SELECT selects annotation voxels using feature-variance ranking, Monte Carlo dropout uncertainty, and a class-balance entropy criterion, and reports mIoU gains over prior active learning baselines on three LiDAR benchmarks.
SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
3D semantic segmentation is one of the key tasks for autonomous driving system. Recently, deep learning models for 3D semantic segmentation task have been widely researched, but they usually require large amounts of training data. However, the present datasets for 3D semantic segmentation are lack of point-wise annotation, diversiform scenes and dynamic objects. In this paper, we propose the SemanticPOSS dataset, which contains 2988 various and complicated LiDAR scans with large quantity of dynamic instances. The data is collected in Peking University and uses the same data format as SemanticKITTI. In addition, we evaluate several typical 3D semantic segmentation models on our SemanticPOSS dataset. Experimental results show that SemanticPOSS can help to improve the prediction accuracy of dynamic objects as people, car in some degree. SemanticPOSS will be published at \url{www.poss.pku.edu.cn}.
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SELECT: A Submodular Approach for Active LiDAR Semantic Segmentation
SELECT selects annotation voxels using feature-variance ranking, Monte Carlo dropout uncertainty, and a class-balance entropy criterion, and reports mIoU gains over prior active learning baselines on three LiDAR benchmarks.