In image classification, there are sometimes images that do not fit in any category.
For example, if I build a CNN in Keras to classify Dogs and Cats, does it help (in terms of training time and performance) to create an "other" (or "unclassified") category in which images of houses, people, birds, etc., are classified? Is there any research paper that discusses this?
A similar question was asked before here, but, unfortunately, it has no answer.
It is not advisable because if you use an "other" class, you are just increasing problems for your network. Since "other" means not dog and not cat, then, what common feature does it have? Most of the time the "other" images won't have many features in common. If they do, then go ahead and make an "other" class.
There is a better way: if the probabilities for both cat and dog are less than a threshold (you need to decide that, take, 0.5), then, you can say it is an "other" object.
