Learning Scalable Discriminative Attributes with Sample Relatedness

Attributes are widely used as mid-level descriptors of object properties in object recognition and retrieval. Mostly, such attributes are manually pre-defined based on domain knowledge, and their number is fixed. However, pre-defined attributes may fail to adapt to the properties of the data at hand, may not necessarily be discriminative, and/or may not generalize well. In this work, we propose a dictionary learning framework that flexibly adapts to the complexity of the given data set and reliably discovers the inherent discriminative mid-level binary features in the data. We use sample relatedness information to improve the generalization of the learned dictionary. We demonstrate that our framework is applicable to both object recognition and complex image retrieval tasks even with few training exam- ples. Moreover, the learned dictionary also help classify novel object categories. Experimental results on the Ani- mals with Attributes, ILSVRC2010 and PASCAL VOC2007 datasets indicate that using relatedness information leads to significant performance gains over established baselines.

Authors: Jiashi Feng, Stefanie Jegelka, Trevor Darrell
Publication Date: May 2014
Conference: CVPR