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

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...

Full description

Bibliographic Details
Main Authors: Serban Stan, Mohammad Rostami
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-06-01
Series:Frontiers in Big Data
Subjects:
domain adaptation
Gaussian mixture model (GMM)
optimal transport and Wasserstein distances
sliced Wasserstein distance
image segmentation
Online Access:https://www.frontiersin.org/articles/10.3389/fdata.2024.1359317/full

Internet

https://www.frontiersin.org/articles/10.3389/fdata.2024.1359317/full

Similar Items