mlsanityData to 7 Oct 2026

Binary Neural Networks: A Survey

arXiv 2004.03333 ↗First posted 31 Mar 2020cs.NE cs.CV cs.LGcited by 184

Not on the map. Why?

Abstract (arXiv)

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected.

Key facts. Cited by 184 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 33; 2023: 38; 2024: 25; 2025: 32; 2026: 9.

184 papers.

Sort:

By area:

  1. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  2. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  3. 20218-bit Optimizers via Block-wise Quantizationcited by 395
  4. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  5. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  6. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  7. 2022I-ViT: Integer-only Quantization for Efficient Vision Transformer Inferencecited by 93
  8. 2023PB-LLM: Partially Binarized Large Language Modelscited by 80
  9. 2023Stable and low-precision training for large-scale vision-language modelscited by 74
  10. 2022Deep Differentiable Logic Gate Networkscited by 67
  11. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 64
  12. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
38 more
  1. 2023SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficientcited by 58
  2. 2021Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Networkcited by 55
  3. 2021A comprehensive review of Binary Neural Networkcited by 44
  4. 2023Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancycited by 44
  5. 2021Scalable Rule-Based Representation Learning for Interpretable Classificationcited by 40
  6. 2024Convolutional Differentiable Logic Gate Networkscited by 37
  7. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  8. 2021QuPeD: Quantized Personalization via Distillation with Applications to Federated Learningcited by 32
  9. 2023Spherical Space Feature Decomposition for Guided Depth Map Super-Resolutioncited by 28
  10. 2022DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Imagecited by 26
  11. 2021Quantization Backdoors to Deep Learning Commercial Frameworkscited by 25
  12. 2021Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networkscited by 24
  13. 2023Binarized Spectral Compressive Imagingcited by 23
  14. 2023A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platformscited by 21
  15. 2022On Quantizing Implicit Neural Representationscited by 20
  16. 2021SiMaN: Sign-to-Magnitude Network Binarizationcited by 18
  17. 2021"BNN - BN = ?": Training Binary Neural Networks without Batch Normalizationcited by 17
  18. 2024Binarized Low-light Raw Video Enhancementcited by 17
  19. 2022Lipschitz Continuity Retained Binary Neural Networkcited by 14
  20. 2023Learning Interpretable Rules for Scalable Data Representation and Classificationcited by 14
  21. 2024Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Modelscited by 14
  22. 2021Quantum Annealing Formulation for Binary Neural Networkscited by 13
  23. 2021Dynamic Binary Neural Network by learning channel-wise thresholdscited by 13
  24. 2021Edge-Native Intelligence for 6G Communications Driven by Federated Learning: A Survey of Trends and Challengescited by 12
  25. 2022Network Binarization via Contrastive Learningcited by 12
  26. 2025Neural Network Verification is a Programming Language Challengecited by 12
  27. 2025Quantized Spike-driven Transformercited by 12
  28. 2021Enabling Binary Neural Network Training on the Edgecited by 11
  29. 2021Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantizationcited by 11
  30. 2021Demystifying and Generalizing BinaryConnectcited by 11
  31. 2021AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networkscited by 11
  32. 2022Binarizing Split Learning for Data Privacy Enhancement and Computation Reductioncited by 11
  33. 2024BinaryDM: Accurate Weight Binarization for Efficient Diffusion Modelscited by 11
  34. 2025LittleBit: Ultra Low-Bit Quantization via Latent Factorizationcited by 11
  35. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  36. 2023DRAW: Defending Camera-shooted RAW against Image Manipulationcited by 10
  37. 2023EQ-Net: Elastic Quantization Neural Networkscited by 10
  38. 2024Q-SNNs: Quantized Spiking Neural Networkscited by 10

50 most cited of 184 All 184 (JSON)