Binarized Neural Networks on the ImageNet Classification Task

We trained Binarized Neural Networks (BNNs) on the high resolution ImageNet LSVRC-2102 dataset classification task and achieved a good performance. With a moderate size network of 13 layers, we obtained top-5 classification accuracy rate of 84.1 percent on validation set through network distillation, much better than previous published results of 73.2\% on XNOR network and 69.1\% on binarized GoogleNET. We expect networks of better performance can be obtained by following our current strategies. We provide a detailed discussion and preliminary analysis on strategies used in the training.