CIFAR-10

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

Papers using CIFAR-10 (4)

Explainable Novel Category Discovery in Semantic Concept Space2026LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation2026AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems2026EdgeFlex-Transformer: Transformer Inference for Edge Devices2025