Interactively Building a Discriminative Vocabulary of Nameable Attributes

10 years 8 months ago
Interactively Building a Discriminative Vocabulary of Nameable Attributes
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be inefficient (costing substantial effort or expertise) and/or insufficient (descriptive properties need not be discriminative). We introduce an approach to define a vocabulary of attributes that is both human understandable and discriminative. The system takes object/scene-labeled images as input, and returns as output a set of attributes elicited from human annotators that distinguish the categories of interest. To ensure a compact vocabulary and efficient use of annotators' effort, we 1) show how to actively augment the vocabulary such that new attributes resolve inter-class confusions, and 2) propose a novel "nameability" manifold that prioritizes candidate attributes by their likelihood of being associated with a nameable property. We demonstrate the approach with multiple datasets, and show its cle...
Devi Parikh, Kristen Grauman
Added 28 Mar 2011
Updated 29 Apr 2011
Type Conference
Year 2011
Where CVPR
Authors Devi Parikh, Kristen Grauman
Comments (0)