Papperoni

2010

Sun Database: Large-Scale Scene Recognition From Abbey to Zoo

Jianxiong Xiao, James Hays, K. Ehinger, Aude Oliva, Antonio Torralba

Open PDF Google Scholar

citations

Cite Score

74

AI summary

This paper introduces the Scene UNderstanding (SUN) database with 899 categories and 130,519 images, used to evaluate state-of-the-art scene recognition algorithms and measure human scene classification performance, establishing new performance bounds.

Main Contributions

Introduced the extensive Scene UNderstanding (SUN) database, containing 899 categories and 130,519 images, a significant increase over existing datasets.
Evaluated numerous state-of-the-art algorithms for scene recognition on the SUN database and established new performance bounds.
Measured human scene classification performance on the SUN database and compared it with computational methods.
Proposed a new task of scene detection within images, recognizing scene types within image regions rather than entire images.
Demonstrated that the proposed 'all features' SVM classifier tends to outperform humans on categories with semantically similar yet visually distinct confusing elements.

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.

Citation Graph

Loading graph...

References [32]

Sort:

Filter:

[1]The PASCAL Visual Object Classes (VOC) Challenge

Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman - 2010

7 papers in library cite

Good overview of the VOC challenge and good read, but too long and the part that they describe methods and results is very boring. Also, not related to NNs at the time!

[2]Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce - 2006

14 papers in library cite

It's a fun read, but in the end is just an application of the spatial pyramid matching kernel from the other paper.

[3]Caltech-256 Object Category Dataset

Greg Griffin, Alex Holub, Pietro Perona - 2007

9 papers in library cite

Boring read, but at least they were somewhat impactful.

[4]80 Million Tiny Images: A Large Dataset for Non-Parametric Object and Scene Recognition

Antonio Torralba, Rob Fergus, W. Freeman - 2008

8 papers in library cite

The initial part about data collection and dataset description was nice, but the part of classifying was a bit overkill

[5]WordNet: An Electronic Lexical Database

C. Fellbaum - 1998

12 papers in library cite

It's huge and I don't think it will add much (it is a book)

[6]Histograms of Oriented Gradients for Human Detection

N. Dalal, B. Triggs - 2005

12 papers in library cite

[7]Object Detection With Discriminatively Trained Part-Based Models

P. F. Felzenszwalb, Ross Girshick, D. Mcallester, D. Ramanan - 2010

8 papers in library cite

[8]Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

Aude Oliva, Antonio Torralba - 2001

7 papers in library cite

[9]A Bayesian Hierarchical Model for Learning Natural Scene Categories

Li Fei Fei, Pietro Perona - 2005

4 papers in library cite

[10]Matching Words and Pictures

K. Barnard, P. Duygulu, N. D. Freitas, David Forsyth, D. Blei, M. Jordan - 2003

3 papers in library cite

[11]A Database of Human Segmented Natural Images and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics

D. Martin, C. Fowlkes, D. Tal, Jitendra Malik - 2001

2 papers in library cite

[12]Context-Based Vision System for Place and Object Recognition

Antonio Torralba, Kevin P. Murphy, William T. Freeman, M. A. Rubin - 2003

2 papers in library cite

[13]Robust Wide Baseline Stereo From Maximally Stable Extremal Regions

J. Matas, O. Chum, M. Urban, T. Pajdla - 2002

2 papers in library cite

[14]A Cortical Representation of the Local Visual Environment

R. Epstein, N. Kanwisher - 1998

1 paper in library cites

[15]A Semantic Typicality Measure for Natural Scene Categorization

J. Vogel, B. Schiele - 2004

1 paper in library cites

[16]Basic Objects in Natural Categories

E. Rosch, C. Mervis, W. Gray, D. Johnson, P. B. Braem - 1976

1 paper in library cites

[17]Categories of Environmental Scenes

B. Tversky, K. Hemenway - 1983

1 paper in library cites

[18]Geometric Context From a Single Image

D. Hoiem, A. Efros, M. Hebert - 2005

1 paper in library cites

[19]im2gps: Estimating Geographic Information From a Single Image

James Hays, A. A. Efros - 2008

1 paper in library cites

[20]Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases

J. Philbin, O. Chum, M. Isard, Josef Sivic, Andrew Zisserman - 2008

1 paper in library cites

[21]Matching Local Self-Similarities Across Images and Videos

E. Shechtman, M. Irani - 2007

1 paper in library cites

[22]Multiresolution Gray-Scale and Rotation Invariant Texture Classification With Local Binary Patterns

T. Ojala, M. Pietikainen, T. Maenpaa - 2002

1 paper in library cites

[23]Natural Categories

E. Rosch - 1973

1 paper in library cites

[24]On Seeing Stuff: The Perception of Materials by Humans

E. H. Adelson - 2001

1 paper in library cites

[25]Photo Clip Art

J. F. Lalonde, D. Hoiem, A. A. Efros, C. Rother, John Winn, A. Criminisi - 2007

1 paper in library cites

[26]Pictures and Names: Making the Connection

P. Jolicoeur, M. Gluck, S. Kosslyn - 1984

1 paper in library cites

[27]Recovering Surface Layout From an Image

D. Hoiem, A. Efros, M. Hebert - 2007

1 paper in library cites

[28]Rotation Invariant Image Description With Local Binary Pattern histogram fourier Features

T. Ahonen, J. Matas, C. He, M. Pietikainen - 2009

1 paper in library cites

[29]Semantic Model of Natural Scenes for Content-Based Image Retrieval

J. Vogel, B. Schiele - 2007

1 paper in library cites

[30]Video Compass

J. Kosecka, Wenxuan Zhang - 2002

1 paper in library cites

[31]Video Data Mining Using Configurations of Viewpoint Invariant Regions

Josef Sivic, Andrew Zisserman - 2004

1 paper in library cites

[32]When Is Scene Recognition Just Texture Recognition?

L. Renninger, Jitendra Malik - 2004

1 paper in library cites

Cited by

2

papers in your library

Cites

5

papers in your library

Read

on February 8, 2026

I like the dataset and the approach. Solid methodology also. However, I don't really think "scene within a scene" is good for practical use. Also not too sure about impact.

Tags

Paper Aliases

No aliases