Research map / Label-efficient and robust learning / Recognition and long-tail
Spatial Classification with Limited Observations Based on Physics-Aware Structural Constraint
Arpan Man Sainju, Wenchong He, Zhe Jiang, Da Yan
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 physics-aware topography-tree structure to EM classification | EM-i.i.d. · Matthew, Kinston | Avg. F: 0.66 -> 0.96 | Improved |
| add physics-aware topography-tree structure to EM classification | EM-i.i.d. · Matthew, Grimesland | Avg. F: 0.77 -> 0.97 | Improved |
| replace the single-modal feature distribution with a multi-modal mixture of Gaussians (ablation) | EM-Structure-Single · Matthew, Kinston (multi-modal training samples) | Avg. F: 0.34 -> 0.97 | Improved |
| replace the single-modal feature distribution with a multi-modal mixture of Gaussians (ablation) | EM-Structure-Single · Matthew, Grimesland (multi-modal training samples) | Avg. F: 0.28 -> 0.95 | Improved |
| use a single-modal rather than multi-modal feature distribution (ablation) | EM-Structure-Multi · Matthew, Kinston (multi-modal training samples) | Avg. F: 0.97 -> 0.34 | Hurt |
| use a single-modal rather than multi-modal feature distribution (ablation) | EM-Structure-Multi · Matthew, Grimesland (multi-modal training samples) | Avg. F: 0.95 -> 0.28 | Hurt |
| vary initial leaf-class prior π from 0.1 to 0.9 (ablation) | EM-Structure · Matthew, Kinston | F-score | No clear effect |
| set initial transition probability ρ above 0.99 (ablation) | EM-Structure · Matthew, Kinston | F-score | No clear effect |
Closest papers by meaning
- Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales (AAAI 2025 · similarity 0.82)
- Scale-aware Recognition in Satellite Images under Resource Constraints (ICLR 2025 · similarity 0.81)
- Multi-Scale Graph Learning for Anti-Sparse Downscaling (AAAI 2025 · similarity 0.81)
- Spatial-Logic-Aware Weakly Supervised Learning for Flood Mapping on Earth Imagery (AAAI 2024 · similarity 0.81)
- Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science (AAAI 2025 · similarity 0.81)
- Pluvial Flood Emulation with Hydraulics-informed Message Passing (ICML 2024 · similarity 0.81)
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.
