Papers › Radar+RGB Attentive Fusion for Robust Object Detection in Autonomous Vehicles

Radar+RGB Attentive Fusion for Robust Object Detection in Autonomous Vehicles

31 Aug 2020arXiv:2008.13642archive 2025-07-28

Ritu Yadav, Axel Vierling, Karsten Berns

This paper presents two variations of architecture referred to as RANet and BIRANet. The proposed architecture aims to use radar signal data along with RGB camera images to form a robust detection network that works efficiently, even in variable lighting and weather conditions such as rain, dust, fog, and others. First, radar information is fused in the feature extractor network. Second, radar points are used to generate guided anchors. Third, a method is proposed to improve region proposal network targets. BIRANet yields 72.3/75.3% average AP/AR on the NuScenes dataset, which is better than the performance of our base network Faster-RCNN with Feature pyramid network(FFPN). RANet gives 69.6/71.9% average AP/AR on the same dataset, which is reasonably acceptable performance. Also, both BIRANet and RANet are evaluated to be robust towards the noise.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous VehiclesObject DetectionRegion ProposalRobust Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection nuScenes BIRANet(RGB+Radar) AP(l) 76.9 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AP(m) 70.1 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AP(s) 53.5 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AP50 88.9 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AP75 84.3 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AP85 65.7 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AR 75.3 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AR(l) 79.8 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AR(m) 73.2 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) AR(s) 56.2 #1 of 2 Archive leaderboard report
Object Detection nuScenes BIRANet(RGB+Radar) MAP 72.3 #1 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AP(l) 73.3 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AP(m) 67.8 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AP(s) 44.8 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AP50 83.9 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AP75 80.1 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AP85 64.4 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AR 71.9 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AR(l) 76.2 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AR(m) 70.9 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) AR(s) 47.3 #2 of 2 Archive leaderboard report
Object Detection nuScenes RANet(Radar) MAP 69 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections