Sampling from object and scene representations using deep feature spaces

Abstract

Understanding how people represent categories is a core problem in cognitive science. Decades of research have yielded a variety of formal theories of categories, but validating them with naturalistic stimuli is difficult. The challenge is that human category representations cannot be directly observed and running informative experiments with naturalistic stimuli such as images requires a workable representation of these stimuli. Deep neural networks have recently been successful in solving a range of computer vision tasks and provide a way to compactly represent image features. Here, we introduce a method to estimate the structure of human categories that combines ideas from cognitive science and machine learning, blending human-based algorithms with state-of-the-art deep image generators. We provide qualitative and quantitative results as a proof-of-concept for the method's feasibility. Samples drawn from human distributions rival those from state-of-the-art generative models in quality and outperform alternative methods for estimating the structure of human categories.

Generative adversarial networks unlock new methods for cognitive science

“…wheel for continuous reports mimicked those acquired with simpler stimuli. Other work [46] likewise proposed to exploit a GAN's latent space to obtain a window into the representations of mental categories. Future work will have to further elucidate the psychological validity of the latent space as a representational space, especially considering that GANs rely on CNNs which are themselves still imperfect models of the visual system [5,[47][48][49].…”

Humanacgan: Conditional Generative Adversarial Network with Human-Based Auxiliary Classifier and its Evaluation in Phoneme Perception

“…Namely, we train the HumanGAN's generator conditioned on the desired class label, and it represents the class-specific human-acceptable distribution as a result. This will contribute establishing a DNN-based framework to model the task-oriented perception by humans [11,12].…”