(If you are using Microsoft Windows, you may need to replace / by \ in the following files.) To plot the curve in Figure 4(b) of the paper, we use the first n=(1, 5, 10, 20) images outof the 50 training images per class for training,Īnd use all the same 50 testing images for testing no matter what size the training set is. (tar.gz file, 39GB, md5sum=8ca2778205c41d23104230ba66911c7a).įor the results in the paper we use a subset of the dataset that has 50 training images and 50 testing images per class,Īveraging over the 10 partitions in the following.The images provided here are for research purposes only. The number of images varies across categories, but there are at least 100 images per category, and 108,754 images in total. The database contains 397 categories SUN dataset used in the benchmark of the paper. We visualize the results using the combined kernel from all features for the first training and testing partition in the following webpage.įor each of the 397 categories, we show the class name, the ROC curve, 5 sample traning images, 5 sample correct predictions, 5 most confident false positives (with true label), and 5 least confident false negatives (with wrong predicted label).
Download Figure4b in Matlab Editable Format (You can put your own curve in the figure.).The results are shown in the figure on the right. We use 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of performance. International Journal of Computer Vision ( IJCV) SUN Database: Exploring a Large Collection of Scene Categories IEEE Conference on Computer Vision and Pattern Recognition ( CVPR) SUN Database: Large-scale Scene Recognition from Abbey to Zoo. We measure human scene classification performance on the SUN database and compare this with computational methods.
In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. Whereas standard databases for object categorization contain hundreds of different classes of objects, the largest available dataset of scene categories contains only 15 classes.
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. Scene categorization is a fundamental problem in computer vision. SUN Database: Large-scale Scene Recognition from Abbey to Zoo SUN Database: Scene Categorization Benchmark Abstract