1

Apologies if this is a stupid question but I have a dataset with two classes I wish to attempt to classify using a U-Net.

When creating the label matrices, do I need to explicitly define the null / base class (everything which isn't a class) or will Keras calculate this automatically?

For example, if I have a set of images where I'd like to classify the regions where there is a dog or where this is a cat, do I need to create a third label matrix which labels everything which is not a dog or cat (and thus, have three classes)?

Furthermore, the null class dominates the images I'm wishing to segment; if I were to use a class_weight, it seems to only accept a dictionary as input whereas I swear before I good specify a list and that would suffice.

If I treat my problem as a two-class problem, I'm assuming I need to specify the weight of the null class too, i.e. class_weight = [nullweight, dogweight, catweight].

Thank you

edit: Attached example enter image description here

Is this above image a two class or three class problem?

Timbus Calin
  • 13,809
  • 5
  • 41
  • 59
user1147964
  • 143
  • 2
  • 11

1 Answers1

2

You must specify the other class since the network needs to differentiate between the dog, the cat and the background.

As for the class_weights parameter, the discussion is a little bit more complicated, you cannot assign like you would do in a simple classification problem.

Indeed, in many problems the background constitutes a big part of the image so you need to be careful when approaching such an imbalanced problem.

You need to inspect the parameter sample_weights, not class_weights, you can have a look at these threads:

  1. https://datascience.stackexchange.com/questions/31129/sample-importance-training-weights-in-keras
  2. https://github.com/keras-team/keras/issues/3653
  3. Weighting samples in multiclass image segmentation using keras image-segmentation-using-keras
Timbus Calin
  • 13,809
  • 5
  • 41
  • 59
  • Thank you for the reply. So it's very straight forward to reframe the problem with the negative class and classes 1 and 2 (three classes total). These examples of weighting the problem so the background (negative class) is weighted less than the other classes seems quite complicated though – user1147964 Jun 22 '20 at 12:35
  • Yes, it is a little bit complicated. By the way, if my answer helped you in a way, I would appreciate if you upvoted it (not necessarily accepting the answer). It helps both me and you and others with the same question. – Timbus Calin Jun 22 '20 at 14:01