I deal with an image classification problem with 3-class. I want to create a model which takes side to one specific class. I mean, while the model predicts a sample, if it is hesitant between class-1 and class-2, decide on class-1.

how can handle this?

  • 2
    $\begingroup$ Would you kindly define hesitant? Chances are, your model prediction is just an argmax of 3 class scores/probabilities, which makes the solution trivial when working with scores directly. Either way, changing the model itself does not seem to be required, it's just the decision making. $\endgroup$
    – dx2-66
    Oct 4 at 6:59


Your Answer

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

Browse other questions tagged or ask your own question.