Research map / Label-efficient and robust learning / Domain adaptation and generalization
Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation
Won Young Jhoo, Jae-Pil Heo
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 the attention-based feature refinement stage (ablation) | Ours · X-NIST (average over all settings) | accuracy (%): 81.72 -> 88.28 | Improved |
| add refinement stage (ablation) | Ours · X-NIST G->C (ToI MNIST, IrT FashionMNIST) | accuracy (%): 68.6 -> 93.3 | Improved |
| add refinement stage (ablation) | Ours · X-NIST N->G (ToI FashionMNIST, IrT MNIST) | accuracy (%): 61.7 -> 83.4 | Improved |
| add refinement stage (ablation) | Ours · X-NIST G->N (ToI FashionMNIST, IrT MNIST) | accuracy (%): 60.6 -> 81.3 | Improved |
| add refinement stage (ablation) | Ours · X-NIST G->E (ToI MNIST, IrT FashionMNIST) | accuracy (%): 84.7 -> 92.9 | Improved |
| add refinement stage (ablation) | Ours · X-NIST C->G (ToI MNIST, IrT FashionMNIST) | accuracy (%): 98.7 -> 98.9 | No clear effect |
| add refinement stage (ablation) | Ours · X-NIST G->C (ToI NIST, IrT MNIST) | accuracy (%): 31.3 -> 45.7 | Improved |
| use Ours instead of Wang et al. generative baseline | Ours · X-NIST G->C (ToI MNIST, IrT FashionMNIST) | accuracy (%): 81.2 -> 93.3 | Improved |
| use Ours instead of Source Only ResNet-50 | Ours · Office-Home Ar->Cl (6 ToI/IrT splits) | accuracy (%): 55.1 -> 71.0 | Improved |
| use Ours instead of Source Only ResNet-50 | Ours · Office-Home Rw->Pr (6 ToI/IrT splits) | accuracy (%): 83.2 -> 88.5 | Improved |
| use Ours instead of Wang et al. | Ours · Office-Home Cl->Ar (6 ToI/IrT splits) | accuracy (%): 72.6 -> 62.1 | Hurt |
Closest papers by meaning
- Learning Across Tasks for Zero-Shot Domain Adaptation From a Single Source Domain (TPAMI 2021 · similarity 0.92)
- Adversarial Learning for Zero-shot Domain Adaptation (ECCV 2020 · similarity 0.92)
- Zero-Shot Deep Domain Adaptation (ECCV 2018 · similarity 0.89)
- Unified Language-driven Zero-shot Domain Adaptation (CVPR 2024 · similarity 0.88)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.86)
- Source-Free Domain Adaptation with Frozen Multimodal Foundation Model (CVPR 2024 · similarity 0.86)
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.
