UIU-Net: U-Net in U-Net for Infrared Small Object Detection

Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerg...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing Jg. 32; S. 1
Hauptverfasser:	Wu, Xin, Hong, Danfeng, Chanussot, Jocelyn
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.01.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Schlagworte:	Artificial Intelligence attention mechanism Computer networks Computer Science Context Datasets Decoding deep learning deep multi-scale feature Feature extraction feature interaction Image resolution Infrared imagery Infrared small object Integrated circuits Learning local and global context information Maintenance Modules Object detection Object recognition Semantics Visualization Infrared small object deep learning feature interaction attention mechanism deep multi-scale feature local and global context information
ISSN:	1057-7149, 1941-0042, 1941-0042
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!