MNIST-M

Introduced by Ganin et al. in Domain-Adversarial Training of Neural Networks

MNIST-M is created by combining MNIST digits with the patches randomly extracted from color photos of BSDS500 as their background. It contains 59,001 training and 90,001 test images.

Source: A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

Homepage

Benchmarks

Add a new result Link an existing benchmark

Trend	Task	Dataset Variant	Best Model	Paper	Code
	Domain Adaptation	MNIST-to-MNIST-M	DRANet

Papers

Paper	Code	Results	Date	Stars

Dataset Loaders

Add Remove

mashaan14/MNIST-M

Tasks

Domain Adaptation

Similar Datasets

Office-Home

USPS

PACS

SVHN

Source: https://arxiv.org/pdf/1505.07818v4.pdf.

Usage

License

Unknown

Modalities

Images

MNIST-M

Benchmarks Edit Add a new result Link an existing benchmark

Papers

Dataset Loaders Edit Add Remove

Tasks Edit