Supervoxel-based and Cost-Effective Active Learning for Point Cloud Semantic Segmentation

Ye, Shanding; Fu, Yongjian; Lin, Hu; Yin, Zhe; Pan, Zhijie

doi:10.1109/itsc55140.2022.9922046

Cited by 1 publication

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are based on ensemble of models, collecting their results and adding a sample to the dataset if there is a significant difference between the results of the models. As for processing point clouds, existing AL approaches, [13] do not focus directly on object detection tasks, but on semantic segmentation of point clouds. Other tasks, where selecting a subset of the training set is useful, include Neural Architecture Search (NAS) or Hyperparameter Optimisation (HO).…”

Section: B Selecting Dataset Subsetmentioning

confidence: 99%

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

Lis

Kryjak

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To address these challenges, one can check the effectiveness of different models by training on a subset of the original training set. In this paper, we present a comparison of three algorithms for selecting such a subsetrandom sampling, random per class sampling, and our proposed MONSPeC (Maximum Object Number Sampling per Class). We provide empirical evidence for the superior effectiveness of random per class sampling and MONSPeC over basic random sampling. By replacing random sampling with one of the more efficient algorithms, the results obtained on the subset are more likely to transfer to the results on the entire dataset. The code is available at: https://github.com/vision-agh/monspec.

show abstract

Section: B Selecting Dataset Subsetmentioning

confidence: 99%