Attribute rating for classification of visual objects

Traditional visual classification approaches focus on predicting absence/presence of labels or attributes for images. However, it is sometimes useful to predict the ratings of the labels or attributes endowed with an ordinal scale (e.g., “very important,” “important” or “not important”). The ordinal scale representation allows us to describe object classes more precisely than simple binary tagging. In this work, we propose a new method where each label/attribute can be assigned to a finite set of ordered ratings, from most to least relevant. Object classes are then predicted using these ratings. Experiments on Animals with Attributes dataset demonstrate the performance of the proposed method and show its advantages over previous methods based on binary tagging and multi-class classification.