Search for: All records

Facial attribute prediction is a facial analysis task that describes images using natural language features. While many works have attempted to optimize prediction accuracy on CelebA, the largest and most widely used facial attribute dataset, few works have analyzed the accuracy of the dataset's attribute labels. In this paper, we seek to do just that. Despite the popularity of CelebA, we find through quantitative analysis that there are widespread inconsistencies and inaccuracies in its attribute labeling. We estimate that at least one third of all images have one or more incorrect labels, and reliable predictions are impossible for several attributes due to inconsistent labeling. Our results demonstrate that classifiers struggle with many CelebA attributes not because they are difficult to predict, but because they are poorly labeled. This indicates that the CelebA dataset is flawed as a facial analysis tool and may not be suitable as a generic evaluation benchmark for imbalanced classification. 

First impressions make up an integral part of our interactions with other humans by providing an instantaneous judgment of the trustworthiness, dominance and attractiveness of an individual prior to engaging in any other form of interaction. Unfortunately, this can lead to unintentional bias in situations that have serious consequences, whether it be in judicial proceedings, career advancement, or politics. The ability to automatically recognize social traits presents a number of highly useful applications: from minimizing bias in social interactions to providing insight into how our own facial attributes are interpreted by others. However, while first impressions are well-studied in the field of psychology, automated methods for predicting social traits are largely non-existent. In this work, we demonstrate the feasibility of two automated approaches—multi-label classification (MLC) and multi-output regression (MOR)—for first impression recognition from faces. We demonstrate that both approaches are able to predict social traits with better than chance accuracy, but there is still significant room for improvement. We evaluate ethical concerns and detail application areas for future work in this direction. 

We introduce a novel algorithm – ConvNEAT – that evolves a convolutional neural network (CNN) from a minimal architecture. Convolutional and dense nodes are evolved without restriction to the number of nodes or connections between nodes. The proposed work advances the field with ConvNEAT’s ability to evolve arbitrary minimal architectures with multi-dimensional inputs using GPU processing.