AI Paper Atlas

Research map / Benchmarks / Tiny-ImageNet, α=0.1

Tiny-ImageNet, α=0.1 leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Tiny-ImageNet, α=0.1. Best accuracy: 82.31 (PFPT, NeurIPS 2024).

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.

Tiny-ImageNet, α=0.1 · accuracy

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

#accuracy ↑MethodPaperTopic
182.31PFPT
ViT
Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
NeurIPS 2024 · TinyImageNet results table
Personalized and heterogeneous FL
266.86GGEUR + FedAvg (CLIP+MLP)
FedAvg (CLIP+MLP)
Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
CVPR 2025 · Table 1
Personalized and heterogeneous FL
365.96HiDFD
ResNet34 → ResNet18
Hybrid Data-Free Knowledge Distillation
AAAI 2025 · Table 1
Knowledge distillation
454.67AFL
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
543.86FedAvg + FedDecorr
MobileNetV2
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
ICLR 2023 · TinyImageNet Experiments table
Personalized and heterogeneous FL
643.62FAFIDoes One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning
ICML 2025 · Table 1
Personalized and heterogeneous FL
740.52MultiSFL
DenseNet161
MultiSFL: Towards Accurate Split Federated Learning via Multi-Model Aggregation and Knowledge Replay
AAAI 2025 · Table 1
Online and replay-based
832.45FedDO
CNN
FedDO: Dynamic Client Optimization for Adaptive Federated Learning
ECCV 2026 · Table 1
Communication-efficient FL
922LeaDQLearn How to Query from Unlabeled Data Streams in Federated Learning
AAAI 2025 · Table: Model accuracy on the T
Personalized and heterogeneous FL
1020.3FedMPQ
ResNet44
Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices
CVPR 2024 · Table 1
Communication-efficient FL

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