CIFAR-10

A foundational computer vision dataset featuring 60,000 labeled 32x32 color images across 10 distinct object classes.

Curated by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton, CIFAR-10 is a staple benchmark for training convolutional neural networks (CNNs). The collection includes 6,000 images per category: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck. Researchers utilize the 50,000 training and 10,000 test samples to prototype architectures quickly due to the manageable 32x32 resolution. It remains a primary tool for evaluating image classification performance and algorithmic efficiency in deep learning.

https://www.cs.toronto.edu/~kriz/cifar.html