AI Paper Atlas

Research map / Benchmarks / ImageNet-1K 224×224

ImageNet-1K 224×224 leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet-1K 224×224. Best accuracy: 86.2 (SeTformer-B, AAAI 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.

ImageNet-1K 224×224 · accuracy

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

#accuracy ↑MethodPaperTopic
186.2SeTformer-BSeTformer Is What You Need for Vision and Language
AAAI 2024 · Table: Classification accuracy
Attention and transformers
285.4BiFormer-B*
BiFormer-B
BiFormer: Vision Transformer With Bi-Level Routing Attention
CVPR 2023 · ImageNet-1K comparison table
Attention and transformers
385.1MSPE
ViT-B
MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution
NeurIPS 2024 · Table 1
Attention and transformers
484.6Adventurer-Base, patch 1×1
Adventurer-Base
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
ICML 2025 · Table 1
Attention and transformers
584.5SparX-Mamba-BSparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks
AAAI 2025 · ImageNet-1K results table
Attention and transformers
683.5RepLKNet-31BScaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
CVPR 2022 · ImageNet results table
CNN design
783.5As-ViT LargeAuto-scaling Vision Transformers without Training
ICLR 2022 · Image Classification table
Attention and transformers
882.3Next-DiT, 300ELumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
NeurIPS 2024 · Table: Comparison of Next-DiT
Fast diffusion sampling
981.5PAC-FNO (parallel, 8 AC-FNO blocks)
ConvNeXt-Tiny
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
ICLR 2024 · Figure: Configurations of PAC-
Image restoration
1080.3IA-RED²
DeiT-B
IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers
NeurIPS 2021 · Table: DeiT-Base in different
Attention and transformers

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