Are CNNs that Learn to Predict Image Statistics Invariant to Domain Shifts?
J.P. Biesheuvel (TU Delft - Electrical Engineering, Mathematics and Computer Science)
T.J. Viering – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Ziqi Wang – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
David M.J. Tax – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
M Loog – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
Klaus Hildebrandt – Graduation committee member (TU Delft - Computer Graphics and Visualisation)
More Info
expand_more
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
Yes, convolutional neural networks are domain-invariant, albeit to some limited extent. We explored the performance impact of domain shift for convolutional neural networks. We did this by designing new synthetic tasks, for which the network’s task was to map images to their mean, median, standard deviation, and variance pixel intensities. We find that the performance drop due to domain shift is related to the shift in pixel values between source and target domain. Colour space transformations seemed to notably impact the network’s performance, opposed to geometric transformations. For the last domain shift we find that the network manages to beat a baseline, from which we can conclude the domain shift is not too severe. Additionally, the findings reveal a less dominant role for feature transferability, for our synthetic regression tasks.