AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Open-World Semantic Segmentation for LIDAR Point Clouds

Jun Cen, Peng Yun, Shiwei Zhang, Junhao Cai, Di Luan, Mingqian Tang, Ming Liu, Michael Yu Wang

ECCV 2022 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 33 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 the calibration loss L_cal (second-largest score on unknown class) (ablation)REAL on Cylinder3D · SemanticKITTI open-set (val)AUPR: 0 -> 10.0Improved
add the calibration loss L_cal (ablation)REAL on Cylinder3D · SemanticKITTI open-set (val)AUROC: 0 -> 77.5Improved
add unknown object synthesis loss L_syn by resizing objects (ablation)REAL on Cylinder3D · SemanticKITTI open-set (val)AUPR: 10.0 -> 20.8Improved
add unknown object synthesis loss L_syn (ablation)REAL on Cylinder3D · SemanticKITTI open-set (val)AUROC: 77.5 -> 84.9Improved
add unknown object synthesis loss L_syn (ablation)REAL on Cylinder3D · SemanticKITTI open-set (val)mIoU_old: 58.1 -> 57.8No clear effect
use REAL instead of MC-Dropout for open-set scoringCylinder3D · nuScenes open-set (val)AUPR: 14.9 -> 21.2Improved
use REAL instead of MSP for open-set scoringCylinder3D · SemanticKITTI open-set (val)AUPR: 6.7 -> 20.8Improved
use REAL instead of MaxLogit for open-set scoringCylinder3D · SemanticKITTI open-set (val)AUROC: 70.5 -> 84.9Improved
open-set finetuning with REAL on closed-set accuracyCylinder3D · nuScenes open-set (val)mIoU_old: 58.7 -> 56.8Hurt
use pseudo labels from the open-set model on unlabeled old-class points in incremental learningREAL IL · SemanticKITTI 18+1 incremental (val)mIoU: 21.6 -> 64.3Improved
use pseudo labels instead of finetuning only on novel labelsREAL IL · SemanticKITTI 18+1 incremental (val)mIoU_old: 0 -> 65.0Improved
use pseudo labels vs Feature extractionREAL IL · nuScenes 12+4 incremental (val)mIoU: 5.5 -> 74.9Improved

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