AI Paper Atlas

Research map / Benchmarks / ImageNet classification

ImageNet classification leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet classification. Best accuracy: 82 (R²MAE, NeurIPS 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.

ImageNet classification · accuracy

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

#accuracy ↑MethodPaperTopic
182R²MAE
ViT-base MAE
Understanding and Enhancing Mask-Based Pretraining towards Universal Representations
NeurIPS 2025 · Table 1
Human and embodied modeling
280.96PELA with both modules
DeiT-Base
PELA: Learning Parameter-Efficient Models with Low-Rank Approximation
CVPR 2024 · Table 7
Pruning and efficient tuning
380SpikedAttention (w/o ReLU)
Swin-T
SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation
NeurIPS 2024 · Table 1
Spiking networks
479.4BiNet-50 (dc-ca), full Bi-volution
ResNet-50
Bi-volution: A Static and Dynamic Coupled Filter
AAAI 2022 · Table 3
CNN features
579.3Mobile-Former-508MMobile-Former: Bridging MobileNet and Transformer
CVPR 2022 · Table 1
Attention and transformers
679.2MDEQ-XLMultiscale Deep Equilibrium Models
NeurIPS 2020 · ImageNet results table
CNN features
778.56ResNet-50 GCP, without down-sampling
ResNet-50
What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective
CVPR 2020 · Table 6
CNN features
878MRP (SimMIM, ResNet50)
ResNet50
Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks
ICLR 2023 · Table 1
Self-supervised and contrastive
977.6Spatially aware values
ResNet-50
Stand-Alone Self-Attention in Vision Models
NeurIPS 2019 · Attention stem ablation table
Attention and transformers
1076.49ResNet50 + TESA
ResNet50
TESA: Tensor Element Self-Attention via Matricization
CVPR 2020 · Table 2a
Attention and transformers
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.