Modeling Human Categorization of Natural Images Using Deep Feature Representations
This work extends psychological categorization models to naturalistic stimuli, enabling study in complex visual domains, but it is incremental as it applies existing methods to new data.
The paper tackled modeling human categorization of natural images using deep feature representations, showing that convolutional neural network-based models perform near human reliability on a database of over 300,000 classifications, with both exemplar and prototype models working well.
Over the last few decades, psychologists have developed sophisticated formal models of human categorization using simple artificial stimuli. In this paper, we use modern machine learning methods to extend this work into the realm of naturalistic stimuli, enabling human categorization to be studied over the complex visual domain in which it evolved and developed. We show that representations derived from a convolutional neural network can be used to model behavior over a database of >300,000 human natural image classifications, and find that a group of models based on these representations perform well, near the reliability of human judgments. Interestingly, this group includes both exemplar and prototype models, contrasting with the dominance of exemplar models in previous work. We are able to improve the performance of the remaining models by preprocessing neural network representations to more closely capture human similarity judgments.