Few-Shot Object Counting with Dynamic Similarity-Aware in Latent Space

Few-shot object counting (FSOC) estimates object quantities in query images using a few of support information. Unlike traditional counting methods, FSOC prioritizes more discriminative and generalized similarity measures between query and support data. This facilitates counting objects from new cat...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2024-01, Vol.62, p.1-1
Hauptverfasser:	He, Jinghui, Liu, Bo, Cao, Fan, Xu, Jian, Xiao, Yanshan
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Counting methods Datasets Decoding Distribution Dynamic similarity Feature extraction Few-shot object counting Latent variable augmentation Metric learning Metric space Modules Pipelines Remote sensing Spatial data Task analysis Training Training data
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!