Search Machine Learning Repository: Analogy-preserving Semantic Embedding for Visual Object Categorization
Authors: Sung J. Hwang, Kristen Grauman and Fei Sha
Conference: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
Year: 2013
Pages: 639-647
Abstract: In multi-class categorization tasks, knowledge about the classes' semantic relationships can provide valuable information beyond the class labels themselves. However, existing techniques focus on preserving the semantic distances between classes (e.g., according to a given object taxonomy for visual recognition), limiting the influence to pairwise structures. We propose to model \emph{analogies} that reflect the relationships between multiple pairs of classes simultaneously, in the form $p$ is to $q$, as $r$ is to $s$"". We translate semantic analogies into higher-order geometric constraints called \emph{analogical parallelograms}, and use them in a novel convex regularizer for a discriminatively learned label embedding. Furthermore, we show how to discover analogies from attribute-based class descriptions, and how to prioritize those likely to reduce inter-class confusion. Evaluating our Analogy-preserving Semantic Embedding (ASE) on two visual recognition datasets, we demonstrate clear improvements over existing approaches, both in terms of recognition accuracy and analogy completion.
[pdf] [BibTeX]

authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).