AI Paper Atlas

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

GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation

Yifan Zhang, Qijian Zhang, Zhiyu Zhu, Junhui Hou, Yixuan Yuan

IJCV 2023 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 81 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 GLENet label uncertainty into KL loss (ablation)Voxel R-CNN with KL loss · KITTI val3D AP R40 moderate (%): 85.25 -> 85.76Improved
train with KL loss only (ablation)Voxel R-CNN · KITTI val3D AP R40 moderate (%): 85.29 -> 85.25No clear effect
add variance voting (ablation)Voxel R-CNN with KL loss and LU · KITTI val3D AP R40 moderate (%): 85.76 -> 85.91Improved
add UAQE module (ablation)GLENet-VR · KITTI val3D AP R40 moderate (%): 85.91 -> 86.10Improved
use GLENet uncertainty instead of points-number heuristic (ablation)GLENet-VR · KITTI val3D AP R40 moderate (%): 85.58 -> 86.10Improved
use GLENet uncertainty instead of convex hull heuristic (ablation)GLENet-VR · KITTI val3D AP R40 moderate (%): 85.45 -> 86.10Improved
add occlusion augmentation to GLENet (ablation)GLENet · KITTI val3D AP R40 moderate (%): 85.52 -> 86.10Improved
add context encoder to GLENet (ablation)GLENet · KITTI val3D AP R40 moderate (%): 85.31 -> 86.10Improved
add absolute coordinates to GLENet input (ablation)GLENet · KITTI val3D AP R40 moderate (%): 86.10 -> 85.66No clear effect
increase latent dimension from 2 to 8 (ablation)GLENet · KITTI val3D AP R40 moderate (%): 84.69 -> 86.15Improved
increase sampling times from 4 to 30 (ablation)GLENet · KITTI val3D AP R40 moderate (%): 85.11 -> 86.10Improved
integrate GLENet into SECONDSECOND · KITTI val3D AP R40 moderate (%): 81.99 -> 84.11Improved

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