• Home
  • Search
  • Empirical Generalization Study: Unsupervised Domain Adaptation vs. Domain Generalization Methods for Semantic Segmentation in the Wild
  • Open Access IconOpen Access
  • Cite Icon19
  • https://doi.org/10.1109/wacv56688.2023.00057Copy DOI Icon

Empirical Generalization Study: Unsupervised Domain Adaptation vs. Domain Generalization Methods for Semantic Segmentation in the Wild

  • Jan 1, 2023
  • Fabrizio J Piva +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

For autonomous vehicles and mobile robots to safely operate in the real world, i.e., the wild, scene understanding models should perform well in the many different scenarios that can be encountered. In reality, these scenarios are not all represented in the model’s training data, leading to poor performance. To tackle this, current training strategies attempt to either exploit additional unlabeled data with unsupervised domain adaptation (UDA), or to reduce overfitting using the limited available labeled data with domain generalization (DG). However, it is not clear from current literature which of these methods allows for better generalization to unseen data from the wild. Therefore, in this work, we present an evaluation framework in which the generalization capabilities of state-of-the-art UDA and DG methods can be compared fairly. From this evaluation, we find that UDA methods, which leverage unlabeled data, outperform DG methods in terms of generalization, and can deliver similar performance on unseen data as fully-supervised training methods that require all data to be labeled. We show that semantic segmentation performance can be increased up to 30% for a priori unknown data without using any extra labeled data.

Similar Papers
  • Research Article
  • Citations31

PCLUDA: A Pseudo-Label Consistency Learning- Based Unsupervised Domain Adaptation Method for Cross-Domain Optical Remote Sensing Image Retrieval

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Dongyang Hou +3
  • Research Article
  • Citations28

Multi-modal unsupervised domain adaptation for semantic image segmentation

  • Jan 02, 2023
  • Pattern Recognition
  • Sijie Hu +3
  • Conference Article
  • Citations79

Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation

  • Oct 01, 2021
  • Guile Wu +1
  • Book Chapter

Unsupervised Domain Adaptation Using Temporal Association for Segmentation and Its Application to C. elegans Time-Lapse Images

  • Jan 01, 2022
  • Hiroaki Nozaki +1
  • Research Article
  • Citations7

Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets.

  • Sep 01, 2024
  • Radiology. Artificial intelligence
  • Hao Li +18
  • Research Article
  • Citations2

Orchard Areas Segmentation in Remote Sensing Images via Class Feature Aggregate Discriminator

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Ming Liu +4
  • Conference Article
  • Citations1

Robust Speech-Age Estimation Using Local Maximum Mean Discrepancy Under Mismatched Recording Conditions

  • Dec 13, 2021
  • Naohiro Tawara +4
  • Research Article
  • Citations22

Divide-and-Regroup Clustering for Domain Adaptive Person Re-identification

  • Jun 28, 2022
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zhengdong Hu +3
  • Abstract

Unsupervised Domain Adaptation of Auto-Segmentation on Multi-Source MRIs

  • Sep 29, 2023
  • International Journal of Radiation Oncology*Biology*Physics
  • W Zhang +4
  • Conference Article

Unsupervised Domain Adaptation Fault Diagnosis Method Using Weight-Based Mask Network

  • Oct 12, 2023
  • Youzhong Xu +3
  • Conference Article
  • Citations7

Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection

  • Jan 01, 2021
  • Tobias Scheck +2
  • Book Chapter
  • Citations21

Domain Adaptive Nuclei Instance Segmentation and Classification via Category-Aware Feature Alignment and Pseudo-Labelling

  • Jan 01, 2022
  • Canran Li +6
  • Conference Article
  • Citations8

Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification

  • Aug 30, 2021
  • Dongchao Yang +2
  • Research Article
  • Citations2

Rethinking unsupervised domain adaptation for semantic segmentation

  • Oct 01, 2024
  • Pattern Recognition Letters
  • Zhijie Wang +2
  • Research Article
  • Citations24

Semi-supervised domain adaptation for segmentation models on different monitoring settings

  • May 01, 2023
  • Automation in Construction
  • Yeji Hong +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.