Context-Aware Self-Adaptation for Domain Generalization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Hao, Guo, Yuhong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909564693118976
author Yan, Hao
Guo, Yuhong
author_facet Yan, Hao
Guo, Yuhong
contents Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called Context-Aware Self-Adaptation (CASA) for domain generalization. CASA simulates an approximate meta-generalization scenario and incorporates a self-adaptation module to adjust pre-trained meta source models to the meta-target domains while maintaining their predictive capability on the meta-source domains. The core concept of self-adaptation involves leveraging contextual information, such as the mean of mini-batch features, as domain knowledge to automatically adapt a model trained in the first stage to new contexts in the second stage. Lastly, we utilize an ensemble of multiple meta-source models to perform inference on the testing domain. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on standard benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03064
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context-Aware Self-Adaptation for Domain Generalization
Yan, Hao
Guo, Yuhong
Machine Learning
Artificial Intelligence
Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called Context-Aware Self-Adaptation (CASA) for domain generalization. CASA simulates an approximate meta-generalization scenario and incorporates a self-adaptation module to adjust pre-trained meta source models to the meta-target domains while maintaining their predictive capability on the meta-source domains. The core concept of self-adaptation involves leveraging contextual information, such as the mean of mini-batch features, as domain knowledge to automatically adapt a model trained in the first stage to new contexts in the second stage. Lastly, we utilize an ensemble of multiple meta-source models to perform inference on the testing domain. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on standard benchmarks.
title Context-Aware Self-Adaptation for Domain Generalization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.03064