On the Sensitivity of Object Detectors to Background Changes

Master thesis (2024)

Authors

M. de Schipper Electrical Engineering, Mathematics and Computer Science

Contributors

J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS (mentor)
J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS (graduation committee member)
C.C.S. Liem (graduation committee member)
O. Strafforello Pattern Recognition and Bioinformatics - EEMCS (mentor)
X. Liu Pattern Recognition and Bioinformatics - EEMCS (mentor)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
More Info
expand_more

Published Date

17-07-2024

Language

English

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.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Object detectors have come a long way and are used for various applications. In pictures and videos, an object detector must deal with the background. In some settings, this background is indicative of the object; in others, it’s not and can even be disruptive. For models trained on data containing correlations between objects and backgrounds (background bias), it makes sense that changing the background can disrupt learned correlations. This paper is interested in how sensitive object detectors are to background changes, specifically when the training data does not contain correlations between objects and backgrounds. Models were trained on carefully controlled synthetic data, so only the backgrounds differed and correlations could be controlled. The results show that models perform better when tested with seen backgrounds than unseen backgrounds. This performance difference diminishes when the model is trained on more unique backgrounds.