Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Adaptation with Conditional Transferable Components
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 CTC (location-scale conditional transferable components) instead of DIP-style invariant components | domain adaptation on Office+Caltech256 · Office+Caltech256 (12 tasks) | classification accuracy % | Helped |
| Use CTC instead of DIP | WiFi cross-device transfer · WiFi hallway1-3 | accuracy % | Helped |
| Add target information preservation (TIP) term to CTC (ablation) | CTC on Office+Caltech256 and WiFi · Office+Caltech256 and WiFi | accuracy % | No clear effect |
| Use CTC on WiFi time-period transfer instead of DIP/TCA | WiFi cross-time transfer · WiFi t1→t3 | accuracy % | Mixed |
| Use CIC (conditional invariant components) instead of DIP when P(Y) changes | Simulated data with class-ratio shift · Simulation, class ratio 0.2-1.8 | classification error % | Helped |
| Use CTC instead of DIP for location-scale shifted features | Simulated data with LS-transformed features · Simulation, d>4 | classification error % | Helped |
Closest papers by meaning
- Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? (NeurIPS 2021 · similarity 0.91)
- Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions (NeurIPS 2018 · similarity 0.90)
- Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation (CVPR 2021 · similarity 0.89)
- Mapping conditional distributions for domain adaptation under generalized target shift (ICLR 2022 · similarity 0.89)
- Partial disentanglement for domain adaptation (ICML 2022 · similarity 0.89)
- On $f$-Divergence Principled Domain Adaptation: An Improved Framework (NeurIPS 2024 · similarity 0.87)
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.