A Unified Semantic Embedding: Relating Taxonomies and Attributes

TL;DR

This paper introduces a unified semantic embedding space that integrates taxonomies and attributes for improved object categorization, allowing categories to be represented as combinations of supercategories and attributes.

Contribution

It presents a novel method that explicitly embeds categories, supercategories, and attributes into a shared space, enabling discriminative and interpretable representations.

Findings

Enhanced object categorization accuracy

Categories represented as supercategory plus sparse attributes

Effective discriminative composition learned through regularization

Abstract

We propose a method that learns a discriminative yet semantic space for object categorization, where we also embed auxiliary semantic entities such as supercategories and attributes. Contrary to prior work which only utilized them as side information, we explicitly embed the semantic entities into the same space where we embed categories, which enables us to represent a category as their linear combination. By exploiting such a unified model for semantics, we enforce each category to be represented by a supercategory + sparse combination of attributes, with an additional exclusive regularization to learn discriminative composition.