What is ImageNet?

• ImageNet is a project aimed at (manually) labeling and categorizing images into almost 22,000 separate object categories for computer vision research.

• When we hear about “ImageNet” in the context of deep learning and Convolutional Neural Networks, we are referring to ImageNet Large Scale Visual Recognition Challenge.

• The main aim of this image classification challenge is to train the model that can correctly classify an input image into the 1,000 separate objects category.

• Models are trained on the ~1.2 million training images with another 50,000 images for validation and 100,000 images for testing.

• These 1,000 image categories represent object classes that we encounter in our day-to-day lives, such as species of dogs, and cats, various household objects, vehicle types, and much more.

• When it comes to image classification, the ImageNet challenge is the “de facto “ benchmark for computer vision classification algorithms — and the leaderboard for this challenge has been dominated by Convolutional Neural Networks and Deep learning techniques since 2012.