Iris Dominguez-Catena

TL;DR: In this article , the authors used a popular FER dataset, FER+, to generate derivative datasets with different amounts of stereotypical bias by altering the gender proportions of certain labels. And they then measured the discrepancy between the performance of the models trained on these datasets for the apparent gender groups.

TL;DR: In this article , a taxonomy for the classification of these metrics, providing a practical guide for the selection of appropriate metrics, was developed, and a case study of 20 datasets used in Facial Emotion Recognition (FER), analyzing the biases present in them.

TL;DR: This paper proposes and explores a new way of using OWA aggregations as a new layer inside a convolutional neural network, and shows that this layer introduces new knowledge into the network without substantially increasing training times.

TL;DR: A new layer is developed that can be placed at different points inside a Deep Neural Network and takes the feature maps of the previous layer and adds new feature maps by applying several channel-wise ordered aggregations based on learned weighting vectors.