Domain generalization in machine learning models for wireless communications: Concepts, state-of-the-art, and open issues
Data-driven machine learning (ML) is promoted as one potential technology to be used in
next-generation wireless systems. This led to a large body of research work that applies ML …
next-generation wireless systems. This led to a large body of research work that applies ML …
A Meta-learning based Generalizable Indoor Localization Model using Channel State Information
Indoor localization has gained significant attention in recent years due to its various
applications in smart homes, industrial automation, and healthcare, especially since more …
applications in smart homes, industrial automation, and healthcare, especially since more …
SETA: Semantic-Aware Token Augmentation for Domain Generalization
Domain generalization (DG) aims to enhance the model robustness against domain shifts
without accessing target domains. A prevalent category of methods for DG is data …
without accessing target domains. A prevalent category of methods for DG is data …
Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models
Despite the huge effort in developing novel regularizers for Domain Generalization (DG),
adding simple data augmentation to the vanilla ERM which is a practical implementation of …
adding simple data augmentation to the vanilla ERM which is a practical implementation of …
CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection
Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in
open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of …
open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of …
Beyond Loss Functions: Leveraging Generative Foundation Models for Domain Generalization
There has been a huge effort to tackle Domain Generalization (DG) problems with a focus
on developing new loss functions. Inspired by the capabilities of the diffusion models, we …
on developing new loss functions. Inspired by the capabilities of the diffusion models, we …