A Novel One-vs-Rest Classification Framework for Mutually Supported Decisions by Independent Parallel Classifiers

We put forward a generic classification architecture of independent parallel CNNs that explicitly exploits a “mutual exclusivity” or “classifiers’ mutually supported decisions” property underlying many dataset domains of interest, namely that in many cases an image in a given dataset might almost unquestionably belong to one class only. Our framework incorporates several designed-to-purpose opinion aggregation decision rules that are triggered when the mutual exclusivity property is or is not satisfied; and makes use of “weights” which intuitively mirror the confidence each CNN has in identifying its corresponding class. Our framework can thus (a) take advantage of clear class boundaries when these exist, and (b) effectively assign items to classes with increased confidence, even when clear class boundaries do not exist. We confirm the effectiveness of our approach via experiments conducted on a well-known dataset from the waste classification domain.