Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Invariant Representation Learning with Domain Density Transformations
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 |
|---|---|---|---|
| use squared error invariance distance instead of contrastive distance (ablation) | DIRT-GAN · Rotated MNIST M75 | accuracy: 95.8 -> 97.1 | Helped |
| use squared error invariance distance instead of cosine distance (ablation) | DIRT-GAN · Rotated MNIST M75 | accuracy: 90.1 -> 97.1 | Helped |
| enforce representation invariance under learned StarGAN domain transformations vs prior invariance methods | domain generalization · PACS average | accuracy: 81.38 -> 83.62 | Helped |
| same, on VLCS | domain generalization · VLCS average | accuracy: 74.38 -> 76.4 | Helped |
| same, on Rotated MNIST | domain generalization · Rotated MNIST average | accuracy: 97.2 -> 98.6 | Helped |
| same, per-domain PACS Cartoon | DIRT-GAN · PACS Cartoon target | accuracy: 80.38 -> 76.37 | No clear effect |
| use normalizing flows (AlignFlow) instead of GAN transformations (ablation) | DIRT · domain generalization | accuracy | No clear effect |
Closest papers by meaning
- Failure Modes of Domain Generalization Algorithms (CVPR 2022 · similarity 0.92)
- Domain Generalization via Entropy Regularization (NeurIPS 2020 · similarity 0.91)
- Domain Generalization With Adversarial Feature Learning (CVPR 2018 · similarity 0.91)
- Domain Generalization via Conditional Invariant Representations (AAAI 2018 · similarity 0.91)
- Learning to Learn Single Domain Generalization (CVPR 2020 · similarity 0.91)
- 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.