Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
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 SRDC instead of CAN | Office-31 domain adaptation · Office-31 average | accuracy (%): 90.6 -> 90.8 | Helped |
| Use SRDC instead of SymNets | ImageCLEF-DA domain adaptation · ImageCLEF-DA average | accuracy (%): 89.9 -> 90.9 | Helped |
| Use SRDC instead of CADA-P | Office-Home domain adaptation · Office-Home average | accuracy (%): 70.2 -> 71.3 | Helped |
| Add structural source regularization (ablation) | SRDC target clustering on Office-31 · Office-31 average | accuracy (%): 82.1 -> 86.3 | Helped |
| Add source and target feature-space discrimination (ablation) | SRDC target clustering on Office-31 · Office-31 average | accuracy (%): 84.6 -> 86.3 | Helped |
| Add soft source sample selection (ablation) | SRDC target clustering on Office-31 · Office-31 average | accuracy (%): 84.9 -> 86.3 | Helped |
| Use SRDC instead of MCD | Office-31 inductive UDA · Office-31 inductive UDA average | accuracy (%): 79.1 -> 83.7 | Helped |
Closest papers by meaning
- COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport (CVPR 2023 · similarity 0.90)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.89)
- Domain Consensus Clustering for Universal Domain Adaptation (CVPR 2021 · similarity 0.89)
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.88)
- Upcycling Models Under Domain and Category Shift (CVPR 2023 · similarity 0.88)
- Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (CVPR 2021 · 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.