Print Email Facebook Twitter Unsupervised Day-Night Domain Adaptation with a Physics Prior for Image Classification Title Unsupervised Day-Night Domain Adaptation with a Physics Prior for Image Classification Author Brouwer, Gees (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Lengyel, A. (mentor) van Gemert, J.C. (mentor) Marroquim, Ricardo (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-01-28 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. To reference this document use: http://resolver.tudelft.nl/uuid:7ea0396b-1bfa-4ebe-b976-b8432ccbcdff Part of collection Student theses Document type bachelor thesis Rights © 2022 Gees Brouwer Files PDF research_paper_gees_brouwer.pdf 1.12 MB Close viewer /islandora/object/uuid:7ea0396b-1bfa-4ebe-b976-b8432ccbcdff/datastream/OBJ/view