Failing to distinguish between a sheepdog and a skyscraper should be worseand penalized more than failing to distinguish between a sheepdog and a poodle;after all, sheepdogs and poodles are both breeds of dogs. However, existingmetrics of failure (so-called "loss" or "win") used in textual or visualclassification/recognition via neural networks seldom view a sheepdog as moresimilar to a poodle than to a skyscraper. We define a metric that, inter alia,can penalize failure to distinguish between a sheepdog and a skyscraper morethan failure to distinguish between a sheepdog and a poodle. Unlike previouslyemployed possibilities, this metric is based on an ultrametric tree associatedwith any given tree organization into a semantically meaningful hierarchy of aclassifier's classes.
展开▼