Do Humans and Convolutional Neural Networks Attend to Similar Areas during Scene Classification: Effects of Task and Image Type

Do Humans and Convolutional Neural Networks Attend to Similar Areas during Scene Classification: Effects of Task and Image Type

Deep neural networks are powerful image classifiers but do they attend to similar image areas as humans? While previous studies have investigated how this similarity is shaped by technological factors, little is known about the role of factors that affect human attention. Therefore, we investigated...

Full beskrivning

Bibliografiska uppgifter
Huvudupphovsmän: Romy Müller, Marcel Dürschmidt, Julian Ullrich, Carsten Knoll, Sascha Weber, Steffen Seitz
Materialtyp: Artikel
Språk:English
Publicerad: MDPI AG 2024-03-01
Serie:Applied Sciences
Ämnen:
convolutional neural networks (CNN)
explainable artificial intelligence (XAI)
attention maps
eye movements
scene viewing
image classification
Länkar:https://www.mdpi.com/2076-3417/14/6/2648

Internet

https://www.mdpi.com/2076-3417/14/6/2648

Liknande verk