AI Paper Atlas

Research map / Point clouds / Segmentation and detection

AGO-Net: Association-Guided 3D Point Cloud Object Detection Network

Liang Du, Xiaoqing Ye, Xiao Tan, Edward Johns, Bo Chen, Errui Ding, Xiangyang Xue, Jianfeng Feng

TPAMI 2021 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 42 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 CFG object-wise domain adaptation (ablation)PFE baseline · KITTI val Car 3D Moderate (R40)AP3D: 83.03 -> 84.21Improved
add SC-reweight on top of CFG (ablation)AGO-Net · KITTI val Car 3D Moderate (R40)AP3D: 84.21 -> 84.84Improved
add spatial attention only in SC-reweight (ablation)AGO-Net CFG · KITTI val Car 3D Moderate (R40)AP3D: 84.21 -> 84.75Improved
add channel attention only in SC-reweight (ablation)AGO-Net CFG · KITTI val Car 3D Moderate (R40)AP3D: 84.21 -> 84.32Improved
train on real plus conceptual data without adaptation (ablation)baseline · KITTI val Car 3D Moderate (R40)AP3D: 83.03 -> 82.97No clear effect
train on conceptual data only, test on real (ablation)baseline · KITTI val Car 3D Moderate (R40)AP3D: 83.03 -> 72.55Hurt
add conceptual model onto object with close-point removal instead of replacing (ablation)AGO-Net · KITTI val Car 3D Moderate (R40)AP3D: 84.38 -> 84.84Improved
adapt F_box instead of F_class only (ablation)AGO-Net CFG · KITTI val Car 3D Moderate (R40)AP3D: 83.16 -> 84.21Improved
adapt F_box instead of F_box + F_class (ablation)AGO-Net CFG · KITTI val Car 3D Moderate (R40)AP3D: 84.10 -> 84.21No clear effect
add AGO to PointPillarsPointPillars · KITTI val Car 3D Moderate (R11)AP3D: 76.44 -> 78.53Improved
add AGO to SECONDSECOND · KITTI val Car 3D Moderate (R11)AP3D: 77.12 -> 78.82Improved
add deformable conv layer (ablation)AGO-Net without attention · KITTI val Car 3D Moderate (R40)AP3D: 84.21 -> 84.39No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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