# Local Binary Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1608.06049 · HTML: https://mlsanity.com/paper/1608.06049/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2016.

## Built on by (most cited first, 30 of 38)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Dual-Cross Central Difference Network for Face Anti-Spoofing](https://mlsanity.com/paper/2105.01290/) (2021)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)
- [ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization](https://mlsanity.com/paper/2406.05981/) (2024)
- [BiBench: Benchmarking and Analyzing Network Binarization](https://mlsanity.com/paper/2301.11233/) (2023)
- [Extreme Compression for Pre-trained Transformers Made Simple and Efficient](https://mlsanity.com/paper/2206.01859/) (2022)
- [Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives](https://mlsanity.com/paper/2308.02066/) (2023)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer](https://mlsanity.com/paper/2306.06446/) (2023)
- [Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2201.02711/) (2022)
- [Resilient Binary Neural Network](https://mlsanity.com/paper/2302.00956/) (2023)
- [Bi-ViT: Pushing the Limit of Vision Transformer Quantization](https://mlsanity.com/paper/2305.12354/) (2023)
- [ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks](https://mlsanity.com/paper/2205.08119/) (2022)
- [A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling](https://mlsanity.com/paper/2407.02283/) (2024)
- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognition](https://mlsanity.com/paper/2202.06673/) (2022)
- [Histogram Layers for Neural Engineered Features](https://mlsanity.com/paper/2403.17176/) (2024)
- [Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation](https://mlsanity.com/paper/2110.05242/) (2021)
- [BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements](https://mlsanity.com/paper/2110.08562/) (2021)
- [Median Pixel Difference Convolutional Network for Robust Face Recognition](https://mlsanity.com/paper/2205.15867/) (2022)
- [Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis](https://mlsanity.com/paper/2409.19582/) (2024)
- [Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions](https://mlsanity.com/paper/2108.13055/) (2021)
- [Spatiotemporal Multi-scale Bilateral Motion Network for Gait Recognition](https://mlsanity.com/paper/2209.12364/) (2022)
- [Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning](https://mlsanity.com/paper/2401.08603/) (2023)
- [PDCFNet: Enhancing Underwater Images through Pixel Difference Convolution](https://mlsanity.com/paper/2409.19269/) (2024)
- [Trilateral Attention Network for Real-time Medical Image Segmentation](https://mlsanity.com/paper/2106.09201/) (2021)
- [From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2303.08414/) (2023)
- [Deep Neural Networks Fused with Textures for Image Classification](https://mlsanity.com/paper/2308.01813/) (2023)

## 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.