Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigm
This addresses the challenge of dataset generalization for emotion recognition systems, but it appears incremental as it builds on existing methods for multi-dataset training.
The paper tackles the problem of training deep neural networks to perform well across multiple datasets without forgetting knowledge from the original dataset, using an extended loss function that incorporates information from similar networks trained on other datasets. In emotion recognition in-the-wild, the approach achieved improved performance, though no concrete numbers are provided in the 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.