Research map / Label-efficient and robust learning / Domain adaptation and generalization
Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transport
Khushboo Mishra, Varun Trivedi, Tanima Dutta
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 |
|---|---|---|---|
| use Sinkhorn OT solver instead of Greenkhorn or unbalanced OT (ablation) | Causal-OT · OT solver comparison | alignment score: 0.79 -> 0.84 | Improved |
| Causal-OT versus TransPL baseline on calibration | Causal-OT · SSC | ECE: 13.55 -> 11.23 | Improved |
| Causal-OT versus TransPL baseline on calibration | Causal-OT · MFD | ECE: 4.37 -> 3.78 | Improved |
| causal-graph-regularized OT plus entropy-filtered pseudo-labeling versus TransPL | Causal-OT · WISDM (average) | accuracy (%): 64.0 -> 68.03 | Improved |
| causal-graph-regularized OT plus entropy-filtered pseudo-labeling versus TransPL | Causal-OT · UCIHAR (average) | accuracy (%): 69.0 -> 73.97 | Improved |
| causal-graph-regularized OT plus entropy-filtered pseudo-labeling versus TransferAttn | Causal-OT · UCF101<->HMDB51 | accuracy (%) average: 88.2 -> 89.85 | Improved |
| Causal-OT versus TransPL on a hard WISDM pair (28->4) | Causal-OT · WISDM pair 28->4 | accuracy (%): 54.5 -> 58.3 | Mixed |
Closest papers by meaning
- Enhancing Multivariate Time-Series Domain Adaptation via Contrastive Frequency Graph Discovery and Language-Guided Adversary Alignment (AAAI 2025 · similarity 0.88)
- CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series (ICML 2024 · similarity 0.88)
- Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation (ICML 2024 · similarity 0.87)
- TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation (ICML 2025 · similarity 0.87)
- Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation (ICML 2025 · similarity 0.86)
- Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains (ICML 2025 · 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.
