Unbalanced data in multiple object detection


I am working in object detection with my own dataset.

The objects present in my dataset are very umbalanced, and I was wondering if it is possible to apply something as a weighted random sampler (I have already employed this for image classification) but for object detection.

In my images several structures are present.


1 Like

Balancing a mutli-label dataset is a bit tricky, as a simple weighted sampling might even increase the imbalance, e.g. if the majority classes are often associated with the oversampled minority classes.

There are a few approaches, such as SCUMBLE, REMEDIAL, MLSOL, MLSMOTE etc.

I don’t know, what the current state of the art is, but I’m sure @rasbt would know. :wink:

1 Like

Thankyou so much @ptrblck, I will check the approaches you have given me.
I’ll provide I new answer if I reach a solution!

1 Like

Did you find a solution? Thanks.