CIFAR-100

CIFAR-100 is a dataset that contains 100 classes of images, each with 600 images, used to evaluate image classification performance in neural networks.

Papers using CIFAR-100 (2)

KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches2025How important are activation functions in regression and classification? A survey, performance comparison, and future directions2022 · 13 cites