At the moment, I'm simply using mean of the features in all the instances in a bag to represent a given bag. I've also tried using min/max, gmean and hmean, but didn't get any better results.

Are there other multi-instance learning approaches that may work well and don't have significantly larger memory or processing requirements?

  • $\begingroup$ could you quantify the buzzword "deep learning?" Are you using a convolutional neural net? Check out Caffe: caffe.berkeleyvision.org , which will work especially well if you have a decent GPU. $\endgroup$
    – Alex R.
    Mar 31 '16 at 22:07
  • $\begingroup$ Thanks Alex. I think my references to deep learning distracted from my core question, so I've removed those references and I've updated the question accordingly. $\endgroup$
    – blu
    Apr 4 '16 at 9:00

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.