ImageNet

Introduced by Jia Deng et al. in ImageNet: A large-scale hierarchical image database

The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection. The publicly released dataset contains a set of manually annotated training images. A set of test images is also released, with the manual annotations withheld. ILSVRC annotations fall into one of two categories: (1) image-level annotation of a binary label for the presence or absence of an object class in the image, e.g., “there are cars in this image” but “there are no tigers,” and (2) object-level annotation of a tight bounding box and class label around an object instance in the image, e.g., “there is a screwdriver centered at position (20,25) with width of 50 pixels and height of 30 pixels”. The ImageNet project does not own the copyright of the images, therefore only thumbnails and URLs of images are provided.

Total number of non-empty WordNet synsets: 21841
Total number of images: 14197122
Number of images with bounding box annotations: 1,034,908
Number of synsets with SIFT features: 1000
Number of images with SIFT features: 1.2 million

Source: ImageNet Large Scale Visual Recognition Challenge

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Classification	ImageNet	OmniVec
Neural Architecture Search	ImageNet	DeepMAD-50M
Self-Supervised Image Classification	ImageNet	DINOv2
Semi-Supervised Image Classification	ImageNet - 10% labeled data	Meta Co-Training
Self-Supervised Image Classification	ImageNet (finetuned)	DINOv2
Semi-Supervised Image Classification	ImageNet - 1% labeled data	REACT
Knowledge Distillation	ImageNet	KD++
Image Classification	ImageNet V2	Model soups
Quantization	ImageNet	FQ-ViT
Zero-Shot Transfer Image Classification	ImageNet	M2-Encoder
Data Augmentation	ImageNet	DeiT-B
Network Pruning	ImageNet	ResNet50-2.3 GFLOPs
Zero-Shot Transfer Image Classification	ImageNet V2	BASIC
Classification with Binary Neural Network	ImageNet	AdaBin
Model Compression	ImageNet	ADLIK-MO-ResNet50+W4A4
Prompt Engineering	ImageNet	PromptKD
Image Clustering	ImageNet	MIM-Refiner
Sparse Learning	ImageNet	Resnet-50: 80% Sparse
Few-Shot Image Classification	ImageNet - 1-shot	ViT-MoE-15B
Few-Shot Image Classification	ImageNet - 5-shot	ViT-MoE-15B
Few-Shot Image Classification	ImageNet - 10-shot	MAWS
Unsupervised Image Classification	ImageNet	iBOT
Binarization	ImageNet	PokeBNN-1.0x
Feature Upsampling	ImageNet	FeatUp
Prompt Engineering	ImageNet V2	HPT
JPEG Decompression	ImageNet	Palette
Image Super-Resolution	ImageNet	DDNM
Weakly-Supervised Object Localization	ImageNet	Stable diffusion
Few-Shot Image Classification	ImageNet - 0-Shot	DebiasPL
Image Inpainting	ImageNet	WavePaint
Adversarial Robustness	ImageNet	ResNet-50
Image Colorization	ImageNet	DDRM
Weakly Supervised Object Detection	ImageNet	PCL-OB-G-Ens + FRCNN
Image Classification with Differential Privacy	ImageNet	NFResnet-50
Adversarial Defense	ImageNet	ResNet101
Image Deblurring	ImageNet	DDNM
Image Compressed Sensing	ImageNet	DDNM
Semi-Supervised Image Classification	ImageNet - 0.2% labeled data	FixMatch w/ EMAN
Medical Image Classification	ImageNet	DaViT-T
Zero-Shot Composed Image Retrieval (ZS-CIR)	ImageNet	Context-I2W