论文标题
Q-Capsnets：定量胶囊网络的专门框架
Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks
论文作者
论文摘要
与传统CNN相比，Google Brain Team最近提出的胶囊网络（CAPSNET）在机器学习任务（例如图像分类）中具有出色的学习能力。但是，CAPSNET需要非常激烈的计算，并且很难在资源受限的边缘设备上以其原始形式部署。本文首次尝试通过为CAPSNET开发专门的量化框架来量化CAPSNET模型，以实现其有效的边缘实现。我们评估了几个基准测试的框架。在CIFAR10数据集的Deep Capsnet模型上，该框架将内存足迹降低了6.2倍，精度损失仅为0.15％。我们将于2020年8月在https://git.io/jvdif上开放框架。
Capsule Networks (CapsNets), recently proposed by the Google Brain team, have superior learning capabilities in machine learning tasks, like image classification, compared to the traditional CNNs. However, CapsNets require extremely intense computations and are difficult to be deployed in their original form at the resource-constrained edge devices. This paper makes the first attempt to quantize CapsNet models, to enable their efficient edge implementations, by developing a specialized quantization framework for CapsNets. We evaluate our framework for several benchmarks. On a deep CapsNet model for the CIFAR10 dataset, the framework reduces the memory footprint by 6.2x, with only 0.15% accuracy loss. We will open-source our framework at https://git.io/JvDIF in August 2020.
