Golden Recursion Inc. logoGolden Recursion Inc. logo
Advanced Search


A large visual database designed for use in visual object recognition software research.

ImageNet is an image database developed for visual object recognition built with WordNet, a lexical database for the English language. It has more than 15 million high resolution images organized into 1000 classes.

The database was presented for the first time as a poster at the 2009 Conference on Computer Vision and Pattern Recognition (CVPR) in Florida by researchers from the Computer Science department at Princeton University.

It uses convolutional neural networks (CNNs) in image recognition and classification. Each meaningful concept in WordNet, possibly described by multiple words or word phrases, is called a "synonym set" or "synset". ImageNet tries to sort and provide images that correspond each synset.

ImageNet is a resource to researchers in the academic world, as well as educators around the world.

ImageNet Challenge

Since 2010, the annual ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is a competition where research teams evaluate their algorithms on the given data set, and compete to achieve higher accuracy on several visual recognition tasks. It uses a "trimmed" list of only 1000 image categories or "classes", including 90 of the 120 dog breeds classified by the full ImageNet schema.

The 2010s saw dramatic progress in image processing. Around 2011, a good ILSVRC classification error rate was 25%. In 2012, a deep convolutional neural network achieved 16%. In the next couple of years, error rates fell to a few percent. By 2015, researchers reported that software exceeded human ability at the narrow ILSVRC tasks.

In 2017, 29 of 38 competing teams got less than 5% wrong. In 2017 ImageNet stated it would roll out a new, much more difficult, challenge in 2018 that involves classifying 3D objects using natural language. Because creating 3D data is more costly than annotating a pre-existing 2D image, the dataset is expected to be smaller. The applications of progress in this area would range from robotic navigation to augmented reality.



Further Resources


About ImageNet

ImageNet Team

ConvNets and ImageNet Beyond Accuracy: Explanations, Bias Detection, Adversarial Examples and Model Criticism

Pierre Stock, Moustapha Cisse

Academic paper

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Academic paper

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky, Ilya Sutskever and Geoffrey Hinton

Academic paper

ImageNet: A Large-Scale Hierarchical Image Database

Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li and Li Fei-Fei


Zoë Corbyn
June 6, 2021
the Guardian
The AI researcher on how natural resources and human labour drive machine learning and the regressive stereotypes that are baked into its algorithms
Karen Hao
April 1, 2021
MIT Technology Review
Our understanding of progress in machine learning has been colored by flawed testing data.
Will Knight
March 31, 2021
The labels attached to images used to train machine-vision systems are often wrong. That could mean bad decisions by self-driving cars and medical algorithms.
Will Knight
March 15, 2021
Managers of the ImageNet data set paved the way for advances in deep learning. Now they've taken a big step to protect people's privacy.
Will Heaven
February 4, 2021
MIT Technology Review
Large datasets like ImageNet have supercharged the last 10 years of AI vision, but they are hard to produce and contain bias. Computer generated datasets provide an alternative.


Golden logo
By using this site, you agree to our Terms & Conditions.