Shape-Based Measures Improve Scene Categorization

Converging evidence indicates that deep neural network models that are trained on large datasets are biased toward color and texture information. Humans, on the other hand, can easily recognize objects and scenes from images as well as from bounding contours. Mid-level vision is characterized by the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2024-04, Vol.46 (4), p.2041-2053
Hauptverfasser:	Rezanejad, Morteza, Wilder, John, Walther, Dirk B., Jepson, Allan D., Dickinson, Sven, Siddiqi, Kaleem
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Classification Contour geometry Contours Convolutional neural networks Feature extraction Gestalt grouping cues medial axis transform (MAT) Object recognition Observers Organizations scene categorization scene perception shape based measures Task analysis Transforms Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!