Research map / Label-efficient and robust learning / Domain adaptation and generalization
Continuously Indexed Domain Adaptation
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 continuous domain-index regression for adaptation instead of categorical domain alignment | CIDA · Rotating MNIST target domains | average accuracy (%): 48.1 -> 85.7 | Helped |
| Use a probabilistic discriminator that predicts the domain-index distribution rather than a point estimate (ablation) | CIDA · Rotating MNIST target domains | average accuracy (%): 85.7 -> 87.1 | Helped |
| Use a probabilistic domain-index discriminator rather than point prediction (ablation) | CIDA · SHHS Outside → (52,75] | accuracy (%): 82.2 -> 83.7 | Helped |
| Use a probabilistic domain-index discriminator rather than point prediction (ablation) | CIDA · SOF → SHHS | accuracy (%): 75.9 -> 80.1 | Helped |
| Use a probabilistic domain-index discriminator rather than point prediction (ablation) | CIDA · MESA → SOF | accuracy (%): 79.3 -> 79.0 | Hurt |
| Add heart rate and health variables to age as dimensions of the domain index (ablation) | CIDA · SHHS [44,52] → (52,90] | accuracy (%): 79.8 -> 81.0 -> 81.2 -> 82.6 | Helped |
| Add heart rate and health variables to age as dimensions of the domain index (ablation) | PCIDA · SHHS [44,52] → (52,90] | accuracy (%): 80.6 -> 81.1 -> 81.3 -> 82.6 | Helped |
| Use categorical domain adaptation instead of continuous-index adaptation | Domain adaptation methods on medical datasets · Intra-dataset domain extrapolation | accuracy (%) | No clear effect |
| Use categorical domain adaptation instead of continuous-index adaptation | Domain adaptation methods on medical datasets · Rotating MNIST target domains | average accuracy (%): 48.1 -> 47.2 | Hurt |
Closest papers by meaning
- Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation (ICLR 2023 · similarity 0.87)
- Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data (CVPR 2025 · similarity 0.86)
- Category-Aware Active Domain Adaptation (ICML 2024 · similarity 0.85)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.85)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.85)
- Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation (NeurIPS 2025 · similarity 0.85)
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.