Please use this identifier to cite or link to this item:
Title: Effect of Loss Functions on Domain Adaptation in Semantic Segmentation
Authors: Serdar, Kirman
Güven, Hilmi
Topal, Cihan
Keywords: semantic segmentation
domain adaptation
loss functions
deep learning
computer vision
Issue Date: 2021
Publisher: IEEE
Abstract: In this paper, it is analyzed how different loss functions affect the performance of domain adaptation in the field of semantic segmentation. Semantic segmentation is a pixel-wise classification problem of an image. Large amounts of annotated data are required to train successfully in multi-parameter deep learning architectures. In recent years, several works have demonstrated that synthetic datasets are a good alternative since they are automatically annotated in virtual environments. However, due to the different distribution of source and target datasets, there is a decrease in performance. Domain adaptation methods address this problem by decreasing gap between source and target data. In this study, it is investigated that the effect of Cross-Entropy, Lovasz-Softmax, Dice Coefficient, Tversky and mean Intersection-over-Union Loss functions on domain adaptation in semantic segmentation. For our study, KITTI and Virtual KITTI datasets are used for real and synthetic images respectively. By evaluating the quantitative results, it is observed that the Dice Coefficient is relatively more successful.
Description: 29th IEEE Conference on Signal Processing and Communications Applications (SIU) -- JUN 09-11, 2021 -- ELECTR NETWORK
ISBN: 978-1-6654-3649-6
Appears in Collections:Elektrik-Elektronik Mühendisliği Bölümü Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu

Show full item record

CORE Recommender

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.