Year: 2020
Type: conference-paper
Abstract: 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.
Institutions: TU Wien, Politecnico di Torino
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Technische Universität Wien
OpenAlex ID: W3017183295