二值化神经网络的相似性度量搜索
Searching Similarity Measure for Binarized Neural Networks
摘要：
二值化神经网络（BNN）作为一种应用于资源受限设备的模型，引起了学术界和工业界的广泛关注。然而，与全精度深度神经网络（DNN）相比，BNN遭受非平凡的精度下降，限制了其在各个领域的适用性。这部分是因为现有的网络组件，如相似性度量，是专门为DNN设计的，并且可能对BNN来说是次优的。在这项工作中，我们专注于BNN的关键组成部分--相似性度量，它量化了输入特征图和过滤器之间的距离，并提出了一种自动搜索方法，基于遗传算法，为BNN定制的相似性度量。使用ResNet、NIN和VGG对Cifar 10和Cifar 100进行的评估结果表明，大多数识别出的相似性度量比常用的互相关方法的精度提高了3.39%。
英文摘要：
Being a promising model to be deployed in resource-limited devices, Binarized Neural Networks (BNNs) have drawn extensive attention from both academic and industry. However, comparing to the full-precision deep neural networks (DNNs), BNNs suffer from non-trivial accuracy degradation, limiting its applicability in various domains. This is partially because existing network components, such as the similarity measure, are specially designed for DNNs, and might be sub-optimal for BNNs. In this work, we focus on the key component of BNNs -- the similarity measure, which quantifies the distance between input feature maps and filters, and propose an automatic searching method, based on genetic algorithm, for BNN-tailored similarity measure. Evaluation results on Cifar10 and Cifar100 using ResNet, NIN and VGG show that most of the identified similarty measure can achieve considerable accuracy improvement (up to 3.39%) over the commonly-used cross-correlation approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
