mlsanityData to 7 Oct 2026

Local Binary Convolutional Neural Networks

arXiv 1608.06049 ↗First posted 22 Aug 2016cs.LG cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN). The design principles of LBC are motivated by local binary patterns (LBP). The LBC layer comprises of a set of fixed sparse pre-defined binary convolutional filters that are not updated during the training process, a non-linear activation function and a set of learnable linear weights. The linear weights combine the activated filter responses to approximate the corresponding activated filter responses of a standard convolutional layer. The LBC layer affords significant parameter savings, 9x to 169x in the number of learnable parameters compared to a standard convolutional layer. Furthermore, the sparse and binary nature of the weights also results in up to 9x to 169x savings in model size compared to a standard convolutional layer. We demonstrate both theoretically and experimentally that our local binary convolution layer is a good approximation of a standard convolutional layer. Empirically, CNNs with LBC layers, called local binary convolutional neural networks (LBCNN), achieves performance parity with regular CNNs on a range of visual datasets (MNIST, SVHN, CIFAR-10, and ImageNet) while enjoying significant computational savings.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 11; 2024: 8; 2025: 4; 2026: 1.

38 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  3. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 90
  4. 2021Dual-Cross Central Difference Network for Face Anti-Spoofingcited by 47
  5. 2023Semantic Diffusion Network for Semantic Segmentationcited by 30
  6. 2024ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterizationcited by 27
  7. 2023BiBench: Benchmarking and Analyzing Network Binarizationcited by 22
  8. 2022Extreme Compression for Pre-trained Transformers Made Simple and Efficientcited by 19
  9. 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitivescited by 18
  10. 2024Lightweight Pixel Difference Networks for Efficient Visual Representation Learningcited by 17
  11. 2023ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformercited by 15
  12. 2022Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networkscited by 13
26 more
  1. 2023Resilient Binary Neural Networkcited by 13
  2. 2023Bi-ViT: Pushing the Limit of Vision Transformer Quantizationcited by 13
  3. 2022ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networkscited by 8
  4. 2024A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsamplingcited by 7
  5. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 6
  6. 2022Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognitioncited by 4
  7. 2021Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluationcited by 3
  8. 2021BNAS v2: Learning Architectures for Binary Networks with Empirical Improvementscited by 3
  9. 2022Median Pixel Difference Convolutional Network for Robust Face Recognitioncited by 3
  10. 2024Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysiscited by 3
  11. 2021Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directionscited by 2
  12. 2022Spatiotemporal Multi-scale Bilateral Motion Network for Gait Recognitioncited by 2
  13. 2023Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learningcited by 2
  14. 2024Histogram Layers for Neural Engineered Featurescited by 2
  15. 2024PDCFNet: Enhancing Underwater Images through Pixel Difference Convolutioncited by 2
  16. 2021Trilateral Attention Network for Real-time Medical Image Segmentationcited by 1
  17. 2023From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learningcited by 1
  18. 2023Deep Neural Networks Fused with Textures for Image Classificationcited by 1
  19. 2025Uncertainty-Aware Decomposed Hybrid Networkscited by 1
  20. 2025Enhancing Learnable Descriptive Convolutional Vision Transformer for Face Anti-Spoofingcited by 1
  21. 2021LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupycited by 0
  22. 2023DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNscited by 0
  23. 2024Toward Efficient Convolutional Neural Networks With Structured Ternary Patternscited by 0
  24. 2024A Novel Feature Extraction Model for the Detection of Plant Disease from Leaf Images in Low Computational Devicescited by 0
  25. 2025STGBD-Net: Spatio-temporal Gradient Basis Decomposition Network for Infrared Small Target Detectioncited by 0
  26. 2026Explicit Over Implicit: Enhancing CNNs Via Complex Structure Tensor Representations for Periocular Recognitioncited by 0