A. Krizhevsky, I. Sutskever, Geoffrey E. Hinton
ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
Alex Krizhevsky, Ilya Sutskever, Geoffrey Hinton. 2012. (View Paper → )
We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 39.7\% and 18.9\% which is considerably better than the previous state-of-the-art results. The neural network, which has 60 million parameters and 500,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and two globally connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of convolutional nets. To reduce overfitting in the globally connected layers we employed a new regularization method that proved to be very effective.
This paper marked a breakthrough in image recognition: dramatically improving the accuracy of image classification, marking a turning point in computer vision. It demonstrated the power of deep learning and convolutional neural networks (CNNs) for complex tasks, sparking widespread adoption of these techniques. AlexNet's success led to rapid advancement in image recognition technologies, affecting industries from autonomous vehicles to medical imaging. It opened up new possibilities for products incorporating visual recognition capabilities.