Binarized Neural Networks on the ImageNet Classification Task

Xundong Wu; Yong Wu; Yong Zhao

arxiv: 1604.03058 · v5 · pith:5WBNKO54new · submitted 2016-04-11 · 💻 cs.CV · cs.LG· cs.NE

Binarized Neural Networks on the ImageNet Classification Task

Xundong Wu , Yong Wu , Yong Zhao This is my paper

classification 💻 cs.CV cs.LGcs.NE

keywords networkbinarizedclassificationnetworksbetterimagenetneuralobtained

0 comments

read the original abstract

We trained Binarized Neural Networks (BNNs) on the high resolution ImageNet ILSVRC-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 % 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 network training.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

What does it mean to understand a neural network?
cs.LG 2019-07 unverdicted novelty 4.0

Simple training code produces complex neural networks, suggesting that brain learning rules may be easier to understand than mature brain properties and that neuroscience should shift focus accordingly.