In real world applications very often the entire set of classes is not known during the training phase (e.g. identifying objects, sounds, etc.). A system is needed that can classify observations into the predefined classes but also tells the user that there is an observation that probably is related to a completely new class which was not in the training data - sort of a combination of classification and anomaly detection.

I saw that this problem is also called "open world classification" or "open set classification" with a few papers addressing this issue.

A simpler approach would be just take the prediction probability of a neural network and interpret a low probability as an indication of a new class.

Do you see any problem with the latter approach? What is your opinion about that "open world classification" research?



1 Answer 1


This approach may work well for points that are close to the training distribution. The prediction of the neural network for points outside the training distribution cannot be trusted a lot. It may happen that for points outside the training distribution the predictions of the neural network are somewhat strange and erratic. For more information on this topic have a look at this paper:


Under the "IMPROPER BEHAVIOR OF MLP OUTSIDE THE BOUNDARY OF THE TRAINING SAMPLE" paragraph, you will find more information on this problem.

  • $\begingroup$ Hi, it looks like you've omitted the link to the paper. $\endgroup$
    – cherub
    Jun 6, 2019 at 12:41
  • $\begingroup$ Sorry for that this was my first post on stack exchange. $\endgroup$ Jun 10, 2019 at 7:51

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.