Source-free domain adaptation for semantic image segmentation using internal representations

Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic unsupervised domain adaptation (UDA) attempts to address a similar problem when there i...

Descripción completa

Detalles Bibliográficos

Autores principales:	Serban Stan, Mohammad Rostami
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	Frontiers Media S.A. 2024-06-01
Colección:	Frontiers in Big Data
Materias:	domain adaptation Gaussian mixture model (GMM) optimal transport and Wasserstein distances sliced Wasserstein distance image segmentation
Acceso en línea:	https://www.frontiersin.org/articles/10.3389/fdata.2024.1359317/full
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!