DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network

TL;DR

This paper presents a fully automated deep learning system for age, gender, and emotion recognition that achieves state-of-the-art results using efficient convolutional neural networks trained on large labeled datasets.

Contribution

It introduces a novel deep CNN-based system for multi-task facial analysis that is computationally efficient and trained with semi-supervised data collection methods.

Findings

Achieved state-of-the-art results on multiple benchmarks.

System is computationally inexpensive and suitable for real-time applications.

Models are accessible via an API for developers.

Abstract

This paper describes the details of Sighthound's fully automated age, gender and emotion recognition system. The backbone of our system consists of several deep convolutional neural networks that are not only computationally inexpensive, but also provide state-of-the-art results on several competitive benchmarks. To power our novel deep networks, we collected large labeled datasets through a semi-supervised pipeline to reduce the annotation effort/time. We tested our system on several public benchmarks and report outstanding results. Our age, gender and emotion recognition models are available to developers through the Sighthound Cloud API at https://www.sighthound.com/products/cloud