AI Paper Atlas

Research map / Benchmarks / CIFAR-100, α=0.1

CIFAR-100, α=0.1 leaderboard

20 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-100, α=0.1. Best accuracy: 94.39 (GGEUR + FedAvg (CLIP+MLP), CVPR 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CIFAR-100, α=0.1 · accuracy

20 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
194.39GGEUR + FedAvg (CLIP+MLP)
FedAvg (CLIP+MLP)
Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
CVPR 2025 · Table 2
Personalized and heterogeneous FL
284.1CAL
ResNet
Neural Collapse To Multiple Centers For Imbalanced Data
NeurIPS 2024 · Table 2
Recognition and long-tail
376.93HiDFD
ResNet34 → ResNet18
Hybrid Data-Free Knowledge Distillation
AAAI 2025 · Table 1
Knowledge distillation
476.5ETF Classifier + DR
ResNet
Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
NeurIPS 2022 · Long-tailed classification tab
Recognition and long-tail
575.08PFPT
ViT
Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
NeurIPS 2024 · CIFAR-100 results table
Personalized and heterogeneous FL
669.6FedType private (pFedBayes)
ResNet-18 proxy
Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning
ICML 2024 · Table 1
Personalized and heterogeneous FL
767.12FedAvg + FedDecorr
MobileNetV2
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
ICLR 2023 · CIFAR10/100 Experiments table
Personalized and heterogeneous FL
861.92FedDO
VGG-11
FedDO: Dynamic Client Optimization for Adaptive Federated Learning
ECCV 2026 · Table 1
Communication-efficient FL
960.66FedPLL-LAAR
ResNet-34
Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization
AAAI 2024 · Table 2
Personalized and heterogeneous FL
1058.56AFL
ResNet-18 pretrained on ImageNet-1k
AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
CVPR 2025 · Table 1
Communication-efficient FL
10 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.