Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
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 GPDA instead of MCDA (n=4) | CNN domain adaptation · SVHN → MNIST | accuracy: 96.2±0.4 -> 98.2±0.1 | Helped |
| Use GPDA instead of ATDA | CNN domain adaptation · SYN SIGNS → GTSRB | accuracy: 96.1 -> 96.19±0.2 | Helped |
| Use GPDA instead of MCDA (n=4) | CNN domain adaptation · MNIST → USPS | accuracy: 94.2±0.7 -> 96.45±0.15 | Helped |
| Use GPDA instead of MCDA (n=4) | CNN domain adaptation · MNIST* → USPS* | accuracy: 96.5±0.3 -> 98.11±0.1 | Helped |
| Use GPDA instead of MCDA (n=4) | CNN domain adaptation · USPS → MNIST | accuracy: 94.1±0.3 -> 96.37±0.1 | Helped |
| Use GPDA instead of MCDA (n=4) | ResNet101 domain adaptation · VisDA | mean accuracy: 71.9 -> 73.31 | Helped |
| Set the maximum-separation regularization weight λ to 0, removing the MCD/MS term (ablation) | GPDA · Digit datasets | accuracy | Hurt |
| Increase the maximum-separation regularization weight λ from 0 toward 50 (ablation) | GPDA · Digit datasets | accuracy | Helped |
| Set α to 0, removing prediction uncertainty from the separation loss (ablation) | GPDA · Digit datasets | accuracy | Hurt |
| Include prediction uncertainty with α > 0 (ablation) | GPDA · Digit datasets | accuracy | Helped |
Closest papers by meaning
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Unsupervised Domain Adaptation With Similarity Learning (CVPR 2018 · similarity 0.89)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.89)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.88)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.88)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · 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.