# MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?

arXiv: https://arxiv.org/abs/2001.05936 · HTML: https://mlsanity.com/paper/2001.05936/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2020.

## Built on by (most cited first, 30 of 32)

- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [How Do Adam and Training Strategies Help BNNs Optimization?](https://mlsanity.com/paper/2106.11309/) (2021)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [Sharpness-aware Quantization for Deep Neural Networks](https://mlsanity.com/paper/2111.12273/) (2021)
- [BiBench: Benchmarking and Analyzing Network Binarization](https://mlsanity.com/paper/2301.11233/) (2023)
- [Information Theoretic Representation Distillation](https://mlsanity.com/paper/2112.00459/) (2021)
- [SiMaN: Sign-to-Magnitude Network Binarization](https://mlsanity.com/paper/2102.07981/) (2021)
- [S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration](https://mlsanity.com/paper/2102.08946/) (2021)
- [Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket](https://mlsanity.com/paper/2211.12933/) (2022)
- [Generalizable Mixed-Precision Quantization via Attribution Rank Preservation](https://mlsanity.com/paper/2108.02720/) (2021)
- [BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models](https://mlsanity.com/paper/2404.05662/) (2024)
- [BoolNet: Minimizing The Energy Consumption of Binary Neural Networks](https://mlsanity.com/paper/2106.06991/) (2021)
- [Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies](https://mlsanity.com/paper/2209.01404/) (2022)
- [PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks](https://mlsanity.com/paper/2404.00103/) (2024)
- [BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons](https://mlsanity.com/paper/2212.14158/) (2022)
- [Input Layer Binarization with Bit-Plane Encoding](https://mlsanity.com/paper/2305.02885/) (2023)
- [BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation](https://mlsanity.com/paper/2207.01394/) (2022)
- [RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating](https://mlsanity.com/paper/2207.09049/) (2022)
- [AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks](https://mlsanity.com/paper/2211.03741/) (2022)
- [Task complexity shapes internal representations and robustness in neural networks](https://mlsanity.com/paper/2508.05463/) (2025)
- [Gradient-Based Interpretability Methods and Binarized Neural Networks](https://mlsanity.com/paper/2106.12569/) (2021)
- [Binary Neural Networks as a general-propose compute paradigm for on-device computer vision](https://mlsanity.com/paper/2202.03716/) (2022)
- [Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices](https://mlsanity.com/paper/2206.09029/) (2022)
- [Learning Accurate Performance Predictors for Ultrafast Automated Model Compression](https://mlsanity.com/paper/2304.06393/) (2023)
- [BiVM: Accurate Binarized Neural Network for Efficient Video Matting](https://mlsanity.com/paper/2507.04456/) (2025)
- [AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks](https://mlsanity.com/paper/2104.07770/) (2021)
- [Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices](https://mlsanity.com/paper/2207.05784/) (2022)
- [IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks](https://mlsanity.com/paper/2210.02637/) (2022)
- [Understanding weight-magnitude hyperparameters in training binary networks](https://mlsanity.com/paper/2303.02452/) (2023)

## Abstract (arXiv)

Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices with limited power and computational resources. However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks. Previous work has increased the number of channels or used multiple binary bases to alleviate these problems. In this paper, we instead present an architectural approach: MeliusNet. It consists of alternating a DenseBlock, which increases the feature capacity, and our proposed ImprovementBlock, which increases the feature quality. Experiments on the ImageNet dataset demonstrate the superior performance of our MeliusNet over a variety of popular binary architectures with regards to both computation savings and accuracy. Furthermore, with our method we trained BNN models, which for the first time can match the accuracy of the popular compact network MobileNet-v1 in terms of model size, number of operations and accuracy. Our code is published online at https://github.com/hpi-xnor/BMXNet-v2