AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

Jinqing Zhang, Yanan Zhang, Qingjie Liu, Yunhong Wang

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 47 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 SA-BEVPool (filter background virtual points) to BEVDepth (ablation)BEVDepth · nuScenes val (ResNet-50)mAP / NDS: 0.330 -> 0.340 mAP, 0.436 -> 0.449 NDSImproved
add BEV-Paste augmentation on top of SA-BEVPool (ablation)BEVDepth · nuScenes val (ResNet-50)mAP / NDS: 0.340 -> 0.354 mAP, 0.449 -> 0.464 NDSImproved
add MSCT head on top of pool and paste (ablation)BEVDepth · nuScenes val (ResNet-50)mAP / NDS: 0.354 -> 0.365 mAP, 0.464 -> 0.483 NDSImproved
apply SA-BEVPool and BEV-Paste to BEVDetBEVDet · nuScenes val (ResNet-50)mAP: 0.278 -> 0.304Improved
apply SA-BEVPool and BEV-Paste to BEVStereoBEVStereo · nuScenes val (ResNet-50)mAP: 0.349 -> 0.364Improved
raise semantic threshold T_S from 0.25 to 0.50 (ablation)SA-BEVPool · nuScenes val (ResNet-50)mAP / NDS: 0.340 -> 0.329 mAP, 0.449 -> 0.432 NDSHurt
paste more frames in BEV-Paste (N_P from 1 to 2) (ablation)BEV-Paste · nuScenes val (ResNet-50)NDS: 0.453 -> 0.452No clear effect
add extra BEV data augmentation to the pasted frame (ablation)BEV-Paste · nuScenes val (ResNet-50)NDS: 0.453 -> 0.464Improved
add multi-task distillation module to the head (ablation)MSCT head · nuScenes val (ResNet-50)NDS: 0.464 -> 0.468Improved
use multi-scale image features in the head (ablation)MSCT head · nuScenes val (ResNet-50)NDS: 0.464 -> 0.478Improved
SA-BEV versus BEVStereo with V2-99 on test setmulti-view 3D detection · nuScenes testmAAE: 0.138 -> 0.139Hurt
SA-BEV versus BEVStereo on val with ConvNeXt-Bmulti-view 3D detection · nuScenes valmAP: 0.478 -> 0.479No clear effect

Later papers that compared with this method

2 later accepted papers report SA-BEV as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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