Research map / Adversarial robustness and security / Certified and empirical robustness
Detection as Regression: Certified Object Detection with Median Smoothing
Ping-yeh Chiang, Michael Curry, Ahmed Abdelkader, Aounon Kumar, John Dickerson, Tom Goldstein
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 |
|---|---|---|---|
| switch from objectness sorting to location sorting (ablation) | median smoothing · MS-COCO | AP@50: +4.52% (best case) | Improved |
| switch to location sorting with location binning (ablation) | median smoothing · MS-COCO | certified AP@50: 3.23% -> 2.67% | Hurt |
| add label binning (ablation) | median smoothing · MS-COCO | AP@50: 21.51% -> 29.75% | Improved |
| add label binning (ablation) | median smoothing · MS-COCO | certified AP@50: 1.24% -> 3.32% | Improved |
| add location binning (ablation) | median smoothing · MS-COCO | AP@50: 21.51% -> 28.90% | Improved |
| combine location and label binning (ablation) | median smoothing · MS-COCO | certified AP@50: 3.32% -> 4.18% | Improved |
| combine location and label binning (ablation) | median smoothing · MS-COCO | AP@50: 29.75% -> 32.04% | Improved |
| remove DnCNN denoiser (no binning) (ablation) | median smoothing · MS-COCO | AP@50: 21.51% -> 5.85% | Hurt |
| remove DnCNN denoiser (no binning) (ablation) | median smoothing · MS-COCO | certified AP@50: 1.24% -> 0.14% | Hurt |
| remove denoiser (location+label binning) (ablation) | median smoothing · MS-COCO | certified AP@50: 4.18% -> 0.44% | Hurt |
| use Mask RCNN base detector instead of YOLOv3 (ablation) | median smoothing · MS-COCO | certified AP@50: 4.21% -> 1.67% | Hurt |
| use Faster RCNN base detector instead of YOLOv3 (ablation) | median smoothing · MS-COCO | certified AP@50: 4.21% -> 1.54% | Hurt |
Closest papers by meaning
- Certified Adversarial Robustness via Randomized Smoothing (ICML 2019 · similarity 0.88)
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (NeurIPS 2019 · similarity 0.88)
- Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models (NeurIPS 2024 · similarity 0.87)
- Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness (NeurIPS 2024 · similarity 0.87)
- Average Certified Radius is a Poor Metric for Randomized Smoothing (ICML 2025 · similarity 0.87)
- Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences (NeurIPS 2024 · similarity 0.86)
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.
