Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks
This work addresses the computational inefficiency of CapsNets for edge deployment, representing an incremental improvement through quantization.
The paper tackles the problem of deploying Capsule Networks (CapsNets) on resource-constrained edge devices by developing a specialized quantization framework, achieving a 6.2x reduction in memory footprint with only 0.15% accuracy loss on CIFAR10.
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.