Research map / Label-efficient and robust learning / Domain adaptation and generalization
Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation Using Structurally Regularized Deep Clustering
Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, C. L. Philip Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add soft selection of source samples (S4) (ablation) | SRDisC+SRGenC · VisDA-2017 (inductive) | accuracy: 82.4 -> 83.4 | Improved |
| add soft selection of source samples (S4) (ablation) | SRDisC+SRGenC · Office-31 (inductive) | accuracy: 84.0 -> 85.1 | Improved |
| add soft selection of source samples (S4) (ablation) | SRDisC+SRGenC · Office-Home (inductive) | accuracy: 67.3 -> 68.0 | Improved |
| add structural source regularization to discriminative clustering (ablation) | DisC · VisDA-2017 (inductive) | accuracy: 78.1 -> 81.2 | Improved |
| add structural source regularization to generative clustering (ablation) | GenC · VisDA-2017 (inductive) | accuracy: 66.7 -> 69.4 | Improved |
| add structural source regularization to the combined clustering (ablation) | DisC+GenC · Office-31 (inductive) | accuracy: 82.0 -> 84.0 | Improved |
| add structural source regularization to the combined clustering (ablation) | DisC+GenC · Office-Home (inductive) | accuracy: 65.8 -> 67.3 | Improved |
| add generative clustering to discriminative clustering (ablation) | DisC · Office-31 (inductive) | accuracy: 79.6 -> 82.0 | Improved |
| add generative clustering to discriminative clustering (ablation) | DisC · VisDA-2017 (inductive) | accuracy: 78.1 -> 79.4 | Improved |
| use discriminative instead of generative clustering (ablation) | GenC · VisDA-2017 (inductive) | accuracy: 66.7 -> 78.1 | Improved |
| use discriminative instead of generative clustering with source regularization (ablation) | SRGenC · VisDA-2017 (inductive) | accuracy: 69.4 -> 81.2 | Improved |
| add clustering-based adaptation over source only (ablation) | Source Only · Office-31 (inductive) | accuracy: 72.4 -> 79.6 | Improved |
Closest papers by meaning
- Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering (CVPR 2020 · similarity 0.97)
- Inferring Latent Domains for Unsupervised Deep Domain Adaptation (TPAMI 2019 · similarity 0.91)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Cluster Alignment With a Teacher for Unsupervised Domain Adaptation (ICCV 2019 · similarity 0.90)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.89)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.89)
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.
