Research map / Learning theory and algorithms / Clustering
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 locally high-density cluster-cores instead of singleton point-modes, then assign remaining samples by hill climbing | Quickshift++ · Real datasets | Adjusted Rand Index | Helped |
| Use locally high-density cluster-cores instead of singleton point-modes, then assign remaining samples by hill climbing | Quickshift++ · Real datasets | Adjusted Mutual Information | Helped |
| Use cluster-cores rather than point-modes | Quickshift++ · Image segmentation | Qualitative segmentation quality | Helped |
| Use cluster-cores rather than point-modes | Quickshift++ · Two rings simulation | Cluster separation | Helped |
| Adapt density thresholds to cluster density rather than use one fixed density level | Quickshift++ · Three Gaussians simulation | Cluster recovery | Helped |
Closest papers by meaning
- On the Consistency of Quick Shift (NeurIPS 2017 · similarity 0.88)
- UEQMS: UMAP Embedded Quick Mean Shift Algorithm for High Dimensional Clustering (AAAI 2023 · similarity 0.87)
- Automated Clustering of High-dimensional Data with a Feature Weighted Mean Shift Algorithm (AAAI 2021 · similarity 0.87)
- On Convergence of Epanechnikov Mean Shift (AAAI 2018 · similarity 0.86)
- MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking (CVPR 2021 · similarity 0.85)
- Contrastive Mean-Shift Learning for Generalized Category Discovery (CVPR 2024 · similarity 0.83)
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.