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

TL;DR

This paper compares subset selection methods for 3D object detection to improve rapid prototyping, demonstrating that targeted sampling methods like MONSPeC outperform random sampling in transferring results.

Contribution

The paper introduces and empirically evaluates MONSPeC, a new subset selection algorithm, showing its effectiveness over traditional random sampling for 3D object detection.

Findings

MONSPeC outperforms random sampling in subset selection.

Random per class sampling improves transferability of results.

Efficient subset selection reduces training time and environmental impact.

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.