AI Paper Atlas

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

TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detection

Leyuan Xing, Huanjia Zhang, Dongyu Pan, Hai Wu, Qiming Xia, Kezheng Xiong, Wen Li, Chenglu Wen, Cheng Wang

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection

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 a detection head (joint multi-task training) (ablation)LiSA localization · OxfoLD testposition/orientation error: 0.95m, 1.14 -> 0.89m, 1.06Improved
add ITCL (inter-task contrastive) to joint model (ablation)TACO · OxfoLD testposition error / vehicle AP: 0.89m -> 0.82m; AP 72.54% -> 75.32%Improved
add IDCL (intra-detection contrastive) to joint model (ablation)TACO · OxfoLD testVehicle AP@0.5: 72.54% -> 77.45%Improved
add ILCL (intra-localization contrastive) to joint model (ablation)TACO · OxfoLD testposition error: 0.89m -> 0.76mImproved
combine ITCL, IDCL and ILCL (ablation)TACO · OxfoLD testVehicle AP@0.5: 72.54% -> 81.60%Improved
train jointly instead of detection-only (ablation)TACO · OxfoLD testVehicle AP@0.5: 60.01% -> 81.60%Improved
train jointly instead of localization-only (ablation)TACO · OxfoLD testposition error: 0.95m,1.14 -> 0.72m,0.85Improved
use TACO instead of Cross-stitch multi-task architectureTACO · OxfoLD testposition error: 1.97m -> 0.72mImproved
use TACO instead of LiDARFormerTACO · OxfoLD testposition error / vehicle AP: 0.89m -> 0.72m; 72.54% -> 81.60%Improved
use TACO instead of LiDARFormerTACO · nuScenesposition error: 1.01m -> 0.92mImproved
use TACO instead of LiDARFormerTACO · KITTI-360 Seq. 09Vehicle AP@0.5: 53.21% -> 53.47%Improved
add more training trajectories (4 vs 1) (ablation)TACO · OxfoLD testposition error: 4.32m -> 0.72mImproved

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