Research map / Detection and segmentation / CNN features
Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach
Zongxin Liu, Lijia Yu, Tao Lin, Zhiming Chi, Lijun Zhang
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 ODPV instead of RCPN (10^6 samples) for IoU lower bounds | YOLO verification · COCO val, eps=1/255, tau=0.5 | verification time: 563.5 -> 109.0 (YOLOv3-spp); 618.1 -> 147.2 (YOLO11x) | Improved |
| use ODPV instead of RCPN for certified IoU lower bounds | YOLO verification · COCO val, eps=1/255, tau=0.5 | mean abs. IoU gap to PGD: 0.54 -> 0.49 (YOLO11x) | Improved |
| use ODPV instead of RCPN or DeepPAC for the same 98% guarantee | PAC verification of YOLO · 98% guarantee at 98% confidence | samples required: 11,000,000 -> 37,000 (vs RCPN) | Improved |
| increase perturbation radius from 1/255 to 2/255 (ablation) | ODPV on YOLO11x · COCO val guarantee eval, tau=0.5 | true positive rate: 94.9 -> 85.2 | Hurt |
| increase perturbation radius from 1/255 to 2/255 (ablation) | ODPV on YOLO11x · COCO val guarantee eval, tau=0.5 | certified robust accuracy: 98.9 -> 99.4 | No clear effect |
| add the Part 3 refinement step to the verification (ablation) | ODPV on YOLO11x · COCO val guarantee eval, tau=0.5 | average bounds improvement: 0.10 (eps 1/255); 0.17 (eps 2/255) | Improved |
Closest papers by meaning
- You Only Look Once: Unified, Real-Time Object Detection (CVPR 2016 · similarity 0.87)
- YOLOv10: Real-Time End-to-End Object Detection (NeurIPS 2024 · similarity 0.86)
- Accelerating Non-Maximum Suppression: A Graph Theory Perspective (NeurIPS 2024 · similarity 0.85)
- Mamba YOLO: A Simple Baseline for Object Detection with State Space Model (AAAI 2025 · similarity 0.84)
- YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary (ICLR 2025 · similarity 0.83)
- Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy (NeurIPS 2025 · 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.
