CoChat

Regularizing Activation Distribution for Training Binarized Deep Networks

Open access
Ding, Ruizhou, Chin, Ting-Wu, Liu, Zeye, Marculescu, Diana · 2019 · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 151

The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.

Abstract

Binarized Neural Networks (BNNs) can significantly reduce the inference latency and energy consumption in resource-constrained devices due to their pure-logical computation and fewer memory accesses. However, training BNNs is difficult since the activation flow encounters degeneration, saturation, and gradient mismatch problems. Prior work alleviates these issues by increasing activation bits and adding floating-point scaling factors, thereby sacrificing BNN's energy efficiency. In this paper, we propose to use distribution loss to explicitly regularize the activation flow, and develop a framework to systematically formulate the loss. Our experiments show that the distribution loss can consistently improve the accuracy of BNNs without losing their energy benefits. Moreover, equipped with the proposed regularization, BNN training is shown to be robust to the selection of hyper-parameters including optimizer and learning rate.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2019.01167

Cites

21 of 21 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 27

  1. 10.1007/s11263-015-0816-y · DOI · Paper page
  2. rastegari, 2016, Xnornet: Imagenet classification using binary convolutional neural networks, ECCV
  3. maas, 2013, Rectifier nonlinearities improve neural network acoustic models, Proc ICML, 30, 3
  4. 10.1109/CVPR.2017.345 · DOI · Paper page
  5. liu, 2018, Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm, Proceedings of the European Conference on Computer Vision (ECCV), 722
  6. polino, 2018, Model compression via distillation and quantization, International Conference on Learning Representations
  7. 10.1109/CVPR.2017.761 · DOI · Paper page
  8. mishra, 2018, Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy, International Conference on Learning Representations
  9. alizadeh, 2019, A systematic study of binary neural networks’ optimisation, International Conference on Learning Representations
  10. 10.1109/ICCV.2017.305 · DOI
  11. hubara, 2017, Binarynet Pytorch
  12. im, 2016, An empirical analysis of deep network loss surfaces
  13. kawaguchi, 2016, Deep learning without poor local minima, Advances in neural information processing systems, 586
  14. 10.1145/3020078.3021741 · DOI · Paper page
  15. 10.1145/3270689 · DOI
  16. 10.1145/3060403.3060465 · DOI
  17. salimans, 2016, Weight normalization: A simple reparameterization to accelerate training of deep neural networks, Advances in neural information processing systems, 901
  18. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249
  19. hou, 2017, Loss-aware binarization of deep networks, International Conference on Learning Representations
  20. 10.1109/ICDMW.2018.00131 · DOI
  21. 10.1109/TCSI.2017.2698019 · DOI
  22. yazdani, 2018, Linear backprop in non-linear networks
  23. sutskever, 2013, On the importance of initialization and momentum in deep learning, International Conference on Machine Learning, 1139
  24. 10.1109/CVPR.2017.539 · DOI
  25. tieleman, 2012, Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude, COURSERA Neural Networks for Machine Learning, 4, 26
  26. shang, 2017, Exploring normalization in deep residual networks with concatenated rectified linear units, AAAI, 1509
  27. 2008, CMOS065LPGP Standard Cell Library User Manual & Databook

Cited by

See all 151

Metadata

Authors
Ding, R., Chin, T.-W., Liu, Z., & Marculescu, D.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
11400-11409
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2982344224
Cited by
151
References
21
FWCI
7.34
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.