Image Classification on Oxford-IIIT Pets

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	EffNet-L2 (SAM)	97.1	No	Sharpness-Aware Minimization for Efficiently Imp...	2020-10-03	Code
2	BiT-L (ResNet)	96.62	No	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
3	µ2Net+ (ViT-L/16)	95.5	No	A Continual Development Methodology for Large-sc...	2022-09-15	Code
4	µ2Net (ViT-L/16)	95.3	No	An Evolutionary Approach to Dynamic Introduction...	2022-05-25	Code
5	CeiT-S (384 finetune resolution)	94.9	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
6	CvT-W24	94.73	No	CvT: Introducing Convolutions to Vision Transfor...	2021-03-29	Code
7	CeiT-S	94.6	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
8	CeiT-T (384 finetune resolution)	94.5	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
9	BiT-M (ResNet)	94.47	No	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
10	NAT-M4	94.3	No	Neural Architecture Transfer	2020-05-12	Code
11	NAT-M3	94.1	No	Neural Architecture Transfer	2020-05-12	Code
12	CeiT-T	93.8	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
13	NAT-M2	93.5	No	Neural Architecture Transfer	2020-05-12	Code
14	ResNet-152-SAM	93.3	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
15	ViT-B/16- SAM	93.1	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
16	ViT-S/16- SAM	92.9	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
17	Mixer-B/16- SAM	92.5	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
18	ResNet-50-SAM	91.6	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
19	Mixer-S/16- SAM	88.7	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
20	SE-ResNet-101 (SAP)	86.011	No	Stochastic Subsampling With Average Pooling	2024-09-25	-
21	PreResNet-101	85.5897	No	How to Use Dropout Correctly on Residual Network...	2023-02-13	Code
22	ResNet-101 (ideal number of groups)	77.076	No	On the Ideal Number of Groups for Isometric Grad...	2023-02-07	-

#1EffNet-L2 (SAM)SOTA
97.1
Accuracy· 2020-10-03
Sharpness-Aware Minimization for Efficiently Improving Generalization Code
#2BiT-L (ResNet)SOTA
96.62
Accuracy· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#3µ2Net+ (ViT-L/16)
95.5
Accuracy· 2022-09-15
A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems Code
#4µ2Net (ViT-L/16)
95.3
Accuracy· 2022-05-25
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems Code
#5CeiT-S (384 finetune resolution)
94.9
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#6CvT-W24
94.73
Accuracy· 2021-03-29
CvT: Introducing Convolutions to Vision Transformers Code
#7CeiT-S
94.6
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#8CeiT-T (384 finetune resolution)
94.5
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#9BiT-M (ResNet)
94.47
Accuracy· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#10NAT-M4
94.3
Accuracy· 2020-05-12
Neural Architecture Transfer Code
#11NAT-M3
94.1
Accuracy· 2020-05-12
Neural Architecture Transfer Code
#12CeiT-T
93.8
Accuracy· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#13NAT-M2
93.5
Accuracy· 2020-05-12
Neural Architecture Transfer Code
#14ResNet-152-SAM
93.3
Accuracy· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#15ViT-B/16- SAM
93.1
Accuracy· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#16ViT-S/16- SAM
92.9
Accuracy· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#17Mixer-B/16- SAM
92.5
Accuracy· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#18ResNet-50-SAM
91.6
Accuracy· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#19Mixer-S/16- SAM
88.7
Accuracy· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#20SE-ResNet-101 (SAP)
86.011
Accuracy· 2024-09-25
Stochastic Subsampling With Average Pooling
#21PreResNet-101
85.5897
Accuracy· 2023-02-13
How to Use Dropout Correctly on Residual Networks with Batch Normalization Code
#22ResNet-101 (ideal number of groups)
77.076
Accuracy· 2023-02-07
On the Ideal Number of Groups for Isometric Gradient Propagation