I have around 3M BW images and I would like to organize them in as few clusters as possible in way which is meaningful for the dataset without any prior knowledge for this data, as they come from domains which are not represented in classic models trained in classic datasets like ImageNET etc.

My target is to produce meaningful labels for images, By meaningful I mean in a machinic way. I don't want exactly to have human readable labels, but I would like for the labels not to be that arbitrary (thus to relate with higher-semantically or deep correspondences from the vast amount of pictures, which I supply to the model).

Are you aware of any method able to do something like this?

Thank you.


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.