论文标题
Meliusnet：二元神经网络可以达到Mobilenet级的准确性吗？
MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
论文作者
论文摘要
二进制神经网络（BNN）是使用二进制重量和激活的神经网络，而不是典型的32位浮点值。它们减少了模型尺寸，并允许对功率和计算资源有限的移动设备或嵌入式设备有效推断。但是，重量和激活的二元化导致具有较低质量和较低容量的地图，因此与传统网络相比，准确性下降。以前的工作增加了渠道的数量或使用多个二进制基础来减轻这些问题。在本文中，我们提出了一种建筑方法：Meliusnet。它包括交替的密集块，这增加了功能能力，我们提出的ImprovementBlock提高了功能质量。 Imagenet数据集的实验证明了我们的Meliusnet在计算节省和准确性方面的卓越性能而不是各种流行的二元架构。此外，通过我们的方法，我们训练了BNN模型，该模型首次可以在模型大小，操作数量和准确性方面首次与流行的紧凑型网络Mobilenet-V1相匹配。我们的代码在线发布在https://github.com/hpi-xnor/bmxnet-v2
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
