ImageNet Large Scale Visual Recognition Challenge
Jia Deng, Andrej Karpathy, Sean Ma, Olga Russakovsky, Zhiheng Huang, Michael A. Bernstein, Jonathan Krause, Hao Su, Li Fei-Fei, Sanjeev Satheesh, Aditya Khosla, Alexander Berg
Abstract
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classifi cation and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenge of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classifi cation and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the fi ve years of the challenge, and propose future directions and improvements.