Print Email Facebook Twitter Image-to-Image Translation of Synthetic Samples for Rare Classes Title Image-to-Image Translation of Synthetic Samples for Rare Classes Author Lanzini, Edoardo (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Intelligent Systems) Contributor van Gemert, J.C. (graduation committee) Lengyel, A. (mentor) Bruintjes, R. (mentor) Zarras, A. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2021-07-01 Abstract The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a known challenge for deep learning based classification algorithms, and is the focus of the field of low-shot learning. One potential approach to increase the training data for these rare classes is to augment the limited real data with synthetic samples. This has been shown to help, but the domain shift between real and synthetic hinders the approaches' efficacy when tested on real data. We explore the use of image-to-image translation methods to close the domain gap between synthetic and real imagery for animal species classification in data collected from camera traps: motion-activated static cameras used to monitor wildlife. We use low-level feature alignment between source and target domains to make synthetic data for a rare species generated using a graphics engine more "realistic". Compared against a system augmented with unaligned synthetic data, our experiments show a considerable decrease in classification error rates on a rare species. Subject Computer VisionCamera Trap DatasetStyle TransferGenerative Adversarial Network To reference this document use: http://resolver.tudelft.nl/uuid:a5005048-9af2-424e-a4c6-481c25fbb03f Bibliographical note https://www.cv4animals.com/paper This work was accepted at CV4Animals workshop at CVPR2021, #11 Part of collection Student theses Document type bachelor thesis Rights © 2021 Edoardo Lanzini Files PDF final_elanzini.pdf 2.58 MB Close viewer /islandora/object/uuid:a5005048-9af2-424e-a4c6-481c25fbb03f/datastream/OBJ/view