XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

  • Mohammad RastegariEmail author
  • Vicente Ordonez
  • Joseph Redmon
  • Ali Farhadi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9908)


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 32\(\times \) 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 58\(\times \) faster convolutional operations (in terms of number of the high precision operations) and 32\(\times \) 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 the same as the full-precision AlexNet. 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. Our code is available at:


Convolutional Neural Network Deep Neural Network Weight Filter Convolutional Layer Binary Input 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work is in part supported by ONR N00014-13-1-0720, NSF IIS- 1338054, Allen Distinguished Investigator Award, and the Allen Institute for Artificial Intelligence.


  1. 1.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105 (2012)Google Scholar
  2. 2.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  3. 3.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR (2015)Google Scholar
  5. 5.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)Google Scholar
  6. 6.
    Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar
  7. 7.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  8. 8.
    Oculus, V.: Oculus rift-virtual reality headset for 3d gaming (2012).
  9. 9.
    Gottmer, M.: Merging reality and virtuality with microsoft hololens (2015)Google Scholar
  10. 10.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  11. 11.
    Courbariaux, M., Bengio, Y.: Binarynet: training deep neural networks with weights and activations constrained to \(+\)1 or \(-\)1. CoRR (2016)Google Scholar
  12. 12.
    Denil, M., Shakibi, B., Dinh, L., de Freitas, N., et al.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems, pp. 2148–2156 (2013)Google Scholar
  13. 13.
    Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Sig. Syst. 2(4), 303–314 (1989)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Interspeech, pp. 437–440 (2011)Google Scholar
  15. 15.
    Dauphin, Y.N., Bengio, Y.: Big neural networks waste capacity. arXiv preprint arXiv:1301.3583 (2013)
  16. 16.
    Ba, J., Caruana, R.: Do deep nets really need to be deep?. In: Advances in Neural Information Processing Systems, pp. 2654–2662 (2014)Google Scholar
  17. 17.
    Hanson, S.J., Pratt, L.Y.: Comparing biases for minimal network construction with back-propagation. In: Advances in Neural Information Processing Systems, pp. 177–185 (1989)Google Scholar
  18. 18.
    LeCun, Y., Denker, J.S., Solla, S.A., Howard, R.E., Jackel, L.D.: Optimal brain damage. In: NIPs, vol. 89 (1989)Google Scholar
  19. 19.
    Hassibi, B., Stork, D.G.: Second Order Derivatives for Network Pruning: Optimal Brain Surgeon. Morgan Kaufmann, San Francisco (1993)Google Scholar
  20. 20.
    Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, pp. 1135–1143 (2015)Google Scholar
  21. 21.
    Van Nguyen, H., Zhou, K., Vemulapalli, R.: Cross-domain synthesis of medical images using efficient location-sensitive deep network. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 677–684. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24553-9_83 CrossRefGoogle Scholar
  22. 22.
    Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)
  23. 23.
    Chen, W., Wilson, J.T., Tyree, S., Weinberger, K.Q., Chen, Y.: Compressing neural networks with the hashing trick. arXiv preprint arXiv:1504.04788 (2015)
  24. 24.
    Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269–1277 (2014)Google Scholar
  25. 25.
    Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. arXiv preprint arXiv:1405.3866 (2014)
  26. 26.
    Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
  27. 27.
    Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR (2016)Google Scholar
  28. 28.
    Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: Squeezenet: alexnet-level accuracy with 50x fewer parameters and \(<\)1mb model size. arXiv preprint arXiv:1602.07360 (2016)
  29. 29.
    Gong, Y., Liu, L., Yang, M., Bourdev, L.: Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)
  30. 30.
    Arora, S., Bhaskara, A., Ge, R., Ma, T.: Provable bounds for learning some deep representations. arXiv preprint arXiv:1310.6343 (2013)
  31. 31.
    Vanhoucke, V., Senior, A., Mao, M.Z.: Improving the speed of neural networks on cpus. In: Proceedings of Deep Learning and Unsupervised Feature Learning NIPS Workshop, vol. 1 (2011)Google Scholar
  32. 32.
    Hwang, K., Sung, W.: Fixed-point feedforward deep neural network design using weights \(+\)1, 0, and \(-\)1. In: 2014 IEEE Workshop on Signal Processing Systems (SiPS), pp. 1–6. IEEE (2014)Google Scholar
  33. 33.
    Anwar, S., Hwang, K., Sung, W.: Fixed point optimization of deep convolutional neural networks for object recognition. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1131–1135. IEEE (2015)Google Scholar
  34. 34.
    Lin, Z., Courbariaux, M., Memisevic, R., Bengio, Y.: Neural networks with few multiplications. arXiv preprint arXiv:1510.03009 (2015)
  35. 35.
    Courbariaux, M., Bengio, Y., David, J.P.: Training deep neural networks with low precision multiplications. arXiv preprint arXiv:1412.7024 (2014)
  36. 36.
    Soudry, D., Hubara, I., Meir, R.: Expectation backpropagation: parameter-free training of multilayer neural networks with continuous or discrete weights. In: Advances in Neural Information Processing Systems, pp. 963–971 (2014)Google Scholar
  37. 37.
    Esser, S.K., Appuswamy, R., Merolla, P., Arthur, J.V., Modha, D.S.: Backpropagation for energy-efficient neuromorphic computing. In: Advances in Neural Information Processing Systems, pp. 1117–1125 (2015)Google Scholar
  38. 38.
    Courbariaux, M., Bengio, Y., David, J.P.: Binaryconnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems, pp. 3105–3113 (2015)Google Scholar
  39. 39.
    Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 1058–1066 (2013)Google Scholar
  40. 40.
    Baldassi, C., Ingrosso, A., Lucibello, C., Saglietti, L., Zecchina, R.: Subdominant dense clusters allow for simple learning and high computational performance in neural networks with discrete synapses. Phys. Rev. Lett. 115(12), 128101 (2015)CrossRefGoogle Scholar
  41. 41.
    Kim, M., Smaragdis, P.: Bitwise neural networks. arXiv preprint arXiv:1601.06071 (2016)
  42. 42.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  43. 43.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  44. 44.
    Redmon, J.: Darknet: open source neural networks in c (2013–2016).

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Mohammad Rastegari
    • 1
    Email author
  • Vicente Ordonez
    • 1
  • Joseph Redmon
    • 2
  • Ali Farhadi
    • 1
    • 2
  1. 1.Allen Institute for AISeattleUSA
  2. 2.University of WashingtonSeattleUSA

Personalised recommendations