RODA-OOD: Robust Domain Adaptation from Out-of-Distribution Data

Jaekyun Jeong, Mangyu Lee, Sunguk Yun, Keejun Han and Jungeun Kim ()
Additional contact information
Jaekyun Jeong: Department of Computer Science and Engineering, Kongju National University, Seongbuk-gu, Cheonan 31080, Republic of Korea
Mangyu Lee: Department of Computer Science and Engineering, Kongju National University, Seongbuk-gu, Cheonan 31080, Republic of Korea
Sunguk Yun: Department of Computer Science and Engineering, Kongju National University, Seongbuk-gu, Cheonan 31080, Republic of Korea
Keejun Han: School of Computer Engineering, Hansung University, Seongbuk-gu, Seoul 02876, Republic of Korea
Jungeun Kim: Department of Computer Engineering, Inha University, Michuhol-gu, Incheon 22212, Republic of Korea

Mathematics, 2024, vol. 12, issue 24, 1-13

Abstract: Domain adaptation aims to effectively learn from two domains with different distributions, solving labeling problems; however, traditional methods assume that the source and target data are in-distribution data that share the same labels. In practice, Out-Of-Distribution (OOD) data which do not share labels with the existing data may also be collected during the target data collection process. These OOD data introduce noise and confusion, leading to decreased performance during adaptation. To address this issue, we propose RObust Domain Adaptation from Out-Of-Distribution data (RODA-OOD), a novel method based on data-centric AI principles that focuses on improving data quality rather than refining model architecture. RODA-OOD utilizes the characteristics of deep learning models that prioritize learning in-distribution data, which are easier to train on compared to OOD data. By dynamically adjusting the threshold for OOD detection, the proposed method effectively filters out OOD data, allowing the model to focus on relevant target data. RODA-OOD was compared with competitor and original domain adaptation algorithms based on target data accuracy. The results show that RODA-OOD demonstrates the most robust performance against OOD data, achieving a 21.3% increase in accuracy compared to existing domain adaptation methods. Thus, RODA-OOD can provide a solution to the OOD issue in unsupervised domain adaptation.

Keywords: robust domain adaptation; out-of-distribution data; temperature scaling; curriculum learning; RODA-OOD (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/24/3895/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/24/3895/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:24:p:3895-:d:1540779

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().