Image Classification

Edit

1701 papers with code • 67 benchmarks • 126 datasets

Image Classification is a fundamental task that attempts to comprehend an entire image as a whole. The goal is to classify the image by assigning it to a specific label. Typically, Image Classification refers to images in which only one object appears and is analyzed. In contrast, object detection involves both classification and localization tasks, and is used to analyze more realistic cases in which multiple objects may exist in an image.

Source: Metamorphic Testing for Object Detection Systems

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
ImageNet	ViT-G/14	Scaling Vision Transformers	See all
CIFAR-10	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
CIFAR-100	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
STL-10	Wide-ResNet-101 (Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
SVHN	WRN28-10 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
MNIST	Branching/Merging CNN + Homogeneous Vector Capsules	No Routing Needed Between Capsules	See all
ImageNet ReaL	Meta Pseudo Labels (EfficientNet-B6-Wide)	Meta Pseudo Labels	See all
Flowers-102	ViT-L/16	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	See all
Clothing1M	PUDistill	Training Classifiers that are Universally Robust to All Label Noise Levels	See all
VTAB-1k	ALIGN (50 hypers/task)	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision	See all
iNaturalist 2018	RegNet-8GF	Grafit: Learning fine-grained image representations with coarse labels	See all
Kuzushiji-MNIST	VGG-5 (Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
mini WebVision 1.0	DivideMix with C2D (ResNet-50)	Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels	See all
Stanford Cars	TResNet-L-V2	ImageNet-21K Pretraining for the Masses	See all
ImageNet V2	ViT-G/14	Scaling Vision Transformers	See all
iNaturalist 2019	Grafit (RegnetY 8GF)	Grafit: Learning fine-grained image representations with coarse labels	See all
Fashion-MNIST	Fine-Tuning DARTS	Fine-Tuning DARTS for Image Classification	See all
ObjectNet	BiT-L (ResNet-152x4)	Big Transfer (BiT): General Visual Representation Learning	See all
WebVision-1000	Heteroscedastic (InceptionResNet-v2)	Correlated Input-Dependent Label Noise in Large-Scale Image Classification	See all
CINIC-10	NAT-M3	Neural Architecture Transfer	See all
EMNIST-Letters	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
Tiered ImageNet 5-way (5-shot)	EGNN+Transduction	Edge-labeling Graph Neural Network for Few-shot Learning	See all
Oxford-IIIT Pets	CeiT-S (384 finetune resolution)	Incorporating Convolution Designs into Visual Transformers	See all
iNaturalist	FixSENet-154	Fixing the train-test resolution discrepancy	See all
smallNORB	Efficient-CapsNet	Efficient-CapsNet: Capsule Network with Self-Attention Routing	See all
EMNIST-Balanced	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
Tiny ImageNet Classification	ViT-B/32 pretrained on ImageNet-21K	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	See all
ObjectNet (Bounding Box)	BiT-L (ResNet)	Big Transfer (BiT): General Visual Representation Learning	See all
EMNIST-Digits	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
MAMe	EfficientNet-B3	The MAMe Dataset: On the relevance of High Resolution and Variable Shape image properties	See all
JFT-300M	V-MoE-H/14 (Every-2)	Scaling Vision with Sparse Mixture of Experts	See all
Food-101N	CleanNet	CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise	See all
CelebA 64x64	cFlow	Null-sampling for Interpretable and Fair Representations	See all
Imbalanced CUB-200-2011	Multi-task	UFPR-Periocular: A Periocular Dataset Collected by Mobile Devices in Unconstrained Scenarios	See all
Noisy MNIST (AWGN)	PCGAN-CHAR	PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters	See all
Noisy MNIST (Motion)	PCGAN-CHAR	PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters	See all
Noisy MNIST (Contrast)	PCGAN-CHAR	PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters	See all
Tiny-ImageNet	UPANets	UPANets: Learning from the Universal Pixel Attention Networks	See all
Fracture/Normal Shoulder Bone X-ray Images on MURA	Our Ensemble Learning-2	Classification of Shoulder X-Ray Images with Deep Learning Ensemble Models	See all
Food-101	NNCLR	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations	See all
EuroSAT	MSMatch Multispectral	MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels	See all
SIPaKMeD	DL+PCA+GWO	Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection	See all
CIFAR-10, 40% Symmetric Noise	FaMUS	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
CIFAR-10, 60% Symmetric Noise	MentorMix	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
CIFAR-100, 40% Symmetric Noise	FaMUS	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
MultiMNIST	CapsNet	Dynamic Routing Between Capsules	See all
QMNIST	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
iCassava'19	E2E-3M	Rethinking Recurrent Neural Networks and Other Improvements for Image Classification	See all
cifar-10,4000	WRN-28-2 + UDA+AutoDropout	AutoDropout: Learning Dropout Patterns to Regularize Deep Networks	See all
ImageNet-10	ResNet-50 + UDA+AutoDropout	AutoDropout: Learning Dropout Patterns to Regularize Deep Networks	See all
WebVision	Ours	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
LabelMe	CoNAL	Learning from Crowds by Modeling Common Confusions	See all
Surrey ASL	E2E-3M	Rethinking Recurrent Neural Networks and Other Improvements for Image Classification	See all
Places205	Barlow Twins (ResNet-50)	Barlow Twins: Self-Supervised Learning via Redundancy Reduction	See all
ArtDL	ResNet-50	A Data Set and a Convolutional Model for Iconography Classification in Paintings	See all
PASCAL VOC 2007	NNCLR	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations	See all
DTD	NNCLR	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations	See all
MNIST-rot-12	PDO-eConv (ours)	PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions	See all
MNIST-rot-12k (DA)	PDO-eConv (ours)	PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions	See all
HErlev	DL+PCA+GWO	Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection	See all
Sports10	Max Margin Contrastive	Contrastive Learning of Generalized Game Representations	See all
CIFAR-100, 60% Symmetric Noise	MentorMix	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
Red MiniImageNet 20% label noise	FaMUS	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
Red MiniImageNet 40% label noise	FaMUS	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
Red MiniImageNet 60% label noise	FaMUS	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
Red MiniImageNet 80% label noise	FaMUS	Faster Meta Update Strategy for Noise-Robust Deep Learning	See all
SARS-COV-2	Fuzzy rank-based fusion of CNN models using Gompertz function	Fuzzy Rank-based Fusion of CNN Models using Gompertz Function for Screening COVID-19 CT-Scans	See all

Show all 67 benchmarks

Collapse benchmarks

Datasets

Subtasks

Small Data Image Classification

Hyperspectral Image Classification

Self-Supervised Image Classification

Learning with noisy labels

Sequential Image Classification

Genre classification

Multi-Label Image Classification

Unsupervised Image Classification

Document Image Classification

Sparse Representation-based Classification

Satellite Image Classification

Superpixel Image Classification

Photo geolocation estimation

Classification Consistency

Artistic style classification

Artist classification

Scale Generalisation

Greatest papers with code

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

tensorflow/tensorflow • • 17 Apr 2017

We present a class of efficient models called MobileNets for mobile and embedded vision applications.

Ranked #181 on Object Detection on COCO test-dev

General Classification Image Classification +1

157,746

Paper
Code

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text

tensorflow/models • • 22 Apr 2021

We show that the convolution-free VATT outperforms state-of-the-art ConvNet-based architectures in the downstream tasks.

Ranked #1 on Action Classification on Moments in Time (using extra training data)

Action Classification Action Recognition +6

70,757

Paper
Code

Searching for MobileNetV3

tensorflow/models • • ICCV 2019

We achieve new state of the art results for mobile classification, detection and segmentation.

Ranked #57 on Semantic Segmentation on Cityscapes test (using extra training data)

Image Classification Neural Architecture Search +2

70,757

Paper
Code

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

tensorflow/models • • CVPR 2019

Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space.

Ranked #7 on Semantic Segmentation on PASCAL VOC 2012 val

Image Classification Neural Architecture Search +1

70,757

Paper
Code

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

tensorflow/models • • NeurIPS 2018

Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.

Ranked #3 on Human Part Segmentation on PASCAL-Part

Image Classification Meta-Learning +2

70,757

Paper
Code

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

tensorflow/models • • ECCV 2018

The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information.

Ranked #2 on Semantic Segmentation on PASCAL VOC 2012 test (using extra training data)

Image Classification Lesion Segmentation +1

70,757

Paper
Code

MobileNetV2: Inverted Residuals and Linear Bottlenecks

tensorflow/models • • CVPR 2018

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.

Ranked #4 on Retinal OCT Disease Classification on OCT2017

Image Classification Object Detection +3

70,757

Paper
Code

Progressive Neural Architecture Search

tensorflow/models • • ECCV 2018

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms.

Ranked #150 on Image Classification on ImageNet

General Classification Image Classification +1

70,757

Paper
Code

Learning Transferable Architectures for Scalable Image Recognition

tensorflow/models • • CVPR 2018

In our experiments, we search for the best convolutional layer (or "cell") on the CIFAR-10 dataset and then apply this cell to the ImageNet dataset by stacking together more copies of this cell, each with their own parameters to design a convolutional architecture, named "NASNet architecture".

Ranked #21 on Image Classification on ImageNet ReaL

Image Classification Neural Architecture Search

70,757

Paper
Code

The iNaturalist Species Classification and Detection Dataset

tensorflow/models • • CVPR 2018

Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.

Ranked #3 on Image Classification on iNaturalist

General Classification Image Classification

70,757

Paper
Code

Image Classification Edit

Benchmarks Add a Result

Datasets

Subtasks

Greatest papers with code

Image Classification

Edit

Benchmarks

Add a Result