Group-level Emotion Recognition using Transfer Learning from Face Identification

TL;DR

This paper presents a transfer learning approach for group-level emotion recognition using face identification features, achieving state-of-the-art accuracy in the EmotiW 2017 challenge.

Contribution

The authors introduce a novel method that leverages face identification CNN features for emotion recognition, outperforming traditional handcrafted features.

Findings

Achieved 75.4% accuracy on validation data.

Outperformed baseline by 20%.

Ensemble classifier improved prediction accuracy.

Abstract

In this paper, we describe our algorithmic approach, which was used for submissions in the fifth Emotion Recognition in the Wild (EmotiW 2017) group-level emotion recognition sub-challenge. We extracted feature vectors of detected faces using the Convolutional Neural Network trained for face identification task, rather than traditional pre-training on emotion recognition problems. In the final pipeline an ensemble of Random Forest classifiers was learned to predict emotion score using available training set. In case when the faces have not been detected, one member of our ensemble extracts features from the whole image. During our experimental study, the proposed approach showed the lowest error rate when compared to other explored techniques. In particular, we achieved 75.4% accuracy on the validation data, which is 20% higher than the handcrafted feature-based baseline. The source code using Keras framework is publicly available.