Research map / Label-efficient and robust learning / Domain adaptation and generalization
Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
Check 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 weighted MMD instead of conventional MMD to account for class-prior differences | DAN with AlexNet · Office-10+Caltech-10 | accuracy: 1.9% | Helped |
| Use weighted MMD instead of conventional MMD to account for class-prior differences | DAN with GoogLeNet · Office-10+Caltech-10 | accuracy: 0.9% | Helped |
| Use weighted MMD instead of conventional MMD to account for class-prior differences | DAN with VGGnet-16 · Office-10+Caltech-10 | accuracy: 0.7% | Helped |
| Use weighted MMD instead of conventional MMD to account for class-prior differences | DAN · ImageCLEF | accuracy: 0.9% | Helped |
| Use weighted MMD instead of conventional MMD to account for class-prior differences | DAN with LeNet · Digit Recognition | accuracy: 3.7% | Helped |
| Use weighted MMD instead of conventional MMD to account for class-prior differences | DAN with AlexNet · Office-31 | accuracy | Helped |
| Use ground-truth class distributions instead of estimating auxiliary weights from pseudo-labels (ablation) | WDAN (AlexNet) · Office-10+Caltech-10 | accuracy: 89.2 -> 89.8 | Helped |
| Increase class-prior bias in the target domain | DAN · ImageCLEF two-class PASCAL VOC2012-to-Caltech256 variant | accuracy | Hurt |
| Increase class-prior bias in the target domain | WDAN · ImageCLEF two-class PASCAL VOC2012-to-Caltech256 variant | accuracy | Mixed |
Closest papers by meaning
- Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation (AAAI 2022 · similarity 0.90)
- On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation (ICML 2023 · similarity 0.90)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.88)
- On $f$-Divergence Principled Domain Adaptation: An Improved Framework (NeurIPS 2024 · similarity 0.87)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.87)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 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.