Generalizing to Unseen Domains: A Survey on Domain Generalization [PDF]
IEEE Transactions on Knowledge and Data Engineering, 2022 Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years.
Cuiling Lan, Philip Yu, Jindong Wang
exaly +5 more sources
Domain Generalization: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI ...
Chen Change Loy, Tao Xiang, Ziwei Liu
exaly +4 more sources
Domain generalization for voice-based cognitive impairment detection [PDF]
BMC Medical Informatics and Decision MakingBackground Voice biomarkers hold potential for early cognitive disorder detection, but variations in recording conditions across different environments present challenges for accurate diagnosis using artificial intelligence (AI) models.
Minsoo Kim +9 more
doaj +2 more sources
Integrating Frequency Guidance into Multi-Source Domain Generalization for Acoustic-Based Fault Diagnosis in Industrial Systems [PDF]
SensorsWith the increasing demand for intelligent fault monitoring, acoustic-based diagnosis has emerged as a promising solution for industrial applications such as pipeline leakage and electrical equipment fault detection.
Yu Wang +6 more
doaj +2 more sources
Fourier transform-based single domain generalization for crowd counting [PDF]
Scientific ReportsAccurate crowd counting is critical for numerous real-world applications. However, domain shift poses a significant barrier to deploying crowd counting models in practical scenarios due to the discrepancy between training and target domains.
Lei Song +6 more
doaj +2 more sources
ICRL: independent causality representation learning for domain generalization [PDF]
Scientific ReportsDomain generalization (DG) addresses the challenge of out-of-distribution (OOD) data; however, the reliance on statistical correlations during model development often introduces shortcut learning problems.
Liwen Xu, Yuxuan Shao
doaj +2 more sources
MedicalCLIP: Anomaly-Detection Domain Generalization with Asymmetric Constraints [PDF]
BiomoleculesMedical data have unique specificity and professionalism, requiring substantial domain expertise for their annotation. Precise data annotation is essential for anomaly-detection tasks, making the training process complex. Domain generalization (DG) is an
Liujie Hua +3 more
doaj +2 more sources
Cross-Subject Motor Imagery Electroencephalogram Decoding with Domain Generalization [PDF]
BioengineeringDecoding motor imagery (MI) electroencephalogram (EEG) signals in the brain–computer interface (BCI) can assist patients in accelerating motor function recovery.
Yanyan Zheng +4 more
doaj +2 more sources
DG-TTA: Out-of-Domain Medical Image Segmentation Through Augmentation, Descriptor-Driven Domain Generalization, and Test-Time Adaptation [PDF]
SensorsApplying pre-trained medical deep learning segmentation models to out-of-domain images often yields predictions of insufficient quality. In this study, we propose using a robust generalizing descriptor, along with augmentation, to enable domain ...
Christian Weihsbach +3 more
doaj +2 more sources
CAT: Class-aware adaptive-thresholding for robust semi-supervised domain generalization. [PDF]
PLoS ONEDomain Generalization (DG) seeks to transfer knowledge from multiple source domains to unseen target domains, even in the presence of domain shifts. Achieving effective generalization typically requires a large and diverse set of labeled source data to ...
Sumaiya Zoha +2 more
doaj +2 more sources