Hierarchical Instance Mixing Across Domains in Aerial Segmentation

Hierarchical Instance Mixing Across Domains in Aerial Segmentation

We investigate the task of unsupervised domain adaptation in aerial semantic segmentation observing that there are some shortcomings in the class mixing strategies used by the recent state-of-the-art methods that tackle this task: 1) they do not account for the large disparity in the extension of th...

Full description

Bibliographic Details
Main Authors: Edoardo Arnaudo, Antonio Tavera, Carlo Masone, Fabrizio Dominici, Barbara Caputo
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Computer vision
deep learning
image processing
remote sensing
semantic segmentation
unsupervised domain adaptation
Online Access:https://ieeexplore.ieee.org/document/10040637/

Internet

https://ieeexplore.ieee.org/document/10040637/

Similar Items