Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks

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 in August 2020.

arXiv commentAccepted for publication at Design Automation Conference 2020 (DAC 2020)

References in corpus (7)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Residual Learning for Image Recognition
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Binarized Neural Networks
• Fixed Point Quantization of Deep Convolutional Networks
• Hardware-oriented Approximation of Convolutional Neural Networks
• CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse

Cited by in corpus (5)

• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware
• Shifting Capsule Networks from the Cloud to the Deep Edge
• FastCaps: A Design Methodology for Accelerating Capsule Network on Field Programmable Gate Arrays