AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Neural Distribution Prior for LiDAR Out-of-Distribution Detection

Zizhao Li, Zhengkang Xiang, Jiayang Ao, Feng Liu, Joseph West, Kourosh Khoshelham

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 0 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 Soft Outlier Exposure (SOE) on void points (ablation)NDP-EE · STU valAP: 67.10 -> 74.24Improved
add NDP reweighting on top of static extended energy (ablation)NDP-EE · STU valAP: 58.69 -> 74.24Improved
add Perlin noise OOD samples to void training (ablation)NDP-EE · STU valAP: 2.09 -> 11.03Improved
train on Perlin samples alone and add SOE void regions instead of void-only (ablation)NDP-EE · STU valAP: 2.09 -> 67.10Improved
add learnable NDP to energy score (ablation)Energy score · STU valAP: 56.88 -> 66.54Improved
learnable NDP instead of statistical class prior (ablation)Energy score · STU valAP: 23.87 -> 66.54Improved
learnable NDP instead of Balanced Energy (ablation)Energy score · STU valAP: 57.05 -> 66.54Improved
vary SOE soft label beta from 0.7 to 1.0 (ablation)NDP-EE · STU valAP: 68.00 / 72.73 / 74.24 / 73.06Mixed
NDP embedding size d 16 vs 8 and 32 (ablation)NDP-EE · STU valAP: 70.29 / 74.24 / 70.14Mixed
add NDP with lightweight MinkUNet backbone (ablation)NDP-EE · STU val (MinkUNet)AP: 58.36 -> 70.29Improved
add NDP training to Mask4Former, in-distribution segmentationMask4Former · STU valPQ: 52.73 -> 52.37No clear effect
NDP-EE instead of NDP-Entropy scoreNDP · STU testAP: 29.53 -> 61.31Improved

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