AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Crash to Not Crash: Learn to Identify Dangerous Vehicles Using a Simulator

Hoon Kim, Kangwook Lee, Gyeongjo Hwang, Changho Suh

AAAI 2019 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 59 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 on synthetic GTACrash instead of real YouTubeCrashCNN (RGB + B.Box) · YouTubeCrash testAUC: 0.8730 -> 0.9086Improved
train on GTACrash instead of YouTubeCrash5-layer NN (B.Box-size) · YouTubeCrash testAUC: 0.8766 -> 0.8812Improved
add RGB channels to bounding box input (RGB+B.Box vs B.Box), GTACrash (ablation)CNN · YouTubeCrash testAUC: 0.8992 -> 0.9086Improved
use RGB+B.Box complex model when trained on small real dataCNN (RGB + B.Box) · YouTubeCrash testAUC: 0.8766 -> 0.8730Hurt
add label adaptation via CTRA path prediction (ablation)CNN (RGB + B.Box) on GTACrash · YouTubeCrash testAUC: 0.9086 -> 0.9154Improved
add feature adaptation (backward CycleGAN mapping) (ablation)CNN (RGB + B.Box) on GTACrash · YouTubeCrash testAUC: 0.9086 -> 0.9102Improved
add both label and feature adaptation (ablation)CNN (RGB + B.Box) on GTACrash · YouTubeCrash testAUC: 0.9086 -> 0.9164Improved
add adaptation with ResNet50 backbone (ablation)CNN (RGB + B.Box) ResNet50 · YouTubeCrash testAUC: 0.9097 -> 0.9241Improved
use GTACrash-trained model vs real-trained at TTC 1.6-1.8 sCNN (RGB + B.Box) · YouTubeCrash testmissed detection rate: -18.5%Improved
use GTACrash-trained complex model at very short TTC (<0.8 s)CNN (RGB + B.Box) · YouTubeCrash testmissed detection rateHurt
use all three frames per sample (ablation)CNN (RGB + B.Box) · YouTubeCrash testAUCImproved

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