Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks
This work addresses the lack of compositionality in machine learning for human-robot interaction, offering a more flexible face perception approach.
The paper tackles the problem of enabling machines to achieve human-like compositional perception of faces by introducing a scheme for generative adversarial networks to learn distributions of face images composed of smaller parts, resulting in realistic high-quality face generation and interchangeable facial parts.
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.