USPS

Introduced by Jonathan J. Hull in A Database for Handwritten Text Recognition Research

USPS is a digit dataset automatically scanned from envelopes by the U.S. Postal Service containing a total of 9,298 16×16 pixel grayscale samples; the images are centered, normalized and show a broad range of font styles.

Source: Hallucinating Agnostic Images to Generalize Across Domains

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Clustering	USPS	SPC
Domain Adaptation	MNIST-to-USPS	FACT
Domain Adaptation	USPS-to-MNIST	FACT
Deep Clustering	USPS	DEKM

Papers

Paper	Code	Results	Date	Stars

Dataset Loaders

Add Remove

pytorch/vision

15,988

activeloopai/Hub

8,043

Tasks

Domain Adaptation
Image Clustering
Deep Clustering

Similar Datasets

MNIST

MNIST-M

SVHN

Source: https://ieeexplore.ieee.org/document/291440.

Usage

License

Unknown

Modalities

Images

USPS

Benchmarks Edit Add a new result Link an existing benchmark

Papers

Dataset Loaders Edit Add Remove

Tasks Edit