Fine-Grained Image Classification

Edit

71 papers with code • 32 benchmarks • 26 datasets

The Fine-Grained Image Classification task focuses on differentiating between hard-to-distinguish object classes, such as species of birds, flowers, or animals; and identifying the makes or models of vehicles.

( Image credit: Looking for the Devil in the Details )

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
Stanford Cars	TResNet-L-V2 (ImageNet-21K-P pretrain)	ImageNet-21K Pretraining for the Masses	See all
CUB-200-2011	TransFG	TransFG: A Transformer Architecture for Fine-grained Recognition	See all
FGVC Aircraft	TBMSL-Net	Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization	See all
Oxford-IIIT Pets	ViT-H/14	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	See all
Oxford 102 Flowers	ViT-L/16	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	See all
DF20 - Mini	ViT-Large/16 (384)	Danish Fungi 2020 -- Not Just Another Image Recognition Dataset	See all
DF20	ViT-Large/16 (384)	Danish Fungi 2020 -- Not Just Another Image Recognition Dataset	See all
CUB-200-2011	TransFG	TransFG: A Transformer Architecture for Fine-grained Recognition	See all
Food-101	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
NABirds	TransFG	TransFG: A Transformer Architecture for Fine-grained Recognition	See all
Stanford Dogs	TransFG	TransFG: A Transformer Architecture for Fine-grained Recognition	See all
Caltech-101	Wide-ResNet-101 (Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
CompCars	ResNet101-swp	Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition	See all
Birdsnap	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
Bird-225	Wide-ResNet-101 (Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
Fruits-360	Wide-ResNet-101 (Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
Imbalanced CUB-200-2011	PC-Softmax	Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator	See all
SOP	Assemble-ResNet-FGVC-50	Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network	See all
Con-Text	PHOC descriptor + Fisher Vector Encoding	Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features	See all
Bottles	PHOC descriptor + Fisher Vector Encoding	Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features	See all
10 Monkey Species	CNN	Performing Image Classification for 10 Different Monkey Species using CNN	See all
MNIST	Vanilla FC layer only	ProgressiveSpinalNet architecture for FC layers	See all
EMNIST-Digits	VGG-5	ProgressiveSpinalNet architecture for FC layers	See all
EMNIST-Letters	VGG-5	ProgressiveSpinalNet architecture for FC layers	See all
QMNIST	VGG-5	ProgressiveSpinalNet architecture for FC layers	See all
Kuzushiji-MNIST	VGG-5	ProgressiveSpinalNet architecture for FC layers	See all
STL-10	Pre trained wide-resnet-101	ProgressiveSpinalNet architecture for FC layers	See all
BoxCars116K	ResNet152 + COOC	Fine-Grained Vehicle Classification with Unsupervised Parts Co-occurrence Learning	See all
CarFlag-1532	ResNet101-swp	Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition	See all
CarFlag-563	ResNet101-swp	Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition	See all
SUN397	NNCLR	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations	See all
iNaturalist	TASN	Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition	See all

Show all 32 benchmarks

Collapse benchmarks

Datasets

Subtasks

Displaced People Recognition

Greatest papers with code

Deep Residual Learning for Image Recognition

tensorflow/models • • CVPR 2016

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Ranked #2 on Semantic Object Interaction Classification on VLOG

Breast Tumour Classification Domain Generalization +8

70,698

Paper
Code

AutoAugment: Learning Augmentation Policies from Data

tensorflow/models • • 24 May 2018

In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.

Ranked #5 on Fine-Grained Image Classification on Caltech-101

Fine-Grained Image Classification Image Augmentation

70,697

Paper
Code

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

huggingface/transformers • • ICLR 2021

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.

Ranked #1 on Image Classification on Tiny ImageNet Classification (using extra training data)

Document Image Classification Fine-Grained Image Classification

48,862

Paper
Code

ResMLP: Feedforward networks for image classification with data-efficient training

rwightman/pytorch-image-models • • 7 May 2021

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification.

Ranked #5 on Image Classification on ImageNet V2 (using extra training data)

Data Augmentation Fine-Grained Image Classification +3

11,791

Paper
Code

TResNet: High Performance GPU-Dedicated Architecture

rwightman/pytorch-image-models • • 30 Mar 2020

In this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency.

Ranked #6 on Fine-Grained Image Classification on Oxford 102 Flowers (using extra training data)

Fine-Grained Image Classification General Classification +2

11,791

Paper
Code

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

rwightman/pytorch-image-models • • ICML 2019

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.

Ranked #2 on Fine-Grained Image Classification on Birdsnap (using extra training data)

Fine-Grained Image Classification Neural Architecture Search +1

11,791

Paper
Code

Transformer in Transformer

rwightman/pytorch-image-models • • 27 Feb 2021

In this paper, we point out that the attention inside these local patches are also essential for building visual transformers with high performance and we explore a new architecture, namely, Transformer iN Transformer (TNT).

Ranked #7 on Fine-Grained Image Classification on Oxford-IIIT Pets

Fine-Grained Image Classification

11,783

Paper
Code

Training data-efficient image transformers & distillation through attention

lucidrains/vit-pytorch • • 23 Dec 2020

In this work, we produce a competitive convolution-free transformer by training on Imagenet only.

Ranked #2 on Image Classification on iNaturalist 2018

Fine-Grained Image Classification

5,108

Paper
Code

When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations

google-research/vision_transformer • • 3 Jun 2021

Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures.

Ranked #1 on Domain Generalization on ImageNet-R (Top 1 Accuracy metric)

Domain Generalization Fine-Grained Image Classification +1

3,162

Paper
Code

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

tensorflow/lingvo • • NeurIPS 2019

Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks.

Ranked #4 on Fine-Grained Image Classification on Birdsnap (using extra training data)

Fine-Grained Image Classification Machine Translation

2,264

Paper
Code

Fine-Grained Image Classification Edit

Benchmarks Add a Result

Datasets

Subtasks

Greatest papers with code

Fine-Grained Image Classification

Edit

Benchmarks

Add a Result