mlsanityData to 7 Oct 2026

A comprehensive review of Binary Neural Network

arXiv 2110.06804 ↗First posted 11 Oct 2021cs.NE cs.AI cs.CVcited by 44

Not on the map. Why?

Abstract (arXiv)

Deep learning (DL) has recently changed the development of intelligent systems and is widely adopted in many real-life applications. Despite their various benefits and potentials, there is a high demand for DL processing in different computationally limited and energy-constrained devices. It is natural to study game-changing technologies such as Binary Neural Networks (BNN) to increase deep learning capabilities. Recently remarkable progress has been made in BNN since they can be implemented and embedded on tiny restricted devices and save a significant amount of storage, computation cost, and energy consumption. However, nearly all BNN acts trade with extra memory, computation cost, and higher performance. This article provides a complete overview of recent developments in BNN. This article focuses exclusively on 1-bit activations and weights 1-bit convolution networks, contrary to previous surveys in which low-bit works are mixed in. It conducted a complete investigation of BNN's development -from their predecessors to the latest BNN algorithms/techniques, presenting a broad design pipeline and discussing each module's variants. Along the way, it examines BNN (a) purpose: their early successes and challenges; (b) BNN optimization: selected representative works that contain essential optimization techniques; (c) deployment: open-source frameworks for BNN modeling and development; (d) terminal: efficient computing architectures and devices for BNN and (e) applications: diverse applications with BNN. Moreover, this paper discusses potential directions and future research opportunities in each section.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 110 of its 190 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

110 of 190 references.

References · 110

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  12. 2017Squeeze-and-Excitation Networkscited by 4,763
38 more
  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2016Wide Residual Networkscited by 3,057
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  9. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  10. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  13. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  14. 2019Object Detection in 20 Years: A Surveycited by 528
  15. 2019Selective Kernel Networkscited by 401
  16. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  17. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  18. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  19. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  20. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  21. 2015MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systemscited by 195
  22. 2020Binary Neural Networks: A Surveycited by 184
  23. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 183
  24. 2020BinaryBERT: Pushing the Limit of BERT Quantizationcited by 175
  25. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  26. 2019Quantization Networkscited by 151
  27. 2017Towards Accurate Binary Convolutional Neural Networkcited by 148
  28. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  29. 2019A Survey of Deep Learning-based Object Detectioncited by 106
  30. 2014Salient Object Detection: A Surveycited by 98
  31. 2019XNOR-Net++: Improved Binary Neural Networkscited by 94
  32. 2015Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networkscited by 80
  33. 2018Vision Meets Drones: A Challengecited by 80
  34. 2020Rotated Binary Neural Networkcited by 77
  35. 2020RGB-D Salient Object Detection: A Surveycited by 73
  36. 2019Regularizing Activation Distribution for Training Binarized Deep Networkscited by 61
  37. 2019Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimizationcited by 58
  38. 2016Loss-aware Binarization of Deep Networkscited by 56

50 most cited of 110 All 110 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 11; 2024: 11; 2025: 9; 2026: 7.

44 papers.

Sort:

By area:

  1. 2023PB-LLM: Partially Binarized Large Language Modelscited by 80
  2. 2021PokeBNN: A Binary Pursuit of Lightweight Accuracycited by 48
  3. 2023AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Riskscited by 34
  4. 2023BiBench: Benchmarking and Analyzing Network Binarizationcited by 22
  5. 2022A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devicescited by 11
  6. 20220/1 Deep Neural Networks via Block Coordinate Descentcited by 10
  7. 2024BiPer: Binary Neural Networks using a Periodic Functioncited by 9
  8. 2023EFaR 2023: Efficient Face Recognition Competitioncited by 7
  9. 2024Custom Gradient Estimators are Straight-Through Estimators in Disguisecited by 6
  10. 2025LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deploymentcited by 6
  11. 2024MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion Segmentationcited by 5
  12. 2023A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniquescited by 4
32 more
  1. 2023Taming Binarized Neural Networks and Mixed-Integer Programscited by 4
  2. 2023Efficient Computation of Shap Explanation Scores for Neural Network Classifiers via Knowledge Compilationcited by 3
  3. 2023Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradientscited by 3
  4. 2022RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeatingcited by 2
  5. 2023Straight-Through meets Sparse Recovery: the Support Exploration Algorithmcited by 2
  6. 2023UCM-Net: A Lightweight and Efficient Solution for Skin Lesion Segmentation using MLP and CNNcited by 2
  7. 2024HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inferencecited by 2
  8. 2022S3NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networkscited by 1
  9. 2022How to train accurate BNNs for embedded systems?cited by 1
  10. 2023Training Neural Networks with Universal Adiabatic Quantum Computingcited by 1
  11. 2024Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAscited by 1
  12. 2024Quantized Approximately Orthogonal Recurrent Neural Networkscited by 1
  13. 2024Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimizationcited by 1
  14. 2024Training Multi-Layer Binary Neural Networks With Local Binary Error Signalscited by 1
  15. 2025Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Datasetcited by 1
  16. 2025Training Deep Morphological Neural Networks as Universal Approximatorscited by 1
  17. 2025HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computingcited by 1
  18. 2024A foundation for exact binarized morphological neural networkscited by 0
  19. 2024An experimental comparative study of backpropagation and alternatives for training binary neural networks for image classificationcited by 0
  20. 2024Improving Detection of Person Class Using Dense Poolingcited by 0
  21. 2025Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networkscited by 0
  22. 2025Generative Binary Memory: Pseudo-Replay Class-Incremental Learning on Binarized Embeddingscited by 0
  23. 2025Variational Inference for Quantum HyperNetworkscited by 0
  24. 2025Red grape detection with accelerated artificial neural networks in the FPGA's programmable logiccited by 0
  25. 2025Weight Mapping Properties of a Dual Tree Single Clock Adiabatic Capacitive Neuroncited by 0
  26. 2026EdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learningcited by 0
  27. 2026PiC-BNN: A 128-kbit 65 nm Processing-in-CAM-Based End-to-End Binary Neural Network Acceleratorcited by 0
  28. 2026Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptationcited by 0
  29. 2026A Sugeno Integral View of Binarized Neural Network Inferencecited by 0
  30. 2026From Detection to Response: A Deep Learning and Retrieval-Augmented Generation Framework for Network Intrusion Mitigationcited by 0
  31. 2026Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementationscited by 0
  32. 2026Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networkscited by 0