AI Paper Atlas

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

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

Peiyan Dong, Zhenglun Kong, Xin Meng, Pinrui Yu, Yifan Gong, Geng Yuan, Hao Tang, Yanzhi Wang

NeurIPS 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 2 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
insert global attention (GA) after local attention in backbone (ablation)HotBEV-nano · nuScenes valNDS: 0.396 -> 0.443Improved
insert global attention (GA) after local attention in backbone (ablation)HotBEV-nano · nuScenes valmAP: 0.328 -> 0.337Improved
add a second GA block (ablation)HotBEV-nano · nuScenes valFPS: 23.7 -> 21.4Hurt
replace GA with semantic-augmented module (SAM) (ablation)HotBEV-nano · nuScenes valNDS: 0.447 -> 0.455Improved
replace GA with SAM (ablation)HotBEV-nano · nuScenes valmAP: 0.340 -> 0.350Improved
replace GA with SAM (ablation)HotBEV-nano · nuScenes valFPS: 21.4 -> 24.5Improved
finest granularity G=2 in latency model (ablation)HOB backbone · nuScenes valFPSHurt
coarsest granularity G=64 (ablation)HOB backbone · nuScenes valmAPHurt
HOB-tiny vs ResNet50 baselines at 256x704 (BEVDepth)HotBEV · nuScenes valNDS: 0.475 -> 0.487Improved
HOB-tiny vs BEVDet at 256x704HotBEV · nuScenes valmAP: 0.298 -> 0.362Improved
larger input resolution 512x1408 for HOB-tinyHotBEV · nuScenes valNDS: 0.487 -> 0.512Improved
scale HOB-nano to HOB-base at 256x704HotBEV · nuScenes valNDS: 0.455 -> 0.506Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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