AAAI 2024technical0 citations
Target-Free Domain Adaptation through Cross-Adaptation (Student Abstract)
Aleksander Obuchowski, Barbara Klaudel, Piotr Frąckowski, Sebastian Krajna, Wasyl Badyra, Michał Czubenko, Zdzisław Kowalczuk
Abstract
The population characteristics of the datasets related to the same task may vary significantly and merging them may harm performance. In this paper, we propose a novel method of domain adaptation called "cross-adaptation". It allows for implicit adaptation to the target domain without the need for any labeled examples across this domain. We test our approach on 9 datasets for SARS-CoV-2 detection from complete blood count from different hospitals around the world. Results show that our solution is universal with respect to various classification algorithms and allows for up to a 10pp increase in F1 score on average.
BibTeX
@article{Obuchowski_Klaudel_Frąckowski_Krajna_Badyra_Czubenko_Kowalczuk_2024, title={Target-Free Domain Adaptation through Cross-Adaptation (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30490}, DOI={10.1609/aaai.v38i21.30490}, abstractNote={The population characteristics of the datasets related to the same task may vary significantly and merging them may harm performance. In this paper, we propose a novel method of domain adaptation called "cross-adaptation". It allows for implicit adaptation to the target domain without the need for any labeled examples across this domain. We test our approach on 9 datasets for SARS-CoV-2 detection from complete blood count from different hospitals around the world. Results show that our solution is universal with respect to various classification algorithms and allows for up to a 10pp increase in F1 score on average.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Obuchowski, Aleksander and Klaudel, Barbara and Frąckowski, Piotr and Krajna, Sebastian and Badyra, Wasyl and Czubenko, Michał and Kowalczuk, Zdzisław}, year={2024}, month={Mar.}, pages={23602-23603} }