AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Voxel Transformer for 3D Object Detection

Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai, Jiashi Feng, Xiaodan Liang, Hang Xu, Chunjing Xu

ICCV 2021 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 542 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
replace SECOND 3D conv backbone with VoTrSECOND · Waymo val vehicle LEVEL_13D mAP: 67.94 -> 68.99 (+1.05%)Improved
replace PV-RCNN 3D conv backbone with VoTrPV-RCNN · Waymo val vehicle LEVEL_13D mAP: 74.06 -> 74.95 (+3.26%)Improved
use VoTr backbone for far objectsVoTr-TSD · Waymo val vehicle 30-50m and 50m-Inf3D mAP: +3.37% (30-50m), +4.83% (50m-Inf)Improved
replace SECOND backbone with VoTrSECOND · KITTI val car moderateAP_3D: 76.48 -> 78.27 (+1.79%)Improved
replace PV-RCNN backbone with VoTrPV-RCNN · KITTI val car moderateAP_3D: 83.69 -> 84.04 (+0.35%)Improved
replace PV-RCNN backbone with VoTrPV-RCNN · KITTI test car easyAP_3D: 90.25 -> 89.90Hurt
replace PV-RCNN backbone with VoTrPV-RCNN · KITTI test car hardAP_3D: 76.82 -> 79.14Improved
add Dilated Attention to Local Attention (ablation)VoTr-SSD · KITTI val car moderateAP_3D: 75.48 -> 78.27 (+2.79%)Improved
add dropout with probability 0.3 (ablation)VoTr-SSD · KITTI val car moderateAP_3D: 78.27 -> 69.75 (-8.52%)Hurt
add dropout with probability 0.1 (ablation)VoTr-SSD · KITTI val car moderateAP_3D: 78.27 -> 75.97Hurt
increase attending voxels from 24 to 48 (ablation)VoTr-SSD · KITTI val car moderateAP_3D: 77.08 -> 78.27 (+1.19%)Improved
replace conv backbone with VoTr (parameters)SECOND · KITTImodel parameters: 5.3M -> 4.8MImproved

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