Self-Filtered Learning for Semantic Segmentation of Buildings in Remote Sensing Imagery With Noisy Labels

Self-Filtered Learning for Semantic Segmentation of Buildings in Remote Sensing Imagery With Noisy Labels

Not all building labels for training improve the performance of the deep learning model. Some labels can be falsely labeled or too ambiguous to represent their ground truths, resulting in poor performance of the model. For example, building labels in OpenStreetMap (OSM) and Microsoft Building Footpr...

Full description

Bibliographic Details
Main Authors: Hunsoo Song, Lexie Yang, Jinha Jung
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Building extraction
deep learning
label noise
semantic segmentation
weakly supervised learning (WSL)
Online Access:https://ieeexplore.ieee.org/document/9992041/

Internet

https://ieeexplore.ieee.org/document/9992041/

Similar Items