AI Paper Atlas

Research map / Detection and segmentation / Tracking

RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects

Bin Yang, Runsheng Guo, Ming Liang, Sergio Casas, Raquel Urtasun

ECCV 2020 · Detection and segmentation › Tracking · approach: Unified transformer tracking · 157 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 Radar early fusion to LiDAR detector (ablation)RadarNet · nuScenes val, motorcyclesAP@2m: 53.7 -> +1.9Improved
add Radar early fusion to LiDAR detector (ablation)RadarNet · nuScenes val, carsAP@2m: 87.6 -> +0.3Improved
add Radar early fusion (ablation)RadarNet · nuScenes val, carsAVE: -2%No clear effect
add Radar early fusion (ablation)RadarNet · DenseRadar val, 70-100mVehicles AP: 77.5 -> +0.8Improved
add attention-based late fusion after early fusion (ablation)RadarNet · nuScenes val, carsAVE: -14%Improved
add attention-based late fusion after early fusion (ablation)RadarNet · nuScenes val, motorcyclesAVE: -15%Improved
add attention-based late fusion after early fusion (ablation)RadarNet · DenseRadar valADVE: -3% -> -19%Improved
use attention-based late fusion instead of heuristic late fusion (ablation)RadarNet · nuScenes val, carsAVE: -9% -> -14%Improved
use attention-based late fusion instead of heuristic late fusion (ablation)RadarNet · DenseRadar valADVE: -6% -> -19%Improved
add heuristic late fusion after early fusion (ablation)RadarNet · DenseRadar valADVE: -3% -> -6%Improved
fuse LiDAR and Radar versus best prior LiDAR (CBGS)RadarNet · nuScenes val, carsAP: 82.3 -> 84.5Improved
fuse LiDAR and Radar versus best prior LiDAR (CBGS)RadarNet · nuScenes val, motorcyclesAVE: 0.339 -> 0.269Improved

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