mlsanityData to 7 Oct 2026

BCNN: Binary Complex Neural Network

arXiv 2104.10044 ↗First posted 28 Mar 2021cs.NE cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Binarized neural networks, or BNNs, show great promise in edge-side applications with resource limited hardware, but raise the concerns of reduced accuracy. Motivated by the complex neural networks, in this paper we introduce complex representation into the BNNs and propose Binary complex neural network -- a novel network design that processes binary complex inputs and weights through complex convolution, but still can harvest the extraordinary computation efficiency of BNNs. To ensure fast convergence rate, we propose novel BCNN based batch normalization function and weight initialization function. Experimental results on Cifar10 and ImageNet using state-of-the-art network models (e.g., ResNet, ResNetE and NIN) show that BCNN can achieve better accuracy compared to the original BNN models. BCNN improves BNN by strengthening its learning capability through complex representation and extending its applicability to complex-valued input data. The source code of BCNN will be released on GitHub.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 64 references that are in the map. First posted on arXiv 28 Mar 2021.

Builds on

32 of 64 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  5. 2013Network In Networkcited by 600
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  7. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  8. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  9. 2017Deep Complex Networkscited by 215
  10. 2020Binary Neural Networks: A Surveycited by 184
  11. 2017Towards Accurate Binary Convolutional Neural Networkcited by 148
  12. 2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 141
20 more
  1. 2017Over the Air Deep Learning Based Radio Signal Classificationcited by 121
  2. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
  3. 2016Full-Capacity Unitary Recurrent Neural Networkscited by 90
  4. 2017Verifying Properties of Binarized Deep Neural Networkscited by 77
  5. 2019Phase-aware Speech Enhancement with Deep Complex U-Netcited by 73
  6. 2019Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimizationcited by 58
  7. 2016Loss-aware Binarization of Deep Networkscited by 56
  8. 2018Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?cited by 38
  9. 2016Associative Long Short-Term Memorycited by 37
  10. 2018Efficient Super Resolution Using Binarized Neural Networkcited by 29
  11. 2013Neuronal Synchrony in Complex-Valued Deep Networkscited by 28
  12. 2017Attacking Binarized Neural Networkscited by 28
  13. 2017The High-Dimensional Geometry of Binary Neural Networkscited by 22
  14. 2017Enhanced Radar Imaging Using a Complex-valued Convolutional Neural Networkcited by 18
  15. 2020Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUscited by 12
  16. 2019Self-Binarizing Networkscited by 11
  17. 2019Structured Binary Neural Networks for Image Recognitioncited by 10
  18. 2021BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devicescited by 7
  19. 2019Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Networkcited by 6
  20. 2018Training Competitive Binary Neural Networks from Scratchcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1.

2 papers.

  1. 2021Binary Complex Neural Network Acceleration on FPGAcited by 14
  2. 2022How to train accurate BNNs for embedded systems?cited by 1