Datasets › Stacked MNIST

Stacked MNIST

Introduced by Luke Metz et al. in Unrolled Generative Adversarial Networks1 Jan 2017 archive 2025-07-28

The Stacked MNIST dataset is derived from the standard MNIST dataset with an increased number of discrete modes. 240,000 RGB images in the size of 32×32 are synthesized by stacking three random digit images from MNIST along the color channel, resulting in 1,000 explicit modes in a uniform distribution corresponding to the number of possible triples of digits.

Source: Inclusive GAN: Improving Data and Minority Coverage in Generative Models Image Source: https://arxiv.org/abs/1705.07761

Benchmarks archive 2025-07-28

All 1 leaderboard 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)PaperCode
Image Generation Stacked MNIST VAEBM FID 12.96 VAEBM: A Symbiosis between Variational Autoencoders and... NVlabs/VAEBM 3 Compare

Papers archive 2025-07-28

3 shown of 3 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 43. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models 1 1 1 Oct 2020 ran 6 of 9 samples (3 unverified; 9 pointer-only for licence)
Implicit Generation and Modeling with Energy Based Models 2 1 1 Dec 2019 not harvested
Prescribed Generative Adversarial Networks 2 1 9 Oct 2019 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Stacked MNIST

1 variant name, 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