Research map / Detection and segmentation / CNN features
Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics
Gaetano Romano, Idris A. Eckley, Paul Fearnhead, Guillem Rigaill
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 FOCuS (functional pruning, all change sizes) instead of Numenta HTM | R-FOCuS · NAB AWS CPU utilization | precision: 0.50 -> 0.58 | Improved |
| use R-FOCuS instead of Numenta HTM | R-FOCuS · NAB AWS CPU utilization | recall: 0.76 -> 0.82 | Improved |
| use R-FOCuS instead of Numenta HTM | R-FOCuS · NAB AWS CPU utilization | false detections: 13 -> 7 | Improved |
| use FOCuS instead of ocd, pre-change mean unknown, large change | FOCuS · 100 streams sparsity 1, magnitude 1 | average detection delay: 675.58 -> 190.29 | Improved |
| use FOCuS0 instead of ocd, pre-change mean known, small change | FOCuS0 · 100 streams sparsity 0.01, magnitude 0.25 | average detection delay: 318.30 -> 365.03 | Hurt |
| use FOCuS0 instead of ocd, pre-change mean known, dense large change | FOCuS0 · 100 streams sparsity 1, magnitude 2 | average detection delay: 17.85 -> 39.74 | Hurt |
| use FOCuS0 instead of ocd, pre-change mean known, sparse large change | FOCuS0 · 100 streams sparsity 0.01, magnitude 2 | average detection delay: 12.65 -> 7.34 | Improved |
| use FOCuS (all mu1) instead of Page-CUSUM on a 10-point grid | FOCuS0 · Gaussian mean change simulation | detection delay for off-grid change sizes | Improved |
| use FOCuS instead of MOSUM | FOCuS0 · Gaussian mean change simulation | detection delay | Improved |
| prune FOCuS0 to a 10-point grid (FOCuS0-10p) from exact | FOCuS0 · Gaussian mean change simulation | detection delay | No clear effect |
| use FOCuS (unknown mean) instead of FOCuS0 with small training data | FOCuS · Gaussian mean change simulation | detection delay | Improved |
| use FOCuS instead of FOCuS0 with large training data | FOCuS · Gaussian mean change simulation | detection delay | Mixed |
Closest papers by meaning
- Robust and Scalable Bayesian Online Changepoint Detection (ICML 2023 · similarity 0.86)
- Iterative Global Mapping-Local Searching for Heterogeneous Change Detection with Unregistered Images (IJCV 2026 · similarity 0.83)
- Restarted Bayesian Online Change-point Detector achieves Optimal Detection Delay (ICML 2020 · similarity 0.82)
- Optimal Online Change Detection via Random Fourier Features (NeurIPS 2025 · similarity 0.82)
- ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model (AAAI 2025 · similarity 0.79)
- Segment Any Change (NeurIPS 2024 · similarity 0.79)
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.
