Deep Neural Networks Predict Category Typicality Ratings for Images

By Brenden M. Lake, Wojciech Zaremba, Rob Fergus, Todd M. Gureckis. 2015

80 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

What are the Visual Features Underlying Human Versus Machine Vision? (2017, background): “Related work has also evaluated the ability of DCNs to predict memorability [6] and the typicality of individual images [16].”
Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future (2020, background): “In addition to similarity, other psychological concepts that have been tested in CNNs include typicality [31], Gestalt principles [32], and animacy [33].”
Adapting Deep Network Features to Capture Psychological Representations (2016, background): “…representations learned by these networks can be used in models of human behavior for perceptual tasks such as predicting the memorability of objects in images (Dubey, Peterson, Khosla, Yang, & Ghanem, 2015) and predicting judgments of category typicality (Lake, Zaremba, Fergus, & Gureckis, 2015).”
Not-So-CLEVR: learning same–different relations strains feedforward neural networks (2018, background): “In addition, deep networks have been shown to be consistent with a number of human behaviours including rapid visual categorization [30,31], image memorability [32], typicality [33] as well as similarity [34] and shape sensitivity [35] judgements.”
The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks (2016, background): “Lake et al. [ 2015 ] showed that the output of the last layer of CNN models can be used as a signal for how typical an input image looks like.”