ML Anthology

Target-Free Domain Adaptation Through Cross-Adaptation (Student Abstract)

Aleksander Obuchowski, Barbara Klaudel, Piotr Frackowski, Sebastian Krajna, Wasyl Badyra, Michal Czubenko, Zdzislaw Kowalczuk
AAAI 2024 pp. 23602-23603
doi:10.1609/AAAI.V38I21.30490 /aaai/2024/obuchowski2024aaai-target/

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.

PDF AAAI Semantic Scholar

Cite

Text

Obuchowski et al. "Target-Free Domain Adaptation Through Cross-Adaptation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30490

Markdown

[Obuchowski et al. "Target-Free Domain Adaptation Through Cross-Adaptation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/obuchowski2024aaai-target/) doi:10.1609/AAAI.V38I21.30490

BibTeX

@inproceedings{obuchowski2024aaai-target,
  title     = {{Target-Free Domain Adaptation Through Cross-Adaptation (Student Abstract)}},
  author    = {Obuchowski, Aleksander and Klaudel, Barbara and Frackowski, Piotr and Krajna, Sebastian and Badyra, Wasyl and Czubenko, Michal and Kowalczuk, Zdzislaw},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23602-23603},
  doi       = {10.1609/AAAI.V38I21.30490},
  url       = {https://mlanthology.org/aaai/2024/obuchowski2024aaai-target/}
}