No class identified by the model

I have multi-label image classification model. When I use to predict on a test set, the model does not return any labels. I understand that the probabilities predicted in the last layer don’t cross the set threshold. How can I mitigate this? Also, is my understanding correct?

Here is the class distribution of the test data vs the predicted .

Column 1, in the second graph contains almost 500 images which are not classified as anything.

Maybe try to see what categories are ending up in the unknown?

interp = ClassificationInterpretation.from_learner(learn)

Also, this link might help in adjusting the threshold