Replicating neuroscience observations on ML/MF and AM face patches by deep generative model

Tian Han, Xianglei Xing, Jiawen Wu, Ying Nian Wu

Research output: Contribution to journalLetterpeer-review

2 Scopus citations

Abstract

A recent Cell paper (Chang & Tsao, 2017) reports an interesting discovery. For the face stimuli generated by a pretrained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit a strong linear relationship with the shape variables and appearance variables of the AAM that generates the face stimuli. In this letter, we show that this behavior can be replicated by a deep generative model, the generator network, that assumes that the observed signals are generated by latent random variables via a top-down convolutional neural network. Specifically, we learn the generator network from the face images generated by a pretrained AAM model using a variational autoencoder, and we show that the inferred latent variables of the learned generator network have a strong linear relationship with the shape and appearance variables of the AAM model that generates the face images. Unlike the AAM model, which has an explicit shape model where the shape variables generate the control points or landmarks, the generator network has no such shape model and shape variables. Yet it can learn the shape knowledge in the sense that some of the latent variables of the learned generator network capture the shape variations in the face images generated by AAM.

Original languageEnglish
Pages (from-to)2348-2367
Number of pages20
JournalNeural Computation
Volume31
Issue number12
DOIs
StatePublished - 1 Dec 2019

Fingerprint

Dive into the research topics of 'Replicating neuroscience observations on ML/MF and AM face patches by deep generative model'. Together they form a unique fingerprint.

Cite this