Deep Evolution for Facial Emotion Recognition

TL;DR

This paper introduces a novel evolutionary algorithm-based method for facial emotion recognition that significantly reduces model parameters, improves interpretability by focusing on key image patches, and maintains or improves classification accuracy.

Contribution

It presents a new evolutionary approach that reduces parameters by 95%, enhances interpretability through attention to important facial regions, and demonstrates the effectiveness of evolutionary algorithms in deep learning.

Findings

Reduced parameters by 95% without accuracy loss

Identified key facial patches for emotion recognition

Enhanced interpretability and potential bias reduction

Abstract

Deep facial expression recognition faces two challenges that both stem from the large number of trainable parameters: long training times and a lack of interpretability. We propose a novel method based on evolutionary algorithms, that deals with both challenges by massively reducing the number of trainable parameters, whilst simultaneously retaining classification performance, and in some cases achieving superior performance. We are robustly able to reduce the number of parameters on average by 95% (e.g. from 2M to 100k parameters) with no loss in classification accuracy. The algorithm learns to choose small patches from the image, relative to the nose, which carry the most important information about emotion, and which coincide with typical human choices of important features. Our work implements a novel form attention and shows that evolutionary algorithms are a valuable addition to machine learning in the deep learning era, both for reducing the number of parameters for facial expression recognition and for providing interpretable features that can help reduce bias.