On the Importance of Attention and Augmentations for Hypothesis Transfer in Domain Adaptation and Generalization

On the Importance of Attention and Augmentations for Hypothesis Transfer in Domain Adaptation and Generalization

Unsupervised domain adaptation (UDA) aims to mitigate the performance drop due to the distribution shift between the training and testing datasets. UDA methods have achieved performance gains for models trained on a source domain with labeled data to a target domain with only unlabeled data. The sta...

Full description

Bibliographic Details
Main Authors: Rajat Sahay, Georgi Thomas, Chowdhury Sadman Jahan, Mihir Manjrekar, Dan Popp, Andreas Savakis
Format: Article
Language:English
Published: MDPI AG 2023-10-01
Series:Sensors
Subjects:
domain adaptation
domain generalization
vision transformers
convolutional neural networks
Online Access:https://www.mdpi.com/1424-8220/23/20/8409

Internet

https://www.mdpi.com/1424-8220/23/20/8409

Similar Items