Open Access

ARTICLE

EDTM: Efficient Domain Transition for Multi-Source Domain Adaptation

Mangyu Lee^1,#, Jaekyun Jeong^2,#, Yun Wook Choo³, Keejun Han⁴, Jungeun Kim^2,*

1 Department of Computer Science and Engineering, Kongju National University, Cheonan, Republic of Korea
2 Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea
3 Department of Civil and Environmental Engineering, Kongju National University, Cheonan, Republic of Korea
4 School of Computer Engineering, Hansung University, Seoul, Republic of Korea

* Corresponding Author: Jungeun Kim. Email:
# These authors contributed equally to this work

Computer Modeling in Engineering & Sciences 2026, 146(2), 33 https://doi.org/10.32604/cmes.2026.074428

Received 10 October 2025; Accepted 22 January 2026; Issue published 26 February 2026

Abstract

Domain adaptation aims to reduce the distribution gap between the training data (source domain) and the target data. This enables effective predictions even for domains not seen during training. However, most conventional domain adaptation methods assume a single source domain, making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets. To address this limitation, recent research has focused on Multi-Source Domain Adaptation (MSDA), which aims to learn effectively from multiple source domains. In this paper, we propose Efficient Domain Transition for Multi-source (EDTM), a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches: (1) integrating knowledge across different source domains and (2) aligning label distributions between source and target domains. EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain. To further stabilize the learning process and improve performance, we incorporate imitation learning into the training of the target model. In addition, Maximum Classifier Discrepancy (MCD) is employed to align class-wise label distributions between the source and target domains. Experiments were conducted using Digits-Five, one of the most representative benchmark datasets for MSDA. The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy. Notably, EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M) and Street View House Numbers(SVHN) datasets, demonstrating enhanced generalization compared to baseline approaches. Furthermore, an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework, highlighting the importance of each module in achieving optimal performance.

---

Keywords

---