Image Classification on Stanford Cars

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	efficient adaptive ensembling	96.868	No	Efficient Adaptive Ensembling for Image Classifi...	2022-06-15	-
2	TResNet-L-V2	96.32	No	ImageNet-21K Pretraining for the Masses	2021-04-22	Code
3	SR-GNN	96.1	No	SR-GNN: Spatial Relation-aware Graph Neural Netw...	2022-09-05	Code
4	SaSPA + CAL	95.72	No	Advancing Fine-Grained Classification by Structu...	2024-06-20	Code
5	EfficientNetV2-L	95.1	No	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
6	EfficientNetV2-M	94.6	No	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
7	CaiT-M-36 U 224	94.2	No	Going deeper with Image Transformers	2021-03-31	Code
8	ELP	94.2	No	-	-	Code
9	ImageNet + iNat on WS-DAN	94.1	No	Domain Adaptive Transfer Learning on Visual Atte...	2020-10-06	-
10	CeiT-S (384 finetune resolution)	94.1	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
11	EfficientNetV2-S	93.8	No	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
12	ViT-B/16 (RPE w/ GAB)	93.743	No	Understanding Gaussian Attention Bias of Vision ...	2023-05-08	Code
13	CeiT-S	93.2	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
14	GFNet-H-B	93.2	Yes	Global Filter Networks for Image Classification	2021-07-01	Code
15	CeiT-T (384 finetune resolution)	93	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
16	MACNN	92.8	No	-	-	Code
17	CeiT-T	90.5	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
18	LeViT-192	89.8	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
19	ResMLP-24	89.5	No	ResMLP: Feedforward networks for image classific...	2021-05-07	Code
20	LeViT-384	89.3	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
21	LeViT-128	88.6	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
22	LeViT-128S	88.4	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
23	LeViT-256	88.2	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
24	MPFG + CLIP	86.79	Yes	-	-	Code
25	SE-ResNet-101 (SAP)	85.812	No	Stochastic Subsampling With Average Pooling	2024-09-25	-
26	ResMLP-12	84.6	No	ResMLP: Feedforward networks for image classific...	2021-05-07	Code
27	ViT-M/16 (RPE w/ GAB)	83.89	No	Understanding Gaussian Attention Bias of Vision ...	2023-05-08	Code
28	NNCLR	67.1	No	With a Little Help from My Friends: Nearest-Neig...	2021-04-29	Code
29	MANO-tiny	65.68	Yes	Linear Attention with Global Context: A Multipol...	2025-07-03	Code

#1efficient adaptive ensemblingSOTA
96.868
Accuracy· 2022-06-15
Efficient Adaptive Ensembling for Image Classification
#2TResNet-L-V2SOTA
96.32
Accuracy· 2021-04-22
ImageNet-21K Pretraining for the Masses Code
#3SR-GNN
96.1
Accuracy· 2022-09-05
SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization Code
#4SaSPA + CAL
95.72
Accuracy· 2024-06-20
Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation Code
#5EfficientNetV2-LSOTA
95.1
Accuracy· 2021-04-01
EfficientNetV2: Smaller Models and Faster Training Code
#6EfficientNetV2-M
94.6
Accuracy· 2021-04-01
EfficientNetV2: Smaller Models and Faster Training Code
#7CaiT-M-36 U 224SOTA
94.2
Accuracy· 2021-03-31
Going deeper with Image Transformers Code
#8ELP
94.2
Accuracy
No paperCode
#9ImageNet + iNat on WS-DANSOTA
94.1
Accuracy· 2020-10-06
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization
#10CeiT-S (384 finetune resolution)
94.1
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#11EfficientNetV2-S
93.8
Accuracy· 2021-04-01
EfficientNetV2: Smaller Models and Faster Training Code
#12ViT-B/16 (RPE w/ GAB)
93.743
Accuracy· 2023-05-08
Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields Code
#13CeiT-S
93.2
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#14GFNet-H-B
93.2
Accuracy· Extra Data· 2021-07-01
Global Filter Networks for Image Classification Code
#15CeiT-T (384 finetune resolution)
93
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#16MACNN
92.8
Accuracy
No paperCode
#17CeiT-T
90.5
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#18LeViT-192
89.8
Accuracy· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#19ResMLP-24
89.5
Accuracy· 2021-05-07
ResMLP: Feedforward networks for image classification with data-efficient training Code
#20LeViT-384
89.3
Accuracy· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#21LeViT-128
88.6
Accuracy· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#22LeViT-128S
88.4
Accuracy· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#23LeViT-256
88.2
Accuracy· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#24MPFG + CLIP
86.79
Accuracy· Extra Data
No paperCode
#25SE-ResNet-101 (SAP)
85.812
Accuracy· 2024-09-25
Stochastic Subsampling With Average Pooling
#26ResMLP-12
84.6
Accuracy· 2021-05-07
ResMLP: Feedforward networks for image classification with data-efficient training Code
#27ViT-M/16 (RPE w/ GAB)
83.89
Accuracy· 2023-05-08
Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields Code
#28NNCLR
67.1
Accuracy· 2021-04-29
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations Code
#29MANO-tiny
65.68
Accuracy· Extra Data· 2025-07-03
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics Code