Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 187

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

Open access
Wang, Tianzhe, Wang, Kuan, Cai, Han, Lin, Ji, Liu, Zhijian, Wang, Hanrui, Lin, Yujun, Han, Song·2020·2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

We present APQ, a novel design methodology for efficient deep learning deployment. Unlike previous methods that separately optimize the neural network architecture, pruning policy, and quantization policy, we design to optimize them in a joint manner. To deal with the larger design space it brings, we devise to train a quantization-aware accuracy predictor that is fed to the evolutionary search to select the best fit. Since directly training such a predictor requires time-consuming quantization data collection, we propose to use predictor-transfer technique to get the quantization-aware predictor: we first generate a large dataset of 〈NN architecture, ImageNet accuracy〉 pairs by sampling a pretrained unified once-for-all network and doing direct evaluation; then we use these data to train an accuracy predictor without quantization, followed by transferring its weights to train the quantization-aware predictor, which largely reduces the quantization data collection time. Extensive experiments on ImageNet show the benefits of this joint design methodology: the model searched by our method maintains the same level accuracy as ResNet34 8-bit model while saving 8× BitOps; we achieve 2×/1.3× latency/energy saving compared to MobileNetV2+HAQ [30, 36] while obtaining the same level accuracy; the marginal search cost ofjoint optimization for a new deployment scenario outperforms separate optimizations using ProxylessNAS+AMC+HAQ [5, 12, 36] by 2.3% accuracy while reducing orders of magnitude GPU hours and CO2emission with respect to the training cost.

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/cvpr42600.2020.00215

Cites

9 of 9 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 9 references

Research works printed but not linked: 36

  1. yang, 2018, Ne-tadapt: Platform-aware neural network adaptation for mobile applications, Lecture Notes in Computer Science
  2. wu, 2018, Mixed precision quantization of convnets via differentiable neural architecture search
  3. 10.1109/ISCA.2018.00069 · DOI · Paper page
  4. 10.1109/CVPR.2019.01099 · DOI · Paper page
  5. wang, 0, Haq: Hardware-aware automated quantization, CVPR
  6. wang, 0, Learning to design circuits, NeurIPS 2018 Machine Learning for Systems Workshop
  7. wang, 0, Tts: Transferable transistor sizing with graph neural networks and reinforcement learning, ACM/IEEE 57th Design Automation Conference (DAC)
  8. han, 0, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, ICLRE
  9. zhang, 0, Sparch: Efficient architecture for sparse matrix multiplication, 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)
  10. han, 0, Learning both weights and connections for efficient neural network, NeurIPS
  11. he, 0, Amc: Automl for model compression and acceleration on mobile devices, ECCV
  12. howard, 2017, Mobilenets Efficient convolutional neural networks for mobile vision applications
  13. hu, 2016, Network trimming A data-driven neuron pruning approach towards efficient deep architectures
  14. lin, 0, Runtime Neural Pruning, NIPS
  15. liu, 0, Progressive neural architecture search, ECCV
  16. liu, 0, Hierarchical representations for efficient architecture search, ICLRE
  17. rastegari, 0, XNOR-Net - ImageNet Classification Using Binary Convolutional Neural Networks, ECCV
  18. cai, 0, Path-level network transformation for efficient architecture search, ICML
  19. 10.1109/ACCESS.2015.2494536 · DOI · Paper page
  20. courbariaux, 2016, Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or ?1, ArXiv
  21. 10.1609/aaai.v33i01.33014780 · DOI · Paper page
  22. cai, 0, ProxylessNAS: Direct neural architecture search on target task and hardware, ICLRE
  23. guo, 2019, Single path one-shot neural architecture search with uniform sampling
  24. cai, 0, Efficient architecture search by network transformation, AAAI
  25. han, 2019, Design automation for efficient deep learning computing
  26. anwar, 2016, Compact deep convolutional neural networks with coarse pruning
  27. liu, 0, Darts: Differentiable architecture search, ICLRE
  28. 10.1109/CVPR.2018.00907 · DOI · Paper page
  29. 10.1109/ICCV.2019.00339 · DOI · Paper page
  30. zhou, 2016, Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients, CoRR, 1606 6160
  31. mao, 0, Park: An open platform for learning-augmented computer systems, Advances in neural information processing systems, 2490
  32. 10.1109/CVPR.2018.00982 · DOI
  33. luo, 0, Neural architecture optimization, NeurIPS
  34. 10.1109/HPCA.2018.00067 · DOI · Paper page
  35. zhu, 0, Trained ternary quantization, ICLRE
  36. molchanov, 2016, Pruning convolutional neural networks for resource efficient inference

Cited by

See all 187

Metadata

Authors
Wang, T., Wang, K., Cai, H., Lin, J., Liu, Z., Wang, H., Lin, Y., & Han, S.
Venue
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2020-06
Pages
2075-2084
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3035332806
Cited by
187
References
9
FWCI
9.98
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

How to cite

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

This page
CoChat. (2026). Citation check: APQ: Joint Search for Network Architecture, Pruning and Quantization Policy. https://app.cochat.ai/papers/10.1109/cvpr42600.2020.00215
The paper
Wang, T., Wang, K., Cai, H., Lin, J., Liu, Z., Wang, H., Lin, Y., & Han, S. (2020). APQ: Joint Search for Network Architecture, Pruning and Quantization Policy. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00215

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.