Research map / Detection and segmentation / Open-set and few-shot detection
Polyhedral Conic Classifiers for Visual Object Detection and Classification
Hakan Cevikalp, Bill Triggs
Check 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 EPCC instead of linear SVM | visual object detection · FDDB | Average Precision (%): 37.6 -> 71.9 | Improved |
| Use EPCC instead of linear SVM | face detection · ESOGU Faces | Average Precision (%): 47.7 -> 89.1 | Improved |
| Use EPCC instead of linear SVM | pedestrian detector · INRIA Person | Average Precision (%): 80.4 -> 85.6 | Improved |
| Use OC-EPCC instead of linear SVM | visual classifier · PASCAL VOC 2007 | Average Precision (%): 68.6 -> 72.5 | Improved |
| Use EPCC instead of linear SVM | multiclass classifier · Multiple Features | classification accuracy (%): 93.9 ± 1.1 -> 96.3 ± 1.2 | Improved |
| Use EPCC instead of linear SVM | multiclass classifier · Letter Recognition | classification accuracy (%): 59.8 ± 1.7 -> 76.0 ± 1.2 | Improved |
| Use EPCC instead of linear SVM | open-set classifier · USPS Digits | Average Precision (%): 61.9 -> 80.6 | Improved |
| Use OC-EPCC instead of EPCC | open-set classifier · Leopard | Average Precision (%): 69.8 ± 7.9 -> 76.6 ± 2.9 | Improved |
| Use OC-EPCC instead of EPCC | open-set classifier · Airplane | Average Precision (%): 15.5 ± 2.8 -> 13.6 ± 1.5 | Hurt |
| Use EPCC instead of SVM | closed-set visual classifier · Caltech-256 | classification accuracy (%): 37.6 ± 0.7 -> 40.1 ± 0.6 | Improved |
| Use EPCC instead of SVM | 2D synthetic classifier · 2D synthetic test set | Average Precision (%): 22.85 -> 86.62 | Improved |
| Use polyhedral acceptance regions rather than a half-space | positive-class classifier · FDDB | Average Precision (%): 37.6 -> 71.9 | Improved |
Closest papers by meaning
- Polyhedral Conic Classifiers for Computer Vision Applications and Open Set Recognition (TPAMI 2019 · similarity 0.97)
- Best Fitting Hyperplanes for Classification (TPAMI 2016 · similarity 0.86)
- "A Simple Approach and Benchmark for 21,000-Category Object Detection" (ECCV 2022 · similarity 0.86)
- Rethinking Open-Set Object Detection: Issues, A New Formulation, and Taxonomy (IJCV 2025 · similarity 0.85)
- ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models (NeurIPS 2019 · similarity 0.85)
- Exploring Orthogonality in Open World Object Detection (CVPR 2024 · similarity 0.84)
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.
