Target-Free Domain Adaptation through Cross-Adaptation (Student 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.

Authors

• Aleksander Obuchowski Polish-Japanese Academy of Information Technology
• Barbara Klaudel Gdańsk University of Technology
• Piotr Frąckowski Gdańsk University of Technology
• Sebastian Krajna Gdańsk University of Technology
• Wasyl Badyra Gdańsk University of Technology
• Michał Czubenko Gdańsk University of Technology
• Zdzisław Kowalczuk Gdańsk University of Technology

Keywords

• Diversity And Inclusion
• Domain Adaptation
• Healthcare
• Transfer Learning