mlsanityData to 14 Oct 2026

XNOR-Net++: Improved Binary Neural Networks

arXiv 1909.13863 ↗First posted 30 Sep 2019cs.CV cs.LG eess.IVcited by 97

Not on the map. Why?

Abstract (arXiv)

This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers. A key but fairly overlooked feature of the current state-of-the-art method of XNOR-Net is the use of analytically calculated real-valued scaling factors for re-weighting the output of binary convolutions. We argue that analytic calculation of these factors is sub-optimal. Instead, in this work, we make the following contributions: (a) we propose to fuse the activation and weight scaling factors into a single one that is learned discriminatively via backpropagation. (b) More importantly, we explore several ways of constructing the shape of the scale factors while keeping the computational budget fixed. (c) We empirically measure the accuracy of our approximations and show that they are significantly more accurate than the analytically calculated one. (d) We show that our approach significantly outperforms XNOR-Net within the same computational budget when tested on the challenging task of ImageNet classification, offering up to 6% accuracy gain.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 30; 2022: 24; 2023: 20; 2024: 13; 2025: 7; 2026: 3.

97 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  2. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
  3. 2021Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimationcited by 79
  4. 2022Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Spacecited by 66
  5. 2021Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Networkcited by 55
  6. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 52
  7. 2021PokeBNN: A Binary Pursuit of Lightweight Accuracycited by 49
  8. 2021A comprehensive review of Binary Neural Networkcited by 45
  9. 2021Learning Frequency Domain Approximation for Binary Neural Networkscited by 38
  10. 2021Quantization Backdoors to Deep Learning Commercial Frameworkscited by 29
  11. 2023QuantEase: Optimization-based Quantization for Language Modelscited by 29
  12. 2022BiViT: Extremely Compressed Binary Vision Transformercited by 28
38 more
  1. 2024VkD: Improving Knowledge Distillation using Orthogonal Projectionscited by 26
  2. 2021Distribution-sensitive Information Retention for Accurate Binary Neural Networkcited by 25
  3. 2021Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networkscited by 25
  4. 2021Bit-Mixer: Mixed-precision networks with runtime bit-width selectioncited by 22
  5. 2023BiBench: Benchmarking and Analyzing Network Binarizationcited by 22
  6. 2022EcoFormer: Energy-Saving Attention with Linear Complexitycited by 21
  7. 2023Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Trainingcited by 19
  8. 2021SiMaN: Sign-to-Magnitude Network Binarizationcited by 18
  9. 2021"BNN - BN = ?": Training Binary Neural Networks without Batch Normalizationcited by 17
  10. 2024Lightweight Pixel Difference Networks for Efficient Visual Representation Learningcited by 17
  11. 2021PhiNets: a scalable backbone for low-power AI at the edgecited by 16
  12. 2021Quantum Annealing Formulation for Binary Neural Networkscited by 15
  13. 2022Lipschitz Continuity Retained Binary Neural Networkcited by 14
  14. 2022Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticketcited by 14
  15. 2021Training Dynamical Binary Neural Networks with Equilibrium Propagationcited by 13
  16. 2021Dynamic Binary Neural Network by learning channel-wise thresholdscited by 13
  17. 2024HiDiff: Hybrid Diffusion Framework for Medical Image Segmentationcited by 13
  18. 2022Network Binarization via Contrastive Learningcited by 12
  19. 2021RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracycited by 11
  20. 2024BiDM: Pushing the Limit of Quantization for Diffusion Modelscited by 11
  21. 2021Equal Bits: Enforcing Equally Distributed Binary Network Weightscited by 9
  22. 2022INSTA-BNN: Binary Neural Network with INSTAnce-aware Thresholdcited by 9
  23. 2022Knowledge Distillation Meets Open-Set Semi-Supervised Learningcited by 9
  24. 2024BiPer: Binary Neural Networks using a Periodic Functioncited by 9
  25. 2021Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networkscited by 8
  26. 2025PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Modelscited by 8
  27. 2023BinaryViT: Towards Efficient and Accurate Binary Vision Transformerscited by 7
  28. 2023MT-SNN: Enhance Spiking Neural Network with Multiple Thresholdscited by 6
  29. 2023Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scalecited by 6
  30. 2021XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networkscited by 5
  31. 2022BiFSMN: Binary Neural Network for Keyword Spottingcited by 5
  32. 2024A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Networkcited by 5
  33. 2021Self-Distribution Binary Neural Networkscited by 4
  34. 2022Fast matrix multiplication for binary and ternary CNNs on ARM CPUcited by 4
  35. 2022BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performancecited by 4
  36. 2023SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalingscited by 4
  37. 2023BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUscited by 4
  38. 2021RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Thingscited by 3

50 most cited of 97 All 97 (JSON)