SVHN

Street View House Numbers

홈페이지 · 논문 3,406편

Street View House Numbers (SVHN) is a digit classification benchmark dataset that contains 600,000 32×32 RGB images of printed digits (from 0 to 9) cropped from pictures of house number plates. The cropped images are centered in the digit of interest, but nearby digits and other distractors are kept in the image. SVHN has three sets: training, testing sets and an extra set with 530,000 images that are less difficult and can be used for helping with the training process. Source: Reading Digits in Natural Images with Unsupervised Feature Learning Image Source: http://ufldl.stanford.edu/housenumbers/

Images

벤치마크

Image Classification on SVHN 결과 63개

Semi-Supervised Image Classification on SVHN, 1000 labels 결과 34개

Semi-Supervised Image Classification on SVHN, 250 Labels 결과 30개

Domain Adaptation on SVHN-to-MNIST 결과 14개

Semi-Supervised Image Classification on SVHN, 500 Labels 결과 12개

Semi-Supervised Image Classification on SVHN, 40 Labels 결과 10개

Unsupervised Image Classification on SVHN 결과 4개

Novel Class Discovery on SVHN 결과 2개

Semi-Supervised Image Classification on SVHN, 2000 Labels 결과 2개

Semi-Supervised Image Classification on SVHN, 4000 Labels 결과 2개

Anomaly Detection on SVHN 결과 1개

Sparse Representation-based Classification on SVHN 결과 1개