XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

author: Mohammad Rastegari, Allen Institute for Artificial Intelligence (AI2)
published: Oct. 24, 2016,   recorded: October 2016,   views: 8883


Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58x faster convolutional operations and 32x memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a Binary-Weight-Network version of AlexNet is only 2.9% less than the full-precision AlexNet (in top-1 measure). We compare our method with recent network binarization methods, BinaryConnect and BinaryNets, and outperform these methods by large margins on ImageNet, more than 16% in top-1 accuracy.

See Also:

Download slides icon Download slides: eccv2016_rastegari_neural_networks_01.pdf (4.4┬áMB)

Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Yadu Krishnan S, April 22, 2020 at 11:54 a.m.:

I tried this XNOR Net Method with an numerical example,but i found out the results are having much deviation with Actual Convolution.Similiarly are we doing XNOR operation on Normalised input or Orginal input????

Comment2 irfandi, November 4, 2020 at 6:43 a.m.:

cara hack

Comment3 Rajib sk, December 19, 2020 at 5:49 p.m.:

Many problem

Comment4 Meaghan Herzog, March 25, 2021 at 8:26 a.m.:

This conference has cleared my reservations on the scope and their trend of Binary Convolutional Neural Networks. Hopefully, these neural networks would be utilized in a much better way for the development of the medical sector. The ideas which are shared here I am thinking to write them in my essay but first I will visit https://edubirdie.org/edubirdie-legit/ website to read reviews about eassy writting service which will assist me in that essays.

Comment5 Shishir, May 25, 2021 at 5:22 p.m.:

I want haker teacher

Comment6 Guest Gates, June 7, 2021 at 6:02 p.m.:

It allows patients to see a digital representation of their <a href="https://www.dentalclinic.london/invisalign-london"> new smile </a> before beginning orthodontic treatment with Invisalign.

Comment7 Invisalign Clinic, June 7, 2021 at 6:03 p.m.:

It allows patients to see a digital representation of their new smile [https://www.dentalclinic.london/invis...] before beginning orthodontic treatment with Invisalign

Write your own review or comment:

make sure you have javascript enabled or clear this field: