The relation between object area and accuracy for a modern mobile convolutional object detector

Bachelor Thesis (2018)
Author(s)

M.S.C. Rijlaarsdam (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

J.C. Van Gemert – Mentor

O.S. Kayhan – Mentor

Miriam Huijser – Mentor

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2018 Matthijs Rijlaarsdam
More Info
expand_more
Publication Year
2018
Language
English
Copyright
© 2018 Matthijs Rijlaarsdam
Graduation Date
01-07-2018
Awarding Institution
Delft University of Technology
Sponsors
Aiir Innovations
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Object detectors, much like humans, perform less well on small than on large objects. Because of this, the object size distribution of a dataset influences the average precision a network achieves on that dataset. Therefore, the object size/precision curve of a network might be a better way to compare convolutional object detectors than the average precision over an entire dataset. In this paper we measure the relationship between object size and accuracy
for a modern mobile convolutional object detector. We verify that this relationship holds for a different dataset, and that the dataset object size distribution influences the average precision over the entire dataset. We conclude that the object size/accuracy curve might contain more information about a network’s performance than the average precision over an entire dataset.

Files

Main.pdf
(pdf | 0.782 Mb)
License info not available