Search
Abstract
While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It was shown that simple color transformations already provide a strong baseline, comparable to using more sophisticated style-transfer data augmentation. Further, by constructing an ensemble consisting of models using different backbones and/or augmentation methods, it was possible to improve significantly model performance in terms of overall accuracy and uncertainty estimation under the domain shift setting. The Expected Calibration Error (ECE) on challenging GTA to Cityscapes adaptation was reduced from 4.05 to the competitive value of 1.1. Further, an ensemble of models was utilized in the self-training setting to improve the pseudo-labels generation, which resulted in a significant gain in the final model accuracy, compared to the standard fine-tuning (without ensemble).o
Citations
-
4
CrossRef
-
0
Web of Science
-
2
Scopus
Authors (5)
Cite as
Full text
- Publication version
- Accepted or Published Version
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/IJCNN52387.2021.9533330
- License
- Copyright (2021 IEEE)
Keywords
Details
- Category:
- Conference activity
- Type:
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language:
- English
- Publication year:
- 2021
- Bibliographic description:
- Cygert S., Czyżewski A., Wróblewski B., Słowiński R., Woźniak K.: Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift// / : , 2021,
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/ijcnn52387.2021.9533330
- Sources of funding:
- Verified by:
- Gdańsk University of Technology
seen 86 times
Recommended for you
Modeling nutrient removal and energy consumption in an advanced activated sludge system under uncertainty
- B. Szeląg,
- A. Kiczko,
- E. Zaborowska
- + 2 authors