use CycleGAN-transformed images for ERM without the RICE invariance regularizer (ablation) | ERM on PACS · PACS | test accuracy (%): 96.2, 84.9, 81.2, 80.5 | Mixed |
| Train with data from one domain rather than several domains (ablation) | RICE · PACS and VLCS | test accuracy | Helped |
Closest papers by meaning
- Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach (AAAI 2024 · similarity 0.90)
- Out-of-Variable Generalisation for Discriminative Models (ICLR 2024 · similarity 0.88)
- On the Out-of-Distribution Generalization of Self-Supervised Learning (ICML 2025 · similarity 0.88)
- Causality Inspired Federated Learning for OOD Generalization (ICML 2025 · similarity 0.88)
- Out-of-Domain Generalization in Dynamical Systems Reconstruction (ICML 2024 · similarity 0.87)
- Dissecting the Failure of Invariant Learning on Graphs (NeurIPS 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.