Comparative study of subset selection methods for rapid prototyping of 3D object detection algorithms

Abstract

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 subset - random 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.

Accepted for MMAR 2023 (27 th International Conference on Methods and Models in Automation and Robotics)

References in corpus (5)

• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
• PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
• PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
• Core-set Sampling for Efficient Neural Architecture Search