Scene Classification Based on Two-Stage Deep Feature Fusion

In convolutional neural networks (CNNs), higher layer information is more abstract and more task specific, so people usually concern themselves with fully connected (FC) layer features, believing that lower layer features are less discriminative. However, a few researchers showed that the lower laye...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE geoscience and remote sensing letters 2018-02, Vol.15 (2), p.183-186
Hauptverfasser:	Liu, Yishu, Liu, Yingbin, Ding, Liwang
Format:	Artikel
Sprache:	eng
Schlagworte:	1 × 1 convolution Adaptation models Artificial neural networks Classification composite convolutional neural networks (CNNs) converted CNN Convolution Data models deep feature fusion global average pooling (GAP) Image representation Neural networks Remote sensing State of the art Topology Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!