Bridging the MiniBatch and Adversarial Optimal Transport for Cross-Scene Classification of Remote Sensing Smoke-Related Scenes

Smoke in remote sensing (RS) images is regarded as the indicator of fire disasters and it is vital to distinguish smoke from other RS scenes. Convolutional neural network (CNN) based classification networks have viewed great success but the cross-entropy loss may suffer from domain gap when training...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE geoscience and remote sensing letters 2023, Vol.20, p.1-5
Hauptverfasser:	Chen, Shikun, Lu, Xin, Li, Weixuan, Lu, Xiaobo
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Adaptation models Algorithms Artificial neural networks Classification Convolutional neural networks Disasters Distance Domain adaptation Entropy Entropy (Information theory) Feature extraction Neural networks Objective function optimal transport (OT) Performance enhancement Remote sensing remote sensing (RS) scene classification Smoke Task analysis Training Transportation
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!