AI Paper Atlas

Research map / Benchmarks / CIFAR-100 (IID)

CIFAR-100 (IID) leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-100 (IID). Best accuracy: 73.56 (FedAvg + SphereFed (Ours), ECCV 2022).

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 (IID) · accuracy

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

#accuracy ↑MethodPaperTopic
173.56FedAvg + SphereFed (Ours)
MobileNetV2 (FedAvg)
SphereFed: Hyperspherical Federated Learning
ECCV 2022 · Table 1
Personalized and heterogeneous FL
272.65LRP
ResNet-18
Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation
ICCV 2023 · Table 2
Privacy attacks and secure learning
371.9FOTFederated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
ICLR 2024 · Table 1
Online and replay-based
471.12FedCKMS
CLIP-2.5B
Cluster Based Heterogeneous Federated Foundation Model Adaptation and Fine-Tuning
AAAI 2025 · Table 1
Personalized and heterogeneous FL
569.87FedGKT (ResNet-8)
ResNet-110
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
NeurIPS 2020 · Table: The Test Accuracy of Re
Communication-efficient FL
667.52DecFus
VGG16
DecFus: Decentralized Layer-wise Fusion with Dynamic Exploration and Exploitation
ICML 2026 · Table 1
Communication-efficient FL
763.22DFedCataBoosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
TPAMI 2026 · Table 1
Communication-efficient FL
860.56FedTSA
ResNet18
FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning
ECCV 2024 · Table 2
Personalized and heterogeneous FL
956.06MultiSFL
ResNet18
MultiSFL: Towards Accurate Split Federated Learning via Multi-Model Aggregation and Knowledge Replay
AAAI 2025 · Table 1
Online and replay-based
1056.06FSL-SAGE
ResNet-18
FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
ICML 2025 · Table 1
Communication-efficient FL
4 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.