CIFAR-10

CIFAR-10 is a dataset containing 60,000 32x32 color images across 10 different classes, used to evaluate the performance of machine learning models in image classification tasks.

Papers using CIFAR-10 (5)

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization2026ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule2026The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphs2025The M-factor: A Novel Metric for Evaluating Neural Architecture Search in Resource-Constrained Environments2025SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning2024