Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks

TL;DR

This paper presents a novel GAN-based approach that learns to generate and assemble face images from smaller parts, enhancing machine face perception by capturing facial part relations and enabling part interchangeability.

Contribution

Introduces a new scheme for GANs to learn face image composition from parts, improving flexibility and generalization in machine face perception.

Findings

Produces realistic high-quality face images from parts

Learns relations and distributions of facial parts

Enables interchangeability of facial parts in generated images

Abstract

An important goal in human-robot-interaction (HRI) is for machines to achieve a close to human level of face perception. One of the important differences between machine learning and human intelligence is the lack of compositionality. This paper introduces a new scheme to enable generative adversarial networks to learn the distribution of face images composed of smaller parts. This results in a more flexible machine face perception and easier generalization to outside training examples. We demonstrate that this model is able to produce realistic high-quality face images by generating and piecing together the parts. Additionally, we demonstrate that this model learns the relations between the facial parts and their distributions. Therefore, the specific facial parts are interchangeable between generated face images.