Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
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 importance-weighted DANN (IWDAN) | DANN · Digits, Visda, Office-31, Office-Home | accuracy: +1.75%, +1.64%, +1.16%, +2.65% | Helped |
| use importance-weighted DANN (IWDAN) | DANN · sDigits, sVisda, sOffice-31, sOffice-Home | accuracy: +9.3%, +7.33%, +6.43%, +5.58% | Helped |
| use importance-weighted CDAN (IWCDAN) | CDAN · Digits, Visda, Office-31, Office-Home | accuracy: +0.18%, +0.89%, +0.07%, +1.07% | Helped |
| use importance-weighted CDAN (IWCDAN) | CDAN · sDigits, sVisda, sOffice-31, sOffice-Home | accuracy: +4.99%, +5.64%, +2.26%, +4.99% | Helped |
| add weighted classification loss (ablation) | DANN · Digits | accuracy: 93.15 -> 93.27 | No clear effect |
| add weighted classification loss (ablation) | DANN · sDigits | accuracy: 83.24 -> 84.52 | Helped |
| add weighted adversarial loss (ablation) | DANN · Digits | accuracy: 93.15 -> 95.31 | Helped |
| add weighted adversarial loss (ablation) | DANN · sDigits | accuracy: 83.24 -> 94.41 | Helped |
| add weighted classification loss (ablation) | CDAN · Digits | accuracy: 95.72 -> 95.65 | No clear effect |
| add weighted classification loss (ablation) | CDAN · sDigits | accuracy: 88.23 -> 91.01 | Helped |
| add weighted adversarial loss (ablation) | CDAN · Digits | accuracy: 95.72 -> 95.42 | Hurt |
| add weighted adversarial loss (ablation) | CDAN · sDigits | accuracy: 88.23 -> 93.18 | Helped |
Closest papers by meaning
- Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment (ICML 2019 · similarity 0.91)
- Label-Noise Robust Domain Adaptation (ICML 2020 · similarity 0.91)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.90)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.89)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.89)
- On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning (AAAI 2024 · similarity 0.88)
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.