Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigm

TL;DR

This paper introduces a novel training method for deep neural networks that leverages information from multiple datasets and related networks to improve emotion recognition performance in real-world scenarios.

Contribution

It proposes an extended loss function incorporating knowledge from similar networks trained on different datasets, enhancing generalization without forgetting previous learning.

Findings

Improved emotion recognition accuracy in-the-wild.

Effective integration of multi-dataset information.

Demonstrated robustness across recent emotion recognition challenges.

Abstract

A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other relevant data sets. This information is included in an extended loss function used for the network training, so that the network can have an improved performance when applied to the other data sets, without forgetting the learned knowledge from the original data set. Facial expression and emotion recognition in-the-wild is the test bed application that is used to demonstrate the improved performance achieved using the proposed approach. In this framework, we provide an experimental study on categorical emotion recognition using datasets from a very recent related emotion recognition challenge.