Predicting and visualizing psychological attributions with a deep neural network

TL;DR

This paper introduces a CNN model that predicts psychological attributions from face images without needing facial landmarks, achieving high accuracy and providing visualizations of influential features.

Contribution

The study presents a landmark-free CNN approach for predicting personality perceptions, surpassing some human performance levels and offering novel visualization techniques.

Findings

High accuracy in predicting 22 attributes

Surpasses human-level performance in some cases

Innovative visualization of positive and negative features

Abstract

Judgments about personality based on facial appearance are strong effectors in social decision making, and are known to have impact on areas from presidential elections to jury decisions. Recent work has shown that it is possible to predict perception of memorability, trustworthiness, intelligence and other attributes in human face images. The most successful of these approaches require face images expertly annotated with key facial landmarks. We demonstrate a Convolutional Neural Network (CNN) model that is able to perform the same task without the need for landmark features, thereby greatly increasing efficiency. The model has high accuracy, surpassing human-level performance in some cases. Furthermore, we use a deconvolutional approach to visualize important features for perception of 22 attributes and demonstrate a new method for separately visualizing positive and negative features.