Research map / Time series / Foundation models for time series
CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series Classification
Yuhang Pei, Fanchun Meng, Wenrui Wu, Tao Ren, Yifan Wang, Wei Ju, Chao Zheng, Xiao Luo
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 distance-correlation independence loss Lind (ablation) | CURE · EMG | accuracy (%): 73.53 -> 77.69 | Improved |
| add distance-correlation independence loss Lind (ablation) | CURE · DSADS | accuracy (%): 70.32 -> 74.23 | Improved |
| add category semantic consistency loss Lcat (ablation) | CURE · EMG | accuracy (%): 62.99 -> 77.69 | Improved |
| add category semantic consistency loss Lcat (ablation) | CURE · DSADS | accuracy (%): 68.91 -> 74.23 | Improved |
| add domain style repulsion loss Ldom (ablation) | CURE · EMG | accuracy (%): 66.63 -> 77.69 | Improved |
| add domain style repulsion loss Ldom (ablation) | CURE · DSADS | accuracy (%): 68.84 -> 74.23 | Improved |
| add adversarial tuning of the diffusion model (ablation) | CURE · EMG | accuracy (%): 61.83 -> 77.69 | Improved |
| add adversarial tuning of the diffusion model (ablation) | CURE · DSADS | accuracy (%): 69.64 -> 74.23 | Improved |
| add boundary-based sample filtering (ablation) | CURE · EMG | accuracy (%): 70.97 -> 77.69 | Improved |
| add boundary-based sample filtering (ablation) | CURE · DSADS | accuracy (%): 72.95 -> 74.23 | Improved |
| replace SEED with CURE | SEED · EMG | accuracy (%): 74.67 -> 77.69 | Improved |
| replace SEED with CURE | SEED · DSADS | accuracy (%): 68.88 -> 74.23 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DIVERSIFY — Diversify: A General Framework for Time Series Out-of-Distribution Detection and Generalization (TPAMI 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (NeurIPS 2025 · similarity 0.88)
- Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer (ICML 2025 · similarity 0.88)
- TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts (AAAI 2025 · similarity 0.87)
- Large Pre-trained time series models for cross-domain Time series analysis tasks (NeurIPS 2024 · similarity 0.86)
- Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments (NeurIPS 2024 · similarity 0.86)
- TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 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.
