ImageNet Classification with Deep Convolutional Neural Networks

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.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Graph Classification BP-fMRI-97 CNN Accuracy 54.6% # 6
F1 52.8% # 7
Image Classification CIFAR-10 DCNN Percentage correct 89 # 177
Graph Classification HIV-DTI-77 CNN Accuracy 54.3% # 6
F1 55.7% # 4
Graph Classification HIV-fMRI-77 CNN Accuracy 59.3% # 4
F1 66.3% # 4
Image Classification ImageNet AlexNet Top 1 Accuracy 63.3% # 718
Top 5 Accuracy 84.6% # 259
Number of params 60M # 551
Hardware Burden 2G # 1
Operations per network pass 0.07G # 1
Image Classification ImageNet ReaL AlexNet Accuracy 62.88% # 51

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Uses Extra
Training Data
Source Paper Compare
Unsupervised Domain Adaptation Office-Home AlexNet [cite:NIPS12CNN] Accuracy 54.9 # 6