# From Hashing to CNNs: Training BinaryWeight Networks via Hashing

arXiv: https://arxiv.org/abs/1802.02733 · HTML: https://mlsanity.com/paper/1802.02733/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2018.

## Built on by (most cited first, 23 of 23)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets](https://mlsanity.com/paper/2208.08084/) (2022)
- [Distribution-sensitive Information Retention for Accurate Binary Neural Network](https://mlsanity.com/paper/2109.12338/) (2021)
- [Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training](https://mlsanity.com/paper/2308.06689/) (2023)
- [Lipschitz Continuity Retained Binary Neural Network](https://mlsanity.com/paper/2207.06540/) (2022)
- [Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks](https://mlsanity.com/paper/2110.09195/) (2021)
- [S3: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks](https://mlsanity.com/paper/2107.03453/) (2021)
- [Model Pruning Based on Quantified Similarity of Feature Maps](https://mlsanity.com/paper/2105.06052/) (2021)
- [DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization](https://mlsanity.com/paper/2208.09708/) (2022)
- [Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions](https://mlsanity.com/paper/2108.13055/) (2021)
- [AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks](https://mlsanity.com/paper/2211.03741/) (2022)
- [Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations](https://mlsanity.com/paper/2107.01400/) (2021)
- [Differentiable Architecture Pruning for Transfer Learning](https://mlsanity.com/paper/2107.03375/) (2021)
- [Signed Binary Weight Networks](https://mlsanity.com/paper/2211.13838/) (2022)
- [RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs](https://mlsanity.com/paper/2301.06193/) (2023)
- [Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration](https://mlsanity.com/paper/2106.09886/) (2021)
- [Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization](https://mlsanity.com/paper/2111.07046/) (2021)
- [HyBNN and FedHyBNN: (Federated) Hybrid Binary Neural Networks](https://mlsanity.com/paper/2205.09839/) (2022)
- [Searching Similarity Measure for Binarized Neural Networks](https://mlsanity.com/paper/2206.03325/) (2022)
- [Learning Discrete Weights and Activations Using the Local Reparameterization Trick](https://mlsanity.com/paper/2307.01683/) (2023)
- [PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off](https://mlsanity.com/paper/2312.01581/) (2023)
- [Cauchy-Schwarz Regularizers](https://mlsanity.com/paper/2503.01639/) (2025)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) have shown appealing performance on various computer vision tasks in recent years. This motivates people to deploy CNNs to realworld applications. However, most of state-of-art CNNs require large memory and computational resources, which hinders the deployment on mobile devices. Recent studies show that low-bit weight representation can reduce much storage and memory demand, and also can achieve efficient network inference. To achieve this goal, we propose a novel approach named BWNH to train Binary Weight Networks via Hashing. In this paper, we first reveal the strong connection between inner-product preserving hashing and binary weight networks, and show that training binary weight networks can be intrinsically regarded as a hashing problem. Based on this perspective, we propose an alternating optimization method to learn the hash codes instead of directly learning binary weights. Extensive experiments on CIFAR10, CIFAR100 and ImageNet demonstrate that our proposed BWNH outperforms current state-of-art by a large margin.