Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning Semantic Representations for Unsupervised Domain Adaptation
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 |
|---|---|---|---|
| moving-average centroids instead of per-iteration centroids (ablation) | MSTN · Office-31 D→A | accuracy (%): 60.7 -> 62.5 | Helped |
| moving-average centroids instead of per-iteration centroids (ablation) | MSTN · Office-31 A→D | accuracy (%): 73.8 -> 74.5 | Helped |
| moving-average centroids instead of per-iteration centroids (ablation) | MSTN · Office-31 D→W | accuracy (%): 96.8 -> 96.9 | No clear effect |
| moving-average centroids instead of per-iteration centroids (ablation) | MSTN · Office-31 W→D | accuracy (%): 100 -> 99.9 | No clear effect |
| moving-average centroids instead of per-iteration centroids (ablation) | MSTN · Office-31 average | accuracy (%): 78.6 -> 79.1 | Helped |
| add semantic centroid alignment on top of adversarial adaptation | MSTN vs RevGrad · Office-31 A→W | accuracy (%): 73.0 -> 80.5 | Helped |
| add semantic centroid alignment on top of adversarial adaptation | MSTN vs RevGrad · Office-31 average | accuracy (%): 74.3 -> 79.1 | Helped |
| MSTN versus JAN | MSTN · Office-31 average | accuracy (%): 76.0 -> 79.1 | Helped |
| MSTN versus JAN | MSTN · ImageCLEF-DA average | accuracy (%): 79.3 -> 80.0 | Helped |
| MSTN versus ADDA | MSTN · SVHN→MNIST | accuracy (%): 76.0 -> 91.7 | Helped |
| MSTN versus coGAN | MSTN · MNIST→USPS | accuracy (%): 91.2 -> 92.9 | Helped |
| MSTN versus RevGrad on A-distance | MSTN · A→W and SVHN→MNIST | A-distance | No clear effect |
Closest papers by meaning
- Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation (AAAI 2025 · similarity 0.88)
- Transferable Semantic Augmentation for Domain Adaptation (CVPR 2021 · similarity 0.88)
- Improving Domain-Specific Classification by Collaborative Learning with Adaptation Networks (AAAI 2019 · similarity 0.88)
- Unsupervised Domain Adaptation With Similarity Learning (CVPR 2018 · similarity 0.87)
- Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.87)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · 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.