Image Classification on ImageNet

1080개 결과 · ⬇ CSV · JSON

Top 1 Accuracy

Rank	Model	Top 1 Accuracy	Number of params	GFLOPs	Hardware Burden	Top 5 Accuracy	Operations per network pass	Paper	Code	Year
1	Vision Transformers for Kidney Stone Ima 자동 추출	95.2	–	–	–	–	–	Vision Transformers for Kidney Stone Image Classification: A Comparative Study with CNNs		2025
2	AEGIS 자동 추출	92.1	–	–	–	–	–	AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors		2026
3	CoCa (finetuned)	91.0%	2100M	–	–	–	–	CoCa: Contrastive Captioners are Image-Text Foundation Models	mlfoundations/open_clip · facebookresearch/multimodal · lucidrains/CoCa-pytorch · +3	2022
4	Model soups (BASIC-L)	90.98%	2440M	–	–	–	–	Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time	mlfoundations/model-soups · Burf/ModelSoups · facebookresearch/ModelRatatouille · +3	2022
5	Model soups (ViT-G/14)	90.94%	1843M	–	–	–	–	Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time	mlfoundations/model-soups · Burf/ModelSoups · facebookresearch/ModelRatatouille · +3	2022
6	DaViT-G	90.4%	1437M	1038	–	–	–	DaViT: Dual Attention Vision Transformers	rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · dingmyu/davit · +1	2022
7	DaViT-H	90.2%	362M	334	–	–	–	DaViT: Dual Attention Vision Transformers	rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · dingmyu/davit · +1	2022
7	Meta Pseudo Labels (EfficientNet-L2)	90.2%	480M	–	95040G	98.8	–	Meta Pseudo Labels	google-research/google-research · kekmodel/MPL-pytorch · sayakpaul/PAWS-TF · +6	2020
9	SwinV2-G	90.17%	3000M	–	–	–	–	Swin Transformer V2: Scaling Up Capacity and Resolution	rwightman/pytorch-image-models · microsoft/Swin-Transformer · PaddlePaddle/PaddleDetection · +20	2021
10	MAWS (ViT-6.5B)	90.1%	6500M	–	–	–	–	The effectiveness of MAE pre-pretraining for billion-scale pretraining	facebookresearch/maws	2023
11	Florence-CoSwin-H	90.05%	893M	–	–	99.02	–	Florence: A New Foundation Model for Computer Vision	microsoft/unicl · MindCode-4/code-3	2021
12	Meta Pseudo Labels (EfficientNet-B6-Wide)	90%	390M	–	–	–	–	Meta Pseudo Labels	google-research/google-research · kekmodel/MPL-pytorch · sayakpaul/PAWS-TF · +6	2020
12	RevCol-H	90.0%	2158M	–	–	–	–	Reversible Column Networks	megvii-research/revcol	2022
14	MAWS (ViT-2B)	89.8%	2000M	–	–	–	–	The effectiveness of MAE pre-pretraining for billion-scale pretraining	facebookresearch/maws	2023
15	EVA	89.7%	1000M	–	–	–	–	EVA: Exploring the Limits of Masked Visual Representation Learning at Scale	rwightman/pytorch-image-models · open-mmlab/mmselfsup · baaivision/eva · +3	2022
16	M3I Pre-training (InternImage-H)	89.6%	–	–	–	–	–	Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information	OpenGVLab/M3I-Pretraining	2022
16	ViT-L/16 (384res, distilled from ViT-22B)	89.6%	307M	–	–	–	–	Scaling Vision Transformers to 22 Billion Parameters	lucidrains/flash-cosine-sim-attention	2023
16	InternImage-H	89.6%	1080M	1478	–	–	–	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions	opengvlab/internimage · OpenGVLab/M3I-Pretraining · chenller/mmseg-extension	2022
19	MaxViT-XL (512res, JFT)	89.53%	–	–	–	–	–	MaxViT: Multi-Axis Vision Transformer	huggingface/pytorch-image-models · lucidrains/vit-pytorch · lucidrains/imagen-pytorch · +12	2022
20	AIMv2-3B (448 res)	89.5%	–	–	–	–	–	Multimodal Autoregressive Pre-training of Large Vision Encoders	apple/ml-aim	2024