Image Classification Edit Task

Computer Vision

1345

papers with code

benchmarks

datasets

About
Edit

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

Libraries

torchvision

8,471 stars · 61 models

PyTorch Image Models

7,651 stars · 337 models

Benchmarks

Add a Result

DATASET	BEST METHOD	PAPER TITLE	COMPARE
ImageNet	Meta Pseudo Labels (EfficientNet-L2)	Meta Pseudo Labels	See all
CIFAR-10	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
CIFAR-100	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
SVHN	WRN28-10 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
MNIST	Branching/Merging CNN + Homogeneous Filter Capsules	A Branching and Merging Convolutional Network with Homogeneous Filter Capsules	See all
VTAB-1k	ViT-H/14	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	See all
Kuzushiji-MNIST	VGG-5 (Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
ImageNet ReaL	Meta Pseudo Labels (EfficientNet-B6-Wide)	Meta Pseudo Labels	See all
Flowers-102	EffNet-L2 (SAM)	Sharpness-Aware Minimization for Efficiently Improving Generalization	See all
Clothing1M	ELR+	Early-Learning Regularization Prevents Memorization of Noisy Labels	See all
iNaturalist 2018	RegNet-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
CINIC-10	NAT-M4	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
ObjectNet	BiT-L (ResNet-152x4)	Big Transfer (BiT): General Visual Representation Learning	See all
smallNORB	Efficient-CapsNet	Efficient-CapsNet: Capsule Network with Self-Attention Routing	See all
EMNIST-Digits	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
EMNIST-Balanced	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
iNaturalist	FixSENet-154	Fixing the train-test resolution discrepancy	See all
ObjectNet (Bounding Box)	BiT-L (ResNet)	Big Transfer (BiT): General Visual Representation Learning	See all
CelebA 64x64	cFlow	Null-sampling for Interpretable and Fair Representations	See all
WebVision-1000	SCC (ResNet50-D)	Webly Supervised Image Classification with Self-Contained Confidence	See all
Food-101N	CleanNet	CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise	See all
Tiny ImageNet Classification	EfficientNet-B1+DCL	Direction Concentration Learning: Enhancing Congruency in Machine Learning	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
QMNIST	VGG-5(Spinal FC)	SpinalNet: Deep Neural Network with Gradual Input	See all
Fracture/Normal Shoulder Bone X-ray Images on MURA	Our Ensemble Learning-2	Classification of Fracture and Normal Shoulder Bone X-Ray Images Using Ensemble and Transfer Learning With Deep Learning Models Based on Convolutional Neural Networks	See all
MultiMNIST	CapsNet	Dynamic Routing Between Capsules	See all
Stanford Cars	ImageNet + iNat on WS-DAN	Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization	See all
Imbalanced CUB-200-2011	PC-Softmax	Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator	See all
iCassava'19	E2E-3M	Rethinking Recurrent Neural Networks and other Improvements for Image Classification	See all
Tiny-ImageNet	PreActResNet18	Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup	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	ELR+	Early-Learning Regularization Prevents Memorization of Noisy Labels	See all
LabelMe	CoNAL	Learning from Crowds by Modeling Common Confusions	See all
Food-101	Inception V3	Image and Text fusion for UPMC Food-101 \\using BERT and CNNs	See all

Subtasks

Few-Shot Image Classification

66 benchmarks

77 papers with code

Fine-Grained Image Classification

20 benchmarks

57 papers with code

Semi-Supervised Image Classification

31 benchmarks

54 papers with code

Small Data Image Classification

6 benchmarks

44 papers with code

Hyperspectral Image Classification

6 benchmarks

35 papers with code

See all 18 subtasks

Datasets

ImageNet

CIFAR-10

STL-10

CIFAR-100

SVHN

See all 91 datasets

Greatest papers with code

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

17 Apr 2017 • tensorflow/tensorflow •

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

Ranked #112 on Object Detection on COCO test-dev

IMAGE CLASSIFICATION OBJECT DETECTION

153,645

Paper
Code

Searching for MobileNetV3

ICCV 2019 • tensorflow/models •

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

Ranked #42 on Semantic Segmentation on Cityscapes test

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH OBJECT DETECTION SEMANTIC SEGMENTATION

68,881

Paper
Code

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

ECCV 2018 • tensorflow/models •

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

IMAGE CLASSIFICATION LESION SEGMENTATION SEMANTIC SEGMENTATION

68,881

Paper
Code

MobileNetV2: Inverted Residuals and Linear Bottlenecks

CVPR 2018 • tensorflow/models •

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 PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

68,881

Paper
Code

Progressive Neural Architecture Search

ECCV 2018 • tensorflow/models •

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 #48 on Image Classification on ImageNet

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH

68,881

Paper
Code

Xception: Deep Learning with Depthwise Separable Convolutions

CVPR 2017 • tensorflow/models •

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution).

Ranked #101 on Image Classification on ImageNet

IMAGE CLASSIFICATION

68,881

Paper
Code

Deep Residual Learning for Image Recognition

CVPR 2016 • tensorflow/models •

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

DOMAIN GENERALIZATION FINE-GRAINED IMAGE CLASSIFICATION IMAGE-TO-IMAGE TRANSLATION OBJECT DETECTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

68,881

Paper
Code

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

11 Feb 2015 • tensorflow/models •

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change.

Ranked #159 on Image Classification on ImageNet

IMAGE CLASSIFICATION

68,881

Paper
Code

Learning Transferable Architectures for Scalable Image Recognition

CVPR 2018 • tensorflow/models •

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 #13 on Image Classification on ImageNet ReaL

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH

68,880

Paper
Code