Research map / Label-efficient and robust learning / Domain adaptation and generalization
Stochastic Classifiers 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 |
|---|---|---|---|
| Replace two fixed MCD classifiers with Gaussian-distribution-sampled stochastic classifiers | MCD · SVHN→MNIST | accuracy: 96.2±0.4 -> 98.8±0.05 | Helped |
| Replace two fixed MCD classifiers with Gaussian-distribution-sampled stochastic classifiers | MCD · SYNSIGNS→GTSRB | accuracy: 94.4±0.3 -> 95.8±0.2 | Helped |
| Replace two fixed MCD classifiers with Gaussian-distribution-sampled stochastic classifiers | MCD · MNIST→USPS | accuracy: 96.5±0.3 -> 97.8±0.1 | Helped |
| Replace two fixed MCD classifiers with Gaussian-distribution-sampled stochastic classifiers | MCD · USPS→MNIST | accuracy: 94.1±0.3 -> 97.7±0.05 | Helped |
| Use STAR stochastic classifiers instead of the CLAN classifier setup | CLAN · GTA5→Cityscapes | mIoU: 42.9 -> 43.6 | Helped |
| Use STAR stochastic classifiers instead of the CLAN classifier setup | CLAN · Synthia→Cityscapes | mIoU: 46.0 -> 48.1 | Helped |
| Sample more classifiers per training iteration (ablation) | STAR with MCD · MNIST→USPS and USPS→MNIST | accuracy | No clear effect |
Closest papers by meaning
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.89)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.88)
- Uncertainty Reduction for Model Adaptation in Semantic Segmentation (CVPR 2021 · similarity 0.88)
- Unsupervised Model Adaptation for Continual Semantic Segmentation (AAAI 2021 · similarity 0.88)
- Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation (NeurIPS 2019 · similarity 0.88)
- Open-Set Domain Adaptation for Semantic Segmentation (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.