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

Oxford-IIIT Pet Dataset

Fine-Grained Image Classification Benchmark

Performance Over Time

📊 Showing 13 results | 📏 Metric: Accuracy

Top Performing Models

Rank	Model	Paper	Accuracy	Date	Code
1	OmniVec 📚	OmniVec: Learning robust representations with cross modal sharing	99.20	2023-11-07	-
2	DINOv2 (ViT-g/14, frozen model, linear eval) 📚	DINOv2: Learning Robust Visual Features without Supervision	96.70	2023-04-14	📦 huggingface/transformers 📦 facebookresearch/dinov2 📦 roboflow/rf-detr
3	ViT R26 + S/32 ( Augmented) 📚	Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection	96.28	2021-08-28	📦 mahdi-darvish/gans-augmented-pet-classifier
4	MANO-tiny 📚	Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics	88.31	2025-07-03	📦 AlexColagrande/MANO
5	ALIGN 📚	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision	0.00	2021-02-11	📦 facebookresearch/metaclip 📦 kakaobrain/coyo-dataset 📦 MicPie/clasp 📦 willard-yuan/video-text-retrieval-papers 📦 pwc-1/Paper-8
6	EfficientNet-B7 📚	EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks	0.00	2019-05-28	📦 ultralytics/yolov5 📦 rwightman/pytorch-image-models 📦 open-mmlab/mmdetection
7	Bamboo (ViT-B/16) 📚	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy	0.00	2022-03-15	📦 zhangyuanhan-ai/bamboo 📦 davidzhangyuanhan/bamboo
8	TNT-B	Transformer in Transformer	0.00	2021-02-27	📦 rwightman/pytorch-image-models 📦 PaddlePaddle/PaddleClas 📦 huawei-noah/CV-backbones
9	AutoFormer-S \| 384	AutoFormer: Searching Transformers for Visual Recognition	0.00	2021-07-01	📦 microsoft/AutoML 📦 microsoft/cream
10	FixSENet-154 📚	Fixing the train-test resolution discrepancy	0.00	2019-06-14	📦 facebookresearch/FixRes 📦 libffcv/ffcv-imagenet 📦 kun-woo-park/Deeplearning_project_STL_10

All Papers (13)

OmniVec: Learning robust representations with cross modal sharing

2023

OmniVec

DINOv2: Learning Robust Visual Features without Supervision

2023

DINOv2 (ViT-g/14, frozen model, linear eval)

huggingface/transformers facebookresearch/dinov2

Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection

2021

ViT R26 + S/32 ( Augmented)

mahdi-darvish/gans-augmented-pet-classifier

Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics

2025

MANO-tiny

AlexColagrande/MANO

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

2021

ALIGN

facebookresearch/metaclip kakaobrain/coyo-dataset

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

2019

EfficientNet-B7

ultralytics/yolov5 rwightman/pytorch-image-models

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

2022

Bamboo (ViT-B/16)

zhangyuanhan-ai/bamboo davidzhangyuanhan/bamboo

Transformer in Transformer

2021

TNT-B

rwightman/pytorch-image-models PaddlePaddle/PaddleClas

AutoFormer: Searching Transformers for Visual Recognition

2021

AutoFormer-S | 384

microsoft/AutoML microsoft/cream

Fixing the train-test resolution discrepancy

2019

FixSENet-154

facebookresearch/FixRes libffcv/ffcv-imagenet kun-woo-park/Deeplearning_project_STL_10

AutoAugment: Learning Augmentation Policies from Data

2018

AutoAugment

tensorflow/models tensorflow/models

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

2022

SEER (RegNet10B)

facebookresearch/vissl

Neural Architecture Transfer

2020

NAT-M1

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

Oxford-IIIT Pet Dataset

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (13)

OmniVec: Learning robust representations with cross modal sharing

DINOv2: Learning Robust Visual Features without Supervision

Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection

Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

Transformer in Transformer

AutoFormer: Searching Transformers for Visual Recognition

Fixing the train-test resolution discrepancy

AutoAugment: Learning Augmentation Policies from Data

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

Neural Architecture Transfer

Model	Paper	Accuracy	Date
OmniVec	OmniVec: Learning robust representations with cro…	99.20	2023-11-07
DINOv2 (ViT-g/14, frozen model, linear eval)	DINOv2: Learning Robust Visual Features without S…	96.70	2023-04-14
ViT R26 + S/32 ( Augmented)	Towards Fine-grained Image Classification with Ge…	96.28	2021-08-28
MANO-tiny	Linear Attention with Global Context: A Multipole…	88.31	2025-07-03
ALIGN	Scaling Up Visual and Vision-Language Representat…		2021-02-11
EfficientNet-B7	EfficientNet: Rethinking Model Scaling for Convol…		2019-05-28
Bamboo (ViT-B/16)	Bamboo: Building Mega-Scale Vision Dataset Contin…		2022-03-15
TNT-B	Transformer in Transformer		2021-02-27
AutoFormer-S \| 384	AutoFormer: Searching Transformers for Visual Rec…		2021-07-01
FixSENet-154	Fixing the train-test resolution discrepancy		2019-06-14
AutoAugment	AutoAugment: Learning Augmentation Policies from …		2018-05-24
SEER (RegNet10B)	Vision Models Are More Robust And Fair When Pretr…		2022-02-16
NAT-M1	Neural Architecture Transfer		2020-05-12