Hi, confusion about the computation of the feature statistics similarity (mean&variance)

[lixingang]

I'm dealing my unbalanced data with your study; A little confusion: how to compute the Feature statistics similarity between the many-shot region and few-shot region? Cuz the features in the few-shot region bins are less than that in many-shot region.

Thanks to your attention!

[lixingang]

I'm not sure whether my understanding is correct: the practice is computing the mean and variance value across the samples in the same bin, and finally each bin owns two features(the feature mean and the feature variance) ? If so, the issue should be closed.

[YyzHarry]

Hi - thanks for your interest. Yes, your understanding is correct -- the feature mean / (co)variance are computed over all samples in the same bin. Then you calculate the similarity between bins.