AI Paper Atlas

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

Exploring Geometry-Aware Contrast and Clustering Harmonization for Self-Supervised 3D Object Detection

Hanxue Liang, Chenhan Jiang, Dapeng Feng, Xin Chen, Hang Xu, Xiaodan Liang, Wei Zhang, Zhenguo Li, Luc Van Gool

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 66 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 GCC-3D pretraining before fine-tuningCenterPoint-pp · Waymo val (5% labels)AP/L2: 49.30 -> 52.92Improved
add GCC-3D pretraining before fine-tuningCenterPoint-pp · nuScenes val (5% labels)mAP: 25.79 -> 32.75Improved
add GCC-3D pretraining before fine-tuningCenterPoint-voxel · Waymo val (5% labels)AP/L2: 43.13 -> 44.70Improved
add GCC-3D pretraining before fine-tuningCenterPoint-voxel · nuScenes val (100% labels)mAP: 56.19 -> 57.26Improved
add two-stage CenterPoint with GCC-3D pretrainingCenterPoint-voxel 2-stage · Waymo val (20% labels)mAP: 64.63 -> 67.29Improved
add Geometry-Aware Contrast module alone (ablation)CenterPoint-pp · nuScenes val (5% labels)mAP: 25.79 -> 32.56Improved
add Harmonized Pseudo-Instance Clustering module alone (ablation)CenterPoint-pp · Waymo val (5% labels)mAP: 49.30 -> 51.89Improved
combine geometry-aware contrast with harmonized clustering (ablation)GCC-3D CenterPoint-pp · nuScenes val (5% labels)mAP: 32.56 -> 32.75Improved
combine geometry-aware contrast with harmonized clustering (ablation)GCC-3D CenterPoint-pp · Waymo val (5% labels)mAP: 51.89 -> 52.92Improved
replace hard-label contrast (PointContrast) with geometry-aware soft contrast (ablation)CenterPoint-pp · nuScenes val (5% labels)mAP: 30.79 -> 32.56Improved
add harmonization term to DeepCluster-style pseudo-instance clustering (ablation)CenterPoint-pp · nuScenes val (5% labels)mAP: 27.84 -> 30.32Improved
set harmonization weight alpha to 0.1 instead of 0 (ablation)CenterPoint-pp · nuScenes val (100% labels)mAP: 50.48 -> 50.84Improved

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