AI Paper Atlas

Research map / Detection and segmentation / CNN features

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration

Guangyu Shen, Siyuan Cheng, Guanhong Tao, Kaiyuan Zhang, Yingqi Liu, Shengwei An, Shiqing Ma, Xiangyu Zhang

NeurIPS 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 4 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
add Gaussian Focus Loss (remove it: DJANGO - GF Loss) (ablation)DJANGO · Traffic Sign Synthesis SSDROC-AUC: 0.7500 -> 1.0000Improved
add Gaussian Focus Loss (ablation)DJANGO · Traffic Sign Synthesis Faster-RCNNROC-AUC: 0.7500 -> 0.8750Improved
add Gaussian Focus Loss (ablation)DJANGO · Traffic Sign Synthesis DETRROC-AUC: 0.7500 -> 0.8750Improved
add label proposal pre-processing (ablation)DJANGO · Traffic Sign Synthesis SSDROC-AUC: 0.6250 -> 1.0000Improved
add label proposal pre-processing (ablation)DJANGO · Traffic Sign Synthesis Faster-RCNNROC-AUC: 0.5000 -> 0.8750Improved
add label proposal pre-processing (ablation)DJANGO · Traffic Sign Synthesis SSDoverhead (s): >3600 -> 859.59Improved
Gaussian Focus Loss on scanning overhead (ablation)DJANGO · Traffic Sign Synthesis SSDoverhead (s): 860.24 -> 859.59No clear effect
warm-up pre-processing added to NC, Pixel, TaborNC/Pixel/Tabor · Traffic Sign Synthesis SSDROC-AUC: 0.6250 -> 0.6641Improved
warm-up pre-processing added to PixelPixel · COCO SSDROC-AUC: 0.6200 -> 0.7000Improved
warm-up pre-processing added to NCNC · DOTA F-RCNNROC-AUC: 0.5625 -> 0.5625No clear effect
DJANGO vs trigger inversion baselines (average)DJANGO · allROC-AUC: 0.592 -> 0.913Improved
DJANGO vs meta classifier MNTDDJANGO · COCO SSDROC-AUC: 0.8144 -> 0.9305Improved

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