Digit-5

The 'Digit-5' dataset is a benchmark used to evaluate the performance of federated learning models by providing a collection of handwritten digit images sampled from five different domains.

Papers using Digit-5 (2)

Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains2024 · 2 citesAn Enhanced Federated Prototype Learning Method under Domain Shift2024 · 1 cites