I want to create a dog-classifier, which outputs the probability of an image containing a dog.
I have two approaches in mind -
Binary classifier (1-class), which just outputs the probability of the image containing a dog. This seems reasonable to me.
2-class classifier with two classes denoting "dog" and "not-dog". But my problem with this approach is that the neural network has to learn the "not-dog" class as well, which is impossible since it has no pattern and is different in each training example.
Would the second approach be less effective than the first? Or even work at all?