AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Naturalistic Physical Adversarial Patch for Object Detectors

Yu-Chih-Tuan Hu, Bo-Han Kung, Daniel Stanley Tan, Jun-Cheng Chen, Kai-Lung Hua, Wen-Huang Cheng

ICCV 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 207 citations (OpenAlex)

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
train with in-plane rotation (ablation)Ours-YOLOv4tiny · INRIA, rotation testmAP (%): 13.42 -> 10.16Improved
train with all transformations (ablation)Ours-YOLOv4tiny · INRIA, all-transformations testmAP (%): 63.37 -> 60.44Hurt
train with random translation (ablation)Ours-YOLOv4tiny · INRIA, translation testmAP (%): 30.15 -> 31.63Improved
train with random occlusion (ablation)Ours-YOLOv4tiny · INRIA, occlusion testmAP (%): 34.92 -> 37.25Mixed
increase patch scale from 0.05 to 0.3 (ablation)Ours-YOLOv4tiny · INRIA 0.0-1.0AP (%): 95.04 -> 1.64Improved
larger-pedestrian subset vs small (patch scale 0.1) (ablation)Ours-YOLOv4tiny · INRIA 0.2-1.0 vs 0.0-0.2AP (%): 75.48 -> 55.17Mixed
train on INRIA and MPII mix instead of INRIA only (ablation)Ours-YOLOv4tiny · INRIA testmAP (%): 8.67 -> 2.69Hurt
replace BigGAN with StyleGAN2 generator (ablation)Ours-YOLOv4tiny · INRIAmAP (%): 8.67 -> 34.34Mixed
use GAN latent-space patch vs Adversarial Patches pixel-space baselineOurs-YOLOv4tiny · INRIA, victim YOLOv4tinymAP (%): 3.25 -> 8.67Hurt
use class dog patch vs bulbul patch (ablation)Ours-YOLOv4tiny · INRIA, victim YOLOv4tinymAP (%): 8.67 -> 24.36Mixed

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