November 21, 2019
Although the popular MNIST dataset [LeCun et al., 1994] is derived from the NIST database [Grother and Hanaoka, 1995], the precise processing steps for this derivation have been lost to time. We propose a reconstruction that is accurate enough to serve as a replacement for the MNIST dataset, with insignificant changes in accuracy. We trace each MNIST digit to its NIST source and its rich metadata such as writer identifier, partition identifier, etc. We also reconstruct the complete MNIST test set with 60,000 samples instead of the usual 10,000. Since the balance 50,000 were never distributed, they can be used to investigate the impact of twenty-five years of MNIST experiments on the reported testing performances. Our limited results unambiguously confirm the trends observed by Recht et al. [2018, 2019]: although the misclassification rates are slightly off, classifier ordering and model selection remain broadly reliable. We attribute this phenomenon to the pairing benefits of comparing classifiers on the same digits. In practice, this suggests that a shifting data distribution is far more dangerous than overusing an adequately distributed testing set.
December 12, 2024
Melissa Hall, Oscar Mañas, Reyhane Askari, Mark Ibrahim, Candace Ross, Pietro Astolfi, Tariq Berrada Ifriqi, Marton Havasi, Yohann Benchetrit, Karen Ullrich, Carolina Braga, Abhishek Charnalia, Maeve Ryan, Mike Rabbat, Michal Drozdzal, Jakob Verbeek, Adriana Romero Soriano
December 12, 2024
December 11, 2024
Pierre Fernandez, Hady Elsahar, Zeki Yalniz, Alexandre Mourachko
December 11, 2024
December 11, 2024
Hu Xu, Bernie Huang, Ellen Tan, Ching-Feng Yeh, Jacob Kahn, Christine Jou, Gargi Ghosh, Omer Levy, Luke Zettlemoyer, Scott Yih, Philippe Brunet, Kim Hazelwood, Ramya Raghavendra, Daniel Li (FAIR), Saining Xie, Christoph Feichtenhofer
December 11, 2024
December 11, 2024
Narine Kokhlikyan, Bargav Jayaraman, Florian Bordes, Chuan Guo, Kamalika Chaudhuri
December 11, 2024
Foundational models
Latest news
Foundational models