Conditional Domain Adaptation with α -Rényi Entropy Regularization and Noise-Aware Label Weighting

Diego Armando Pérez-Rosero (), Andrés Marino Álvarez-Meza and German Castellanos-Dominguez
Additional contact information
Diego Armando Pérez-Rosero: Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, Colombia
Andrés Marino Álvarez-Meza: Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, Colombia
German Castellanos-Dominguez: Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, Colombia

Mathematics, 2025, vol. 13, issue 16, 1-29

Abstract: Domain adaptation is a key approach to ensure that artificial intelligence models maintain reliable performance when facing distributional shifts between training (source) and testing (target) domains. However, existing methods often struggle to simultaneously preserve domain-invariant representations and discriminative class structures, particularly in the presence of complex covariate shifts and noisy pseudo-labels in the target domain. In this work, we introduce Conditional Rényi α -Entropy Domain Adaptation, named CREDA, a novel deep learning framework for domain adaptation that integrates kernel-based conditional alignment with a differentiable, matrix-based formulation of Rényi’s quadratic entropy. The proposed method comprises three main components: (i) a deep feature extractor that learns domain-invariant representations from labeled source and unlabeled target data; (ii) an entropy-weighted approach that down-weights low-confidence pseudo-labels, enhancing stability in uncertain regions; and (iii) a class-conditional alignment loss, formulated as a Rényi-based entropy kernel estimator, that enforces semantic consistency in the latent space. We validate CREDA on standard benchmark datasets for image classification, including Digits, ImageCLEF-DA, and Office-31, showing competitive performance against both classical and deep learning-based approaches. Furthermore, we employ nonlinear dimensionality reduction and class activation maps visualizations to provide interpretability, revealing meaningful alignment in feature space and offering insights into the relevance of individual samples and attributes. Experimental results confirm that CREDA improves cross-domain generalization while promoting accuracy, robustness, and interpretability.

Keywords: domain adaptation; image classification; Rényi’s entropy; class-conditional alignment; noisy labels (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/16/2602/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/16/2602/ (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:13:y:2025:i:16:p:2602-:d:1724330

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 ().