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

By Jianxiong Xiao, James Hays, Krista A. Ehinger, Aude Oliva, Antonio Torralba. 2010

4,415 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “The SUN2012 (Xiao et al., 2010) dataset contains 16,873 manually cleaned up and fully annotated images suitable for object detection.”
Microsoft COCO: Common Objects in Context (2014, methodology): “We accomplished this using a surprisingly simple yet effective technique that queries for pairs of objects in conjunction with images retrieved via scene-based queries [17,3].”
Do Better ImageNet Models Transfer Better? (2018, background): “These datasets covered a wide range of image classification tasks, including superordinate-level object classification (CIFAR-10 [37], CIFAR-100 [37], PASCAL VOC 2007 [19], Caltech-101 [20]); fine-grained object classification (Food-101 [5], Birdsnap [4], Stanford Cars [36], FGVC Aircraft [48], Oxfo”
On Robustness and Transferability of Convolutional Neural Networks (2020, background): “13 [68] Jianxiong Xiao, James Hays, Krista A Ehinger, Aude Oliva, and Antonio Torralba.”
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019, neutral): “Sun397 (Xiao et al., 2010) The Sun397 task is a scenery benchmark with 397 classes and, at least, 100 images per class.”
Natural Adversarial Examples (2019, background): “, 2017 [27] treat CIFAR-10 as the in-distribution and treat Gaussian noise and the SUN scene dataset [52] as out-ofdistribution data.”
Learning Visual Features from Large Weakly Supervised Data (2015, methodology): “…experiments on seven test datasets comprising a range of computer-vision tasks: (1) the MIT Indoor dataset [38], (2) the MIT SUN dataset [55], (3) the Stanford 40 Actions dataset [57], (4) the Oxford Flowers dataset [33], (5) the Sports dataset [17], (6) the ImageNet ILSVRC 2014 dataset…”
Webly Supervised Learning of Convolutional Networks (2015, methodology): “Therefore, instead of using random noun phrases, we obtained three lists of categories from ImageNet Challenge [41], SUN database [58] and NEIL knowledge base [9].”
Colorful Image Colorization (2016, methodology): “Here we show results on the dataset from [10], which consists of six scene categories from SUN [28].”
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop (2015, background): “On the other hand, to search for the optimal settings for a large number of parameters, these data-hungry algorithms require a massive amount of training data with humainitiallced labels [4, 6, 23, 24].”
COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “The literature provides definitions for several aspects of stuff and things, including: (1) Shape: Things have characteristic shapes (car, cat, phone), whereas stuff is amorphous (sky, grass, water) [21, 59, 28, 51, 55, 39, 17, 14].”