ML Research Wiki / Benchmarks / Fine-Grained Image Classification / Oxford-IIIT Pets

Oxford-IIIT Pets

Fine-Grained Image Classification Benchmark

Performance Over Time

📊 Showing 19 results | 📏 Metric: Accuracy

Top Performing Models

Rank	Model	Paper	Accuracy	Date	Code
1	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	97.10	2020-10-03	📦 davda54/sam 📦 google-research/sam 📦 moskomule/sam.pytorch
2	BiT-L (ResNet)	Big Transfer (BiT): General Visual Representation Learning	96.62	2019-12-24	📦 google-research/big_transfer 📦 sayakpaul/FunMatch-Distillation 📦 bethgelab/InDomainGeneralizationBenchmark
3	µ2Net+ (ViT-L/16)	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems	95.50	2022-09-15	📦 google-research/google-research
4	µ2Net (ViT-L/16)	An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems	95.30	2022-05-25	📦 google-research/google-research
5	BiT-M (ResNet)	Big Transfer (BiT): General Visual Representation Learning	94.47	2019-12-24	📦 google-research/big_transfer 📦 sayakpaul/FunMatch-Distillation 📦 bethgelab/InDomainGeneralizationBenchmark
6	NAT-M4	Neural Architecture Transfer	94.30	2020-05-12	📦 human-analysis/neural-architecture-transfer 📦 awesomelemon/encas
7	NAT-M3	Neural Architecture Transfer	94.10	2020-05-12	📦 human-analysis/neural-architecture-transfer 📦 awesomelemon/encas
8	NAT-M2	Neural Architecture Transfer	93.50	2020-05-12	📦 human-analysis/neural-architecture-transfer 📦 awesomelemon/encas
9	ResNet-152-SAM	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations	93.30	2021-06-03	📦 google-research/vision_transformer 📦 ttt496/VisionTransformer
10	ViT-B/16- SAM	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations	93.10	2021-06-03	📦 google-research/vision_transformer 📦 ttt496/VisionTransformer

All Papers (19)

Sharpness-Aware Minimization for Efficiently Improving Generalization

2020

EffNet-L2 (SAM)

davda54/sam google-research/sam

Big Transfer (BiT): General Visual Representation Learning

2019

BiT-L (ResNet)

google-research/big_transfer sayakpaul/FunMatch-Distillation

A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

2022

µ2Net+ (ViT-L/16)

google-research/google-research

An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems

2022

µ2Net (ViT-L/16)

google-research/google-research

Big Transfer (BiT): General Visual Representation Learning

2019

BiT-M (ResNet)

google-research/big_transfer sayakpaul/FunMatch-Distillation

Neural Architecture Transfer

2020

NAT-M4

human-analysis/neural-architecture-transfer awesomelemon/encas

Neural Architecture Transfer

2020

NAT-M3

human-analysis/neural-architecture-transfer awesomelemon/encas

Neural Architecture Transfer

2020

NAT-M2

human-analysis/neural-architecture-transfer awesomelemon/encas

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

2021

ResNet-152-SAM

google-research/vision_transformer ttt496/VisionTransformer

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

2021

ViT-B/16- SAM

google-research/vision_transformer ttt496/VisionTransformer

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

2021

ViT-S/16- SAM

google-research/vision_transformer ttt496/VisionTransformer

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

2021

Mixer-B/16- SAM

google-research/vision_transformer ttt496/VisionTransformer

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

2021

ResNet-50-SAM

google-research/vision_transformer ttt496/VisionTransformer

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

2021

Mixer-S/16- SAM

google-research/vision_transformer ttt496/VisionTransformer

Stochastic Subsampling With Average Pooling

2024

SE-ResNet-101 (SAP)

How to Use Dropout Correctly on Residual Networks with Batch Normalization

2023

PreResNet-101

kmbmjn/DropoutCorrectly

On the Ideal Number of Groups for Isometric Gradient Propagation

2023

ResNet-101 (ideal number of groups)

Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

2020

Assemble-ResNet-FGVC-50

clovaai/assembled-cnn

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

2020

ViT-B/16

huggingface/transformers labmlai/annotated_deep_learning_paper_implementations

Oxford-IIIT Pets

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (19)

Sharpness-Aware Minimization for Efficiently Improving Generalization

Big Transfer (BiT): General Visual Representation Learning

A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems

Big Transfer (BiT): General Visual Representation Learning

Neural Architecture Transfer

Neural Architecture Transfer

Neural Architecture Transfer

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

Stochastic Subsampling With Average Pooling

How to Use Dropout Correctly on Residual Networks with Batch Normalization

On the Ideal Number of Groups for Isometric Gradient Propagation

Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Model	Paper	Accuracy	Date
EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Impr…	97.10	2020-10-03
BiT-L (ResNet)	Big Transfer (BiT): General Visual Representation…	96.62	2019-12-24
µ2Net+ (ViT-L/16)	A Continual Development Methodology for Large-sca…	95.50	2022-09-15
µ2Net (ViT-L/16)	An Evolutionary Approach to Dynamic Introduction …	95.30	2022-05-25
BiT-M (ResNet)	Big Transfer (BiT): General Visual Representation…	94.47	2019-12-24
NAT-M4	Neural Architecture Transfer	94.30	2020-05-12
NAT-M3	Neural Architecture Transfer	94.10	2020-05-12
NAT-M2	Neural Architecture Transfer	93.50	2020-05-12
ResNet-152-SAM	When Vision Transformers Outperform ResNets witho…	93.30	2021-06-03
ViT-B/16- SAM	When Vision Transformers Outperform ResNets witho…	93.10	2021-06-03
ViT-S/16- SAM	When Vision Transformers Outperform ResNets witho…	92.90	2021-06-03
Mixer-B/16- SAM	When Vision Transformers Outperform ResNets witho…	92.50	2021-06-03
ResNet-50-SAM	When Vision Transformers Outperform ResNets witho…	91.60	2021-06-03
Mixer-S/16- SAM	When Vision Transformers Outperform ResNets witho…	88.70	2021-06-03
SE-ResNet-101 (SAP)	Stochastic Subsampling With Average Pooling	86.01	2024-09-25
PreResNet-101	How to Use Dropout Correctly on Residual Networks…	85.59	2023-02-13
ResNet-101 (ideal number of groups)	On the Ideal Number of Groups for Isometric Gradi…	77.08	2023-02-07
Assemble-ResNet-FGVC-50	Compounding the Performance Improvements of Assem…	5.70	2020-01-17
ViT-B/16	An Image is Worth 16x16 Words: Transformers for I…		2020-10-22