AI Paper Atlas

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

CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection

Yingjie Wang, Jiajun Deng, Yuenan Hou, Yao Li, Yu Zhang, Jianmin Ji, Wanli Ouyang, Yanyong Zhang

NeurIPS 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 0 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 CFD module (soft cluster-to-BEV diffusion) (ablation)BEV baseline · WOD val 20%mAPH/L2: 60.5 -> 61.9Improved
add imitation loss on top of CFD (ablation)CluB · WOD val 20%mAPH/L2: 61.9 -> 62.5Improved
add CQG module (ablation)BEV baseline · WOD val 20%mAPH/L2: 60.5 -> 61.0Improved
add direction loss to CQG (ablation)CluB · WOD val 20%mAPH/L2: 61.0 -> 61.6Improved
combine all four components (ablation)BEV baseline · WOD val 20%mAPH/L2: 60.5 -> 63.9Improved
replace direct concatenation with 2D convolution in CFD (ablation)CFD module · WOD val VehicleAPH/L2: 61.9 -> 61.4Hurt
replace concatenation with class-agnostic max pooling (ablation)CFD module · WOD val Vehicle vs PedestrianAPH/L2: 61.9 -> 61.0 (Veh), 63.0 -> 63.4 (Ped)Mixed
make diffusion class-aware (ablation)CFD max pooling · WOD val VehicleAPH/L2: 61.0 -> 62.9Improved
make diffusion class-aware (ablation)CFD max pooling · WOD val PedestrianAPH/L2: 63.4 -> 64.4Improved
add cluster branch with KNN-4 aggregation (ablation)BEV detector · WOD val PedestrianAPH/L2: 60.4 -> 64.3Improved
use KNN-8 instead of KNN-4 aggregation (ablation)cluster branch · WOD val PedestrianAPH/L2: 64.3 -> 59.9Hurt
use KNN-8 instead of KNN-4 aggregation (ablation)cluster branch · WOD val VehicleAPH/L2: 61.4 -> 63.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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