Research map / Label-efficient and robust learning / Recognition and long-tail
Invariant Information Bottleneck for Domain Generalization
Read the paperCheck 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 |
|---|---|---|---|
| add the information-bottleneck penalty to IIB (ablation) | IIB · CS-CMNIST test | accuracy (%): 66.93 $\pm$ 0.33 -> 74.23 $\pm$ 4.80 | Helped |
| add the invariant-risk term (ablation) | IIB · CS-CMNIST test | accuracy (%): 69.52 $\pm$ 0.80 -> 74.23 $\pm$ 4.80 | Helped |
| add the information-bottleneck penalty to IIB (ablation) | IIB · Cross Lines test | accuracy (%): 66.93 $\pm$ 0.33 -> 71.04 $\pm$ 0.37 | Helped |
| add the invariant-risk term (ablation) | IIB · Cross Lines test | accuracy (%): 69.52 $\pm$ 0.80 -> 71.04 $\pm$ 0.37 | Helped |
| use IIB instead of IB-IRM | CS-CMNIST · CS-CMNIST test | accuracy (%): 71.79 $\pm$ 0.70 -> 74.23 $\pm$ 4.80 | Helped |
| use IIB instead of IB-ERM | Cross Lines · Cross Lines test | accuracy (%): 69.70 $\pm$ 0.42 -> 71.04 $\pm$ 0.37 | Helped |
| use IIB instead of the strongest listed baseline | DomainBed · Colored-MNIST | accuracy (%): 40.7 $\pm$ 2.3 -> 39.9 $\pm$ 1.2 | Mixed |
| use IIB instead of the strongest listed baseline | DomainBed · PACS | accuracy (%): 83.7 $\pm$ 0.4 -> 83.9 $\pm$ 0.2 | Helped |
| use IIB instead of the strongest listed baseline | DomainBed · TerraIncognita | accuracy (%): 48.7 $\pm$ 0.4 -> 45.8 $\pm$ 1.4 | Hurt |
| use IIB instead of the strongest listed baseline | DomainBed · DomainBed average | accuracy (%): 64.0 -> 64.9 | Helped |
| use a non-linear instead of a linear classifier | IIB · Rotated-MNIST, leave-one-domain-out | accuracy (%): 95.3 -> 97.3 | Helped |
Closest papers by meaning
- Invariant Risk Minimization Is A Total Variation Model (ICML 2024 · similarity 0.87)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.87)
- Enhancing Evolving Domain Generalization through Dynamic Latent Representations (AAAI 2024 · similarity 0.87)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.86)
- Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains (AAAI 2024 · similarity 0.86)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.86)
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.