Deep Learning Models for Automated Classification of Dog Emotional States from Facial Expressions

Abstract

Similarly to humans, facial expressions in animals are closely linked with emotional states. However, in contrast to the human domain, automated recognition of emotional states from facial expressions in animals is underexplored, mainly due to difficulties in data collection and establishment of ground truth concerning emotional states of nonverbal users. We apply recent deep learning techniques to classify (positive) anticipation and (negative) frustration of dogs on a dataset collected in a controlled experimental setting. We explore the suitability of different backbones (e.g. ResNet, ViT) under different supervisions to this task, and find that features of a self-supervised pretrained ViT (DINO-ViT) are superior to the other alternatives. To the best of our knowledge, this work is the first to address the task of automatic classification of canine emotions on data acquired in a controlled experiment.

Categorization of emotions in dog behavior based on the deep neural network

“…We are currently seeing a growing interest in the subject of emotional recognition in dogs. For example, two new articles 13,14 appeared last year. The first approach is to convert the FACS method to a dog's case 15 and use visual features to discover a dog's emotions using a neural network and a Vision Transformer.…”