Research map / Label-efficient and robust learning / Domain adaptation and generalization
Deep Domain Generalization via Conditional Invariant Adversarial Networks
Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu, Tongliang Liu, Kun Zhang, Dacheng Tao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add marginal domain-adversarial loss to Deep-All (ablation) | DeepA · Rotated MNIST (target 90 deg) | accuracy (%): 79.56 -> 82.95 | Improved |
| add class-conditional domain loss to marginal-adversarial (DeepC vs DeepD) (ablation) | DeepD · Rotated MNIST (target 90 deg) | accuracy (%): 82.95 -> 80.08 | Hurt |
| add class-conditional domain loss (DeepC vs DeepD) (ablation) | DeepD · PACS (target S) | accuracy (%): 60.76 -> 64.45 | Improved |
| add class-conditional domain loss (DeepC vs DeepD) (ablation) | DeepD · VLCS (target C) | accuracy (%): 86.58 -> 87.47 | Improved |
| add class prior-normalized loss (DeepN vs DeepC) (ablation) | DeepC · PACS (target P) | accuracy (%): 80.72 -> 77.45 | Hurt |
| use class prior-normalized loss instead of class-conditional loss (ablation) | DeepC · Rotated MNIST (target 90 deg) | accuracy (%): 80.08 -> 83.99 | Improved |
| combine class-conditional and prior-normalized losses (CIDDG vs DeepC) (ablation) | DeepC · VLCS (target C) | accuracy (%): 87.47 -> 88.83 | Improved |
| combine both losses (CIDDG vs DeepN) (ablation) | DeepN · Rotated MNIST (target 90 deg) | accuracy (%): 83.99 -> 84.00 | No clear effect |
| combine both losses (CIDDG vs DeepN) (ablation) | DeepN · PACS (target P) | accuracy (%): 77.45 -> 78.65 | Improved |
| CIDDG instead of marginal-matching DeepD (ablation) | DeepD · PACS (target P) | accuracy (%): 80.39 -> 78.65 | Hurt |
| CIDDG instead of marginal-matching DeepD (ablation) | DeepD · VLCS (target S) | accuracy (%): 60.29 -> 62.10 | Improved |
| end-to-end deep fine-tuning instead of shallow methods on pretrained features (DeepA vs MATE) | MATE · VLCS (target V) | accuracy (%): 51.66 -> 62.71 | Improved |
Closest papers by meaning
- Domain Invariant Representation Learning with Domain Density Transformations (NeurIPS 2021 · similarity 0.94)
- Domain Generalization via Entropy Regularization (NeurIPS 2020 · similarity 0.93)
- Domain Generalization via Conditional Invariant Representations (AAAI 2018 · similarity 0.93)
- Domain Generalization With Adversarial Feature Learning (CVPR 2018 · similarity 0.91)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.90)
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.89)
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.
