# Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks

arXiv: https://arxiv.org/abs/2011.09398 · HTML: https://mlsanity.com/paper/2011.09398/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 20 of 20)

- [PokeBNN: A Binary Pursuit of Lightweight Accuracy](https://mlsanity.com/paper/2112.00133/) (2021)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2104.07085/) (2021)
- [Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2201.02711/) (2022)
- [MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation](https://mlsanity.com/paper/2507.04290/) (2025)
- [Highly-Efficient Binary Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2202.12375/) (2022)
- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [Reaching the Edge of the Edge: Image Analysis in Space](https://mlsanity.com/paper/2301.04954/) (2023)
- [Enabling On-device Continual Learning with Binary Neural Networks](https://mlsanity.com/paper/2401.09916/) (2024)
- [Input Layer Binarization with Bit-Plane Encoding](https://mlsanity.com/paper/2305.02885/) (2023)
- [On-Device Learning with Binary Neural Networks](https://mlsanity.com/paper/2308.15308/) (2023)
- [Optimizing data-flow in Binary Neural Networks](https://mlsanity.com/paper/2304.00952/) (2023)
- [Gradient-Based Interpretability Methods and Binarized Neural Networks](https://mlsanity.com/paper/2106.12569/) (2021)
- [FedTrans: Efficient Federated Learning via Multi-Model Transformation](https://mlsanity.com/paper/2404.13515/) (2024)
- [LAB: Learnable Activation Binarizer for Binary Neural Networks](https://mlsanity.com/paper/2210.13858/) (2022)
- [Evaluation Metrics for DNNs Compression](https://mlsanity.com/paper/2305.10616/) (2023)
- [Efficient and Low-Footprint Object Classification using Spatial Contrast](https://mlsanity.com/paper/2311.03422/) (2023)
- [Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks](https://mlsanity.com/paper/2503.07107/) (2025)
- [Generative Binary Memory: Pseudo-Replay Class-Incremental Learning on Binarized Embeddings](https://mlsanity.com/paper/2503.10333/) (2025)

## Abstract (arXiv)

We introduce Larq Compute Engine, the world's fastest Binarized Neural Network (BNN) inference engine, and use this framework to investigate several important questions about the efficiency of BNNs and to design a new state-of-the-art BNN architecture. LCE provides highly optimized implementations of binary operations and accelerates binary convolutions by 8.5 - 18.5x compared to their full-precision counterparts on Pixel 1 phones. LCE's integration with Larq and a sophisticated MLIR-based converter allow users to move smoothly from training to deployment. By extending TensorFlow and TensorFlow Lite, LCE supports models which combine binary and full-precision layers, and can be easily integrated into existing applications. Using LCE, we analyze the performance of existing BNN computer vision architectures and develop QuickNet, a simple, easy-to-reproduce BNN that outperforms existing binary networks in terms of latency and accuracy on ImageNet. Furthermore, we investigate the impact of full-precision shortcuts and the relationship between number of MACs and model latency. We are convinced that empirical performance should drive BNN architecture design and hope this work will facilitate others to design, benchmark and deploy binary models.