CINIC-10
Emerging11papers using it
2020first seen
CINIC-10 is a dataset that contains images for evaluating machine learning models, specifically designed to benchmark performance in image classification tasks.
Papers using CINIC-10 (10)
- EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated LearningEnergy and Memory-Efficient Federated Learning With Ordered Layer FreezingTackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable AggregationFedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated LearningGroup Knowledge Transfer: Federated Learning of Large CNNs at the EdgeNo Fear of Heterogeneity: Classifier Calibration for Federated Learning
with Non-IID DataPersonalized Federated Learning with Gaussian ProcessesVFLIP: A Backdoor Defense for Vertical Federated Learning via
Identification and PurificationSparse Personalized Federated LearningCombating Data Imbalances in Federated Semi-supervised Learning with
Dual Regulators