Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels

05/19/2018
by   Joshua C. Peterson, et al.
0

Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the categorization problem is posed differently for these networks than for humans: the accuracy of these networks is evaluated by their ability to identify single labels assigned to each image. These labels often cut arbitrarily across natural psychological taxonomies (e.g., dogs are separated into breeds, but never jointly categorized as "dogs"), and bias the resulting representations. By contrast, it is common for children to hear both "dog" and "Dalmatian" to describe the same stimulus, helping to group perceptually disparate objects (e.g., breeds) into a common mental class. In this work, we train CNN classifiers with multiple labels for each image that correspond to different levels of abstraction, and use this framework to reproduce classic patterns that appear in human generalization behavior.

READ FULL TEXT
research
11/12/2015

Basic Level Categorization Facilitates Visual Object Recognition

Recent advances in deep learning have led to significant progress in the...
research
11/13/2017

Modeling Human Categorization of Natural Images Using Deep Feature Representations

Over the last few decades, psychologists have developed sophisticated fo...
research
03/13/2018

Expert identification of visual primitives used by CNNs during mammogram classification

This work interprets the internal representations of deep neural network...
research
09/11/2018

Taking a machine's perspective: Human deciphering of adversarial images

How similar is the human mind to the sophisticated machine-learning syst...
research
09/11/2018

Taking a machine's perspective: Humans can decipher adversarial images

How similar is the human mind to the sophisticated machine-learning syst...
research
06/08/2017

Leveraging deep neural networks to capture psychological representations

Artificial neural networks have seen a recent surge in popularity for th...
research
09/02/2019

HiCoRe: Visual Hierarchical Context-Reasoning

Reasoning about images/objects and their hierarchical interactions is a ...

Please sign up or login with your details

Forgot password? Click here to reset