Research map / Label-efficient and robust learning / Domain adaptation and generalization
Transporting Causal Mechanisms for Unsupervised Domain Adaptation
Zhongqi Yue, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang
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 |
|---|---|---|---|
| increase number of DCMs from 1 to 2 (ablation) | TCM · ImageCLEF-DA | accuracy %: 88.7 -> 89.9 | Improved |
| increase number of DCMs from 2 to 3 (ablation) | TCM · ImageCLEF-DA | accuracy %: 89.9 -> 90.3 | Improved |
| increase number of DCMs from 3 to 5 (ablation) | TCM · ImageCLEF-DA | accuracy %: 90.3 -> 90.3 | No clear effect |
| increase number of DCMs from 5 to 10 (ablation) | TCM · ImageCLEF-DA | accuracy %: 90.3 -> 90.0 | Hurt |
| use proxy function h_y with a single DCM (k=1) instead of baseline classifier on transformed samples (ablation) | TCM · ImageCLEF-DA | accuracy %: 87.3 -> 88.7 | Improved |
| use multiple DCMs with proxy theory instead of the CycleGAN baseline | TCM · Office-Home | accuracy %: 66.6 -> 70.7 | Improved |
| use multiple DCMs with proxy theory instead of the CycleGAN baseline | TCM · ImageCLEF-DA | accuracy %: 87.3 -> 90.5 | Improved |
| use TCM instead of GVB-GD | TCM · Office-Home A->C | accuracy %: 57.0 -> 58.6 | Improved |
| use TCM instead of GVB-GD | TCM · Office-Home average | accuracy %: 70.4 -> 70.7 | Improved |
| use TCM instead of SymNets | TCM · ImageCLEF-DA average | accuracy %: 89.9 -> 90.5 | Improved |
Closest papers by meaning
- U$^3$CF: Unbiased, Unconfounding, and Unified Causal Framework for Multi-Target Domain Adaptation (ICML 2026 · similarity 0.90)
- Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transport (CVPR 2026 · similarity 0.89)
- UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework (ECCV 2024 · similarity 0.89)
- On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis for Parametric Models (JMLR 2024 · similarity 0.89)
- Few-shot Domain Adaptation by Causal Mechanism Transfer (ICML 2020 · similarity 0.89)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · 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.
