PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans

arXiv:2308.13651v2 Announce Type: replace
Abstract: Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes; and (2) uses S's output scores …

abstract accuracy arxiv class classification classifiers compute cs.cv cs.hc decision decisions fine-grained humans image machines neighbors novel paper predictions show support support vector machines type utility vector