Tiny-ImageNet
Emerging22papers using it
9HF downloads
0HF likes
2021first seen
'Tiny-ImageNet' is a dataset that contains 200 classes of images, each with 500 training images, used to evaluate the performance of machine learning models in image classification tasks.
Papers using Tiny-ImageNet (22)
- Separate Aggregation of Split Network for Personalized Federated LearningProbabilistic Federated Learning on Uncertain and Heterogeneous Data with Model PersonalizationDiffusion-Guided Semantic Consistency for Multimodal HeterogeneityRethinking LoRA for Privacy-Preserving Federated Learning in Large ModelsDP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large ModelsPrompt Estimation from Prototypes for Federated Prompt Tuning of Vision TransformersDOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated ConstraintsOn the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation ApproachDecoupled Contrastive Learning for Federated LearningpFedDSH: Enabling Knowledge Transfer in Personalized Federated Learning through Data-free Sub-HypernetworkFedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight AveragingOrthogonal Soft Pruning for Efficient Class UnlearningSSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated LearningLocal-Global Knowledge Distillation in Heterogeneous Federated Learning
with Non-IID DataNo Fear of Classifier Biases: Neural Collapse Inspired Federated
Learning with Synthetic and Fixed ClassifierUnlocking the Potential of Federated Learning for Deeper ModelsTowards Instance-adaptive Inference for Federated LearningOvercoming Catastrophic Forgetting in Federated Class-Incremental
Learning via Federated Global Twin GeneratorDivide-and-Conquer the NAS puzzle in Resource Constrained Federated
Learning SystemsText-Enhanced Data-free Approach for Federated Class-Incremental
LearningData-Free Federated Class Incremental Learning with Diffusion-Based
Generative MemoryPIP: Prototypes-Injected Prompt for Federated Class Incremental Learning