Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cluster Alignment With a Teacher for Unsupervised Domain Adaptation
Zhijie Deng, Yucen Luo, Jun Zhu
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 CAT to RevGrad | RevGrad · SVHN to MNIST | accuracy: 73.9 -> 98.0 | Improved |
| add CAT to MCD | MCD · SVHN to MNIST | accuracy: 96.2 -> 97.1 | Improved |
| add CAT to VADA (first stage only) | VADA · SVHN to MNIST | accuracy: 94.5 -> 95.2 | Improved |
| add CAT to MCD | MCD · second digits task | accuracy: 94.2 -> 96.3 | Improved |
| replace RevGrad with RevGrad+CAT | RevGrad · third digits task | accuracy: 73.0 -> 95.7 | Improved |
| use CAT alone instead of MSTN | MSTN · second digits task | accuracy: 92.9 -> 90.6 | Hurt |
| use CAT instead of RevGrad/MSTN under class imbalance | RevGrad and MSTN · Imbalanced SVHN-MNIST-USPS (first task) | accuracy: 27.4 -> 100.0 | Improved |
| add CAT to JAN (ResNet-50) | JAN · Office-31 (average of 6 tasks) | accuracy: 84.3 -> 86.2 | Improved |
| add CAT to RevGrad (rRevGrad+CAT, ResNet-50) | RevGrad · Office-31 (average of 6 tasks) | accuracy: 82.2 -> 87.6 | Improved |
| add CAT to RevGrad (rRevGrad+CAT, AlexNet) | RevGrad · Office-31 (average of 6 tasks) | accuracy: 74.3 -> 80.1 | Improved |
| add CAT to JAN (ResNet-50) | JAN · ImageCLEF-DA (average of 6 tasks) | accuracy: 85.8 -> 86.4 | Improved |
| add CAT to RevGrad (ResNet-50) | RevGrad · ImageCLEF-DA (average of 6 tasks) | accuracy: 85.0 -> 87.3 | Improved |
Closest papers by meaning
- Domain Consensus Clustering for Universal Domain Adaptation (CVPR 2021 · similarity 0.91)
- Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering (CVPR 2020 · similarity 0.91)
- Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation (CVPR 2020 · similarity 0.90)
- Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation Using Structurally Regularized Deep Clustering (TPAMI 2021 · similarity 0.90)
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation (AAAI 2025 · 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.
