CIFAR-10 Note, this post is from 2011 and slightly outdated in some places. Statistics. CIFAR-10 consists of 50,000 training images, all of them in 1 of 10 categories (displayed left). The test set consists of 10,000 novel images from the same categories, and the task is to classify each to its category. The state of the art is currently at about 80% classification accuracy (4000 centroids), achieved by Adam Coates et al. (PDF). This paper achieved the accuracy by using whitening, k-means to lea...