As far as I can tell, most work on facial recognition has been done in relation to human faces. Has any significant work been done for dogs, and are there any special challenges that would make it difficult to adapt existing work to this use case?
To clarify: I don't mean image classification, but segmentation. In other words, I refer to a model that can take an image that can have any number, including zero, of dogs in it, and that will produce bounding boxes around each dog's face.