Unsupervised Day-Night Domain Adaptation with a Physics Prior for Image Classification
G.D. Brouwer (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Attila Lengyel – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
J.C. van Gemert – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
Ricardo Guerra Marroquim – 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
While deep neural networks show great potential for being part of safety-critical applications such as autonomous driving, covering their sensitivity to illumination shifts by adding training data is of- ten non-trivial. The undesired illumination shift between train and test data can be addressed by domain adaptation methods. Recent work [9] has demonstrated performance improvements with a novel zero-shot domain adaptation setting by in- troducing a physics-based visual inductive prior - a trainable Color Invariant Convolution (CIConv) layer - aiming to transform its input to a more do- main invariant representation.
We compare the performance of image classifica- tion for day-night domain adaptation in the zero- shot and the unsupervised setting, and explore the effectiveness of using CIConv in both settings. We show that unsupervised domain adaptation reduces the day-night distribution shift similarly to CIConv in the zero-shot setting. We demonstrate improved performance when CIConv and unsupervised day- night domain adaptation are combined.