USPS

Introduced in A Database for Handwritten Text Recognition Research1 Jan 1994 archive 2025-07-28

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

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Image Clustering	USPS	SPC NMI 0.954	Selective Pseudo-label Clustering	Lou1sM/clustering	16	Compare
Deep Clustering	USPS	DEKM NMI 82.23	Deep Embedded K-Means Clustering	spdj2271/DEKM +1	1	Compare

Papers archive 2025-07-28

16 shown of 16 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 459. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
Deep Embedded K-Means Clustering	2	1	30 Sep 2021	not harvested
Selective Pseudo-label Clustering	1	1	22 Jul 2021	not harvested
Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement	1	1	23 Nov 2020	not harvested
Deep Transformation-Invariant Clustering	1	1	19 Jun 2020	ran 1 of 10 samples (9 unverified)
Interpretable Visualizations with Differentiating Embedding Networks	1	1	11 Jun 2020	not harvested
Tree-SNE: Hierarchical Clustering and Visualization Using t-SNE	1	1	13 Feb 2020	not harvested
N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding	5	1	16 Aug 2019	ran 2 of 4 samples (2 unverified; 2 pointer-only for licence)
Balanced Self-Paced Learning for Generative Adversarial Clustering Network	0	1	1 Jun 2019	not harvested
Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction	1	1	23 Jan 2019	not harvested
Deep Density-based Image Clustering	1	2	11 Dec 2018	not harvested
Deep clustering: On the link between discriminative models and K-means	1	1	9 Oct 2018	not harvested
Deep Multimodal Subspace Clustering Networks	1	1	17 Apr 2018	not harvested
Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders	2	1	23 Mar 2017	not harvested
Joint Unsupervised Learning of Deep Representations and Image Clusters	3	1	13 Apr 2016	ran 0 of 1 samples (1 unverified)
Graph Degree Linkage: Agglomerative Clustering on a Directed Graph	2	1	25 Aug 2012	not harvested
Divide-and-conquer based Large-Scale Spectral Clustering	1	1		not harvested

Dataset loaders archive 2025-07-28

pytorch.org/vision/stable/generated/torchvision.datasets.USPS.html pytorch/visionpytorch

docs.activeloop.ai/datasets/usps-dataset activeloopai/Hubtfpytorch

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Domain Adaptation Image Clustering Deep Clustering

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

USPS
MNIST-to-USPS
USPS-to-MNIST

3 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections