Research map / Detection and segmentation / Open-set and few-shot detection
Faster Multi-Object Segmentation Using Parallel Quadratic Pseudo-Boolean Optimization
Niels Jeppesen, Patrick M. Jensen, Anders N. Christensen, Anders B. Dahl, Vedrana A. Dahl
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 bottom-up merging with a single thread (P-QPBO(1) instead of K-QPBO) | QPBO · Nerve segmentation N2 | solve time: 4,987 s -> 2,429 s (51% reduction) | Improved |
| add bottom-up merging with a single thread (P-QPBO(1) instead of K-QPBO) | QPBO · Nerve segmentation N1 | solve time: 836 s -> 558 s (33% reduction) | Improved |
| use compact data structures (M-QPBO instead of K-QPBO) | K-QPBO · Nerve segmentation N1 | solve time and memory: 836 s -> 628 s (25% reduction); 134.2 GB -> 60.1 GB | Improved |
| use compact data structures (M-QPBO instead of K-QPBO) | K-QPBO · Nerve segmentation N2 | solve time and memory: 4,987 s -> 3,704 s; 306.8 GB -> 182.7 GB | Improved |
| increase threads from 1 to 16 | P-QPBO · Nerve segmentation N1 | solve time: 558 s -> 94 s | Improved |
| increase threads from 32 to 40 | P-QPBO · Nerve segmentation N1 | solve time: 80 s -> 74 s | Improved |
| increase threads from 40 to 48 | P-QPBO · Nerve segmentation N1 | solve time: 74 s -> 76 s | No clear effect |
| increase threads from 40 to 48 | P-QPBO · Nerve segmentation N2 | solve time: 245 s -> 239 s | No clear effect |
| add the two-stage QPBO strategy to parallel merging (P-QPBO instead of Liu-Sun maxflow) (ablation) | P-QPBO · Nerve segmentation N1 | speed-up vs K-QPBO: 6.07 -> 10.47 | Improved |
| use P-QPBO instead of parallel EIBFS with bottom-up merging (ablation) | P-EIBFS · BBBC038v1 S1 | mean speed-up vs K-QPBO: 0.68 -> 2.96 | Improved |
| use P-QPBO instead of serial EIBFS maxflow on full graph (ablation) | EIBFS · Nerve segmentation N1 | speed-up vs K-QPBO: 1.08 -> 10.47 | Improved |
| use P-QPBO instead of best-case EIBFS-QPBO estimate (ablation) | EIBFS-QPBO · BBBC038v1 S1 | mean speed-up vs K-QPBO: 0.66 -> 2.96 | Improved |
Closest papers by meaning
- Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision (TPAMI 2022 · similarity 0.85)
- A Fast Binary Quadratic Programming Solver Based on Stochastic Neighborhood Search (TPAMI 2020 · similarity 0.83)
- Large-Scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications (TPAMI 2016 · similarity 0.83)
- BOIDS: High-Dimensional Bayesian Optimization via Incumbent-Guided Direction Lines and Subspace Embeddings (AAAI 2025 · similarity 0.81)
- Decomposed Quadratization: Efficient QUBO Formulation for Learning Bayesian Network (AAAI 2025 · similarity 0.81)
- RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation (NeurIPS 2025 · 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.
