CIFAR-10

CIFAR-10 is a dataset that contains 60,000 32x32 color images in 10 different classes, used to evaluate image classification algorithms.

Papers using CIFAR-10 (6)

First-Passage Approach to Optimizing Perturbations for Improved Training of Machine Learning Models2025 · 3 citesKITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches2025Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems2025Cauchy activation function and XNet2024How important are activation functions in regression and classification? A survey, performance comparison, and future directions2022 · 13 citesKernel Regression with Infinite-Width Neural Networks on Millions of Examples2023 · 1 cites