CIFAR-100

CIFAR-100 is a dataset containing 60,000 32x32 color images across 100 classes, used to evaluate image classification and retrieval performance in machine learning models.

Papers using CIFAR-100 (6)

End-to-end Efficient Representation Learning Via Cascading Combinatorial Optimization2019 · 1 citesFrom Hashing to CNNs: Training BinaryWeight Networks via Hashing2018 · 41 citesEfficient end-to-end learning for quantizable representations2018 · 5 citesIntegrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval2023 · 3 citesEnd-to-End Efficient Representation Learning via Cascading Combinatorial Optimization2019Learning to hash with semantic similarity metrics and empirical KL divergence2020