SVHN

Dataset Card for Street View House Numbers Dataset Summary SVHN is a real-world image dataset for developing machine learning and object recognition algorithms with minimal requirement on data preprocessing and formatting. It can be seen as similar in flavor to MNIST (e.g., the images are of small cropped digits), but incorporates an order of magnitude more labeled data (over 600,000 digit images) and comes from a significantly harder, unsolved, real world problem… See the full description on the dataset page: https://huggingface.co/datasets/ufldl-stanford/svhn.

Papers using SVHN (2)

OOD Augmentation May Be At Odds With Open-set Recognition2022 · 2 citesCoswin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-scale Vision2025