AI Paper Atlas

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

NeurIPS 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Randomized smoothing certification

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 changedWhereMeasuredEffect
switch from objectness sorting to location sorting (ablation)median smoothing · MS-COCOAP@50: +4.52% (best case)Improved
switch to location sorting with location binning (ablation)median smoothing · MS-COCOcertified AP@50: 3.23% -> 2.67%Hurt
add label binning (ablation)median smoothing · MS-COCOAP@50: 21.51% -> 29.75%Improved
add label binning (ablation)median smoothing · MS-COCOcertified AP@50: 1.24% -> 3.32%Improved
add location binning (ablation)median smoothing · MS-COCOAP@50: 21.51% -> 28.90%Improved
combine location and label binning (ablation)median smoothing · MS-COCOcertified AP@50: 3.32% -> 4.18%Improved
combine location and label binning (ablation)median smoothing · MS-COCOAP@50: 29.75% -> 32.04%Improved
remove DnCNN denoiser (no binning) (ablation)median smoothing · MS-COCOAP@50: 21.51% -> 5.85%Hurt
remove DnCNN denoiser (no binning) (ablation)median smoothing · MS-COCOcertified AP@50: 1.24% -> 0.14%Hurt
remove denoiser (location+label binning) (ablation)median smoothing · MS-COCOcertified AP@50: 4.18% -> 0.44%Hurt
use Mask RCNN base detector instead of YOLOv3 (ablation)median smoothing · MS-COCOcertified AP@50: 4.21% -> 1.67%Hurt
use Faster RCNN base detector instead of YOLOv3 (ablation)median smoothing · MS-COCOcertified AP@50: 4.21% -> 1.54%Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy