SUN database: Large-scale scene recognition from abbey to zoo

Abstract

Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object categorization contain hundreds of different classes of objects, the largest available dataset of scene categories contains only 15 classes. In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. We use 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of performance. We measure human scene classification performance on the SUN database and compare this with computational methods. Additionally, we study a finer-grained scene representation to detect scenes embedded inside of larger scenes.

Keywords

CategorizationComputer scienceScene statisticsArtificial intelligenceObject (grammar)Representation (politics)Scale (ratio)Variety (cybernetics)Scope (computer science)Cognitive neuroscience of visual object recognitionDatabasePattern recognition (psychology)Computer visionPerceptionGeographyCartography

Affiliated Institutions

Related Publications

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

Geneviève Patterson , James Hays

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,...

2012 857 citations

ConceptLearner: Discovering visual concepts from weakly labeled image collections

Bolei Zhou , Vignesh Jagadeesh , Robinson Piramuthu

Discovering visual knowledge from weakly labeled data is crucial to scale up computer vision recognition systems, since it is expensive to obtain fully labeled data for a large ...

2015 40 citations

Recognizing indoor scenes

Ariadna Quattoni , Antonio Torralba

We propose a scheme for indoor place identification based on the recognition of global scene views. Scene views are encoded using a holistic representation that provides low-res...

2009 2009 IEEE Conference on Computer Visi... 1464 citations

Object class recognition by unsupervised scale-invariant learning

Rob Fergus , Pietro Perona , Andrew Zisserman

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible const...

2003 2035 citations

A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

Rob Fergus , Pietro Perona , Andrew Zisserman

We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images ...

2005 266 citations

Publication Info

Year: 2010
Type: article
Pages: 3485-3492
Citations: 3052
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

SUN database: Large-scale scene recognition from abbey to zoo

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

3052

OpenAlex

Cite This

APA Style

                            
                                    Jianxiong Xiao, 
                                
                                    James Hays, 
                                
                                    Krista A. Ehinger
                                
                                et al.
                            
                            (2010). 
                            SUN database: Large-scale scene recognition from abbey to zoo. 
                            
                            , 3485-3492.
                            https://doi.org/10.1109/cvpr.2010.5539970

Identifiers

DOI: 10.1109/cvpr.2010.5539970