Abstract Recent work in computer vision has addressed zero-shot learning or unseen class detection, which involves categorizing objects without observing any training examples. However, these problems assume that attributes or de?ning characteristics of these unobserved classes are known, leveraging this information at test time to detect an unseen class. We address the more realistic problem of detecting categories that do not appear in the dataset in any form. We denote such a category as an unfamiliar class; it is neither observed at train time, nor do we possess any knowledge regarding its relationships to attributes. This problem is one that has received limited attention within the computer vision community. In this work, we propose a novel approach to the unfamiliar class detection task that builds on attribute-based classi?cation methods, and we empirically demonstrate how classi?cation accuracy is impacted by attribute noise and dataset “dif?culty,” as quanti?ed by the separation of classes in the attribute space. We also present a method for incorporating human users to overcome de?ciencies in attribute detection. We demonstrate results superior to existing methods on the challenging CUB-200-2011 dataset.