• Home
  • Search
  • Effect of Loss Functions on Domain Adaptation in Semantic Segmentation
  • https://doi.org/10.1109/siu53274.2021.9477825Copy DOI Icon

Effect of Loss Functions on Domain Adaptation in Semantic Segmentation

  • Jun 9, 2021
  • Kirman Serdar +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
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.

Similar Papers
  • Research Article
  • Citations42

Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Suhyeon Lee +3
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • Book Chapter
  • Citations1

Consistency Regularization for Unsupervised Domain Adaptation in Semantic Segmentation

  • Jan 01, 2022
  • Sebastian Scherer +2
  • Book Chapter

Unsupervised Domain Adaptation for Semantic Segmentation with Global and Local Consistency

  • Jan 01, 2022
  • Xiangxuan Shan +5
  • Conference Article
  • Citations20

Source Free Domain Adaptation for Semantic Segmentation via Distribution Transfer and Adaptive Class-Balanced Self-Training

  • Jul 18, 2022
  • Cheng-Yu Yang +2
  • Research Article
  • Citations4

Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation

  • Jan 01, 2021
  • SSRN Electronic Journal
  • Daehan Kim +3
  • Research Article
  • Citations17

DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yuxiang Cai +4
  • Research Article
  • Citations11

Entropy-weighted reconstruction adversary and curriculum pseudo labeling for domain adaptation in semantic segmentation

  • Jul 26, 2022
  • Neurocomputing
  • Xiwen Bi +3
  • Conference Article
  • Citations1567

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

  • Dec 03, 2018
  • Tuan-Hung Vu +4
  • Conference Article
  • Citations13

Towards Unsupervised Online Domain Adaptation for Semantic Segmentation

  • Jan 01, 2022
  • Yevhen Kuznietsov +2
  • Book Chapter

Unsupervised Domain Adaptation for Semantic Segmentation with Unstable Category Feature Enhancement

  • Oct 21, 2025
  • Frontiers in artificial intelligence and applications
  • Xuewei Li +5
  • Conference Article
  • Citations261

Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation

  • Oct 01, 2019
  • Jaehoon Choi +2
  • Research Article
  • Citations57

IDDA: A Large-Scale Multi-Domain Dataset for Autonomous Driving

  • Jul 02, 2020
  • IEEE Robotics and Automation Letters
  • Emanuele Alberti +3
  • Research Article
  • Citations2

Domain adaptation for semantic segmentation of road scenes via two-stage alignment of traffic elements

  • Oct 18, 2024
  • Neurocomputing
  • Yuan Gao +4
  • Research Article
  • Citations27

Knowledge based domain adaptation for semantic segmentation

  • Dec 27, 2019
  • Knowledge-Based Systems
  • Yuxiao Zhang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.