Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 191

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Ternary Weight Networks

Liu, Bin, Li, Fengfu, Wang, Xiaoxing, Zhang, Bo, Yan, Junchi·2023·ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Abstract

We present a memory and computation efficient ternary weight networks (TWNs) - with weights constrained to +1, 0 and -1. The Euclidian distance between full (float or double) precision weights and the ternary weights along with a scaling factor is minimized in training stage. Besides, a threshold-based ternary function is optimized to get an approximated solution which can be fast and easily computed. TWNs have shown better expressive abilities than binary precision counterparts. Meanwhile, TWNs achieve up to 16× model compression rate and need fewer multiplications compared with the float32 precision counterparts. Extensive experiments on MNIST, CIFAR-10, and ImageNet datasets show that the TWNs achieve much better result than the Binary-Weight-Networks (BWNs) and the classification performance on MNIST and CIFAR-10 is very close to the full precision networks. We also verify our method on object detection task and show that TWNs significantly outperforms BWN by more than 10% mAP on PASCAL VOC dataset. The pytorch version of source code is available at: https://github.com/Thinklab-SJTU/twns.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/icassp49357.2023.10094626

Cites

5 of 5 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Show all 5 references

Research works printed but not linked: 21

  1. 10.5555/2999134.2999257 · doi:10.5555/2999134.2999257
  2. Simonyan, 2014, Very deep convolutional networks for large-scale image recognition
  3. Liu, Going deeper with convolutions, 1
  4. 10.1007/978-3-319-46448-0_2 · DOI · Paper page
  5. 10.1007/978-3-319-46493-0_32 · DOI · Paper page
  6. 10.1073/pnas.1604850113 · DOI · Paper page
  7. Han, 2015, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding
  8. Courbariaux, 2015, Binaryconnect: Training deep neural networks with binary weights during propagations, NeurIPS, 3123
  9. Hubara, 2016, Binarized neural networks, Advances in neural information processing systems
  10. Lin, 2015, Neural networks with few multiplications
  11. Iandola, 2016, Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size
  12. 10.48550/ARXIV.1704.04861 · DOI · Paper page
  13. 10.1109/CVPR.2018.00716 · DOI · Paper page
  14. Liu, DARTS: differentiable architecture search
  15. 10.24963/ijcai.2020/424 · DOI
  16. 10.1007/978-3-031-20044-1_38 · DOI
  17. 10.1109/SiPS.2014.6986082 · DOI · Paper page
  18. Ioffe, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 448
  19. Lee, Deeply-supervised nets, 562
  20. Jocher, 2020, Yolov5 documentation
  21. 10.1007/978-3-319-10602-1_48 · DOI · Paper page

Cited by

See all 191

Metadata

Authors
Liu, B., Li, F., Wang, X., Zhang, B., & Yan, J.
Venue
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2023-06-04
Pages
1-5
ISSN
1520-6149 (ISSN-L)
OpenAlex
W4375869345
Cited by
191
References
5
FWCI
10.92
Type
conference paper
Language
en
Open access
closed
Funders
National Natural Science Foundation of China

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Ternary Weight Networks. https://app.cochat.ai/papers/10.1109/icassp49357.2023.10094626
The paper
Liu, B., Li, F., Wang, X., Zhang, B., & Yan, J. (2023). Ternary Weight Networks. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10094626

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.