Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Generalization via Conditional Invariant Representations
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 |
|---|---|---|---|
| Learn class-conditional invariant features instead of marginal-invariant features | CIDG · VLCS domain generalization tasks | accuracy | Helped |
| Learn class-conditional invariant features instead of marginal-invariant features | CIDG · Office+Caltech domain generalization tasks | accuracy | Helped |
| Use CIDG rather than Undo-bias | Office+Caltech: D,W → A,C · Office+Caltech: D,W → A,C | accuracy: 65.91 ± 1.42 vs 74.14 ± 3.45 | Hurt |
| Use CIDG rather than KPCA | VLCS: L,S → V,C · VLCS: L,S → V,C | accuracy: 55.65 ± 3.57 vs 58.50 ± 3.84 | Hurt |
| Enforce conditional invariance and discriminative class separation | CIDG · Synthetic dataset | accuracy | Helped |
Closest papers by meaning
- Failure Modes of Domain Generalization Algorithms (CVPR 2022 · similarity 0.92)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.92)
- Domain Generalization via Entropy Regularization (NeurIPS 2020 · similarity 0.91)
- Adaptive Methods for Real-World Domain Generalization (CVPR 2021 · similarity 0.91)
- Domain Invariant Representation Learning with Domain Density Transformations (NeurIPS 2021 · similarity 0.91)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.90)
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.