0
$\begingroup$

Is there an approach for the following problem:

Lets say, I trained a neural network on a big dataset for categorizing different fruits in $k$ classes. Afterwards I got a nice model, which performs very well.

Now I want to use the model for categorizing fruits in the corresponding $k$ classes, as it was planned beforehand. Unfortunately the fruits I want to categorize now are all not ripe yet, but my training set consisted only of ripe fruits. Furthermore I have some pictures of these not ripe fruits, but no labels.

How can I adapt my neural network to these slightly different domain with my pictures of not ripe fruits (and no labels!). Performance on the old task does not matter. The only thing I want, is categorizing not ripe fruits.

My only Idea now is to use virtual adversarial training (VAT) for the unlabeled pictures.

$\endgroup$
1
$\begingroup$

I think those are one of the most cited papers:

| improve this answer | |
$\endgroup$
  • $\begingroup$ Thank you very much. There seem to be some very promising ideas for my problem. Take my upvote ;) $\endgroup$ – Andreas Look Dec 18 '18 at 16:45
  • $\begingroup$ You're welcome! Yes, these papers looks really exciting... I'll try this techniques soon, we could exchange our impressions and considerations :) $\endgroup$ – ignatius Dec 18 '18 at 16:46
  • $\begingroup$ I will definitely report back^^ $\endgroup$ – Andreas Look Dec 18 '18 at 16:46

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.