SUN attribute database: Discovering, annotating, and recognizing scene attributes

TLDR

The paper introduces the first large-scale scene attribute database. We crowdsourced 102 discriminative attributes, built the SUN attribute database on the SUN categorical database, and trained classifiers to evaluate attribute recognition. The database covers over 700 categories and 14,000 images, and classifiers trained on it can recognize a wide range of material, surface, lighting, functional, affordance, and spatial envelope attributes.

Abstract

In this paper we present the first large-scale scene attribute database. First, we perform crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next, we build the "SUN attribute database" on top of the diverse SUN categorical database. Our attribute database spans more than 700 categories and 14,000 images and has potential for use in high-level scene understanding and fine-grained scene recognition. We use our dataset to train attribute classifiers and evaluate how well these relatively simple classifiers can recognize a variety of attributes related to materials, surface properties, lighting, functions and affordances, and spatial envelope properties.