Predicting and visualizing psychological attributions with a deep neural network
This work addresses the need for efficient and accurate facial attribute prediction in social decision-making contexts, though it is incremental as it builds on prior methods by removing the landmark requirement.
The authors tackled the problem of predicting psychological attributions from facial images without requiring expert-annotated landmarks, achieving high accuracy that sometimes surpasses human-level performance.
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.