AI Paper Atlas

Research map / Benchmarks / Tiny-ImageNet

Tiny-ImageNet leaderboard

201 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Tiny-ImageNet. Best accuracy: 99 (SPEAR, 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 · accuracy

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

#accuracy ↑MethodPaperTopic
199SPEAR
6-layer FCNN, width 200
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
NeurIPS 2024 · Table: Reconstruction quality
Privacy attacks and secure learning
294.3pFedSeq
ViT-B/16 + LoRA
Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning
AAAI 2025 · Table 1
Personalized and heterogeneous FL
394.21CLAdapter ViT-L
ViT-L
Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains
NeurIPS 2025 · Table, Results on Tiny-ImageNe
Recognition and long-tail
492DeiT-B/16-D + OCD, ensemble of five
DeiT-B/16-D
OCD: Learning to Overfit with Conditional Diffusion Models
ICML 2023 · Table 2
Fast diffusion sampling
591.93LoTeP-TK
ViT-B/16
Going Deep: Deep Visual Prompting with LoTeP
ECCV 2026 · Table 1
CLIP and zero-shot
691.1I-ViT-L/16 (full: IQ + IC + GC)
ViT-L/16
Knowledge Transfer from Interaction Learning
ICCV 2025 · Table 3
CLIP and zero-shot
790.63GRED-SoftPlusGeneralized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation
TPAMI 2026 · Table 2
Uncertainty and Gaussian processes
889.95RECAP
ViT-large
Resource-Efficient Transformer Pruning for Finetuning of Large Models
CVPR 2024 · Table 1
Pruning and efficient tuning
989.65DPS
ViT-B/16
Deep Probabilistic Supervision for Image Classification
NeurIPS 2026 · Table 1
Recognition and long-tail
1089.19Vanilla KD, original data
ConvNeXt-T → ResNet18
What Makes a Good Dataset for Knowledge Distillation?
CVPR 2025 · Table 2
Knowledge distillation
153 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

Tiny-ImageNet · error rate

13 papers, each with its best reported number for its own method; lower is better.

3 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

Tiny-ImageNet · AUROC

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

2 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

Tiny-ImageNet · FID

11 papers, each with its best reported number for its own method; lower is better.

1 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

Tiny-ImageNet · ECE

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

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