mlsanityData to 14 Oct 2026

Shifting Capsule Networks from the Cloud to the Deep Edge

arXiv 2110.02911 ↗First posted 6 Oct 2021cs.LG cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Capsule networks (CapsNets) are an emerging trend in image processing. In contrast to a convolutional neural network, CapsNets are not vulnerable to object deformation, as the relative spatial information of the objects is preserved across the network. However, their complexity is mainly related to the capsule structure and the dynamic routing mechanism, which makes it almost unreasonable to deploy a CapsNet, in its original form, in a resource-constrained device powered by a small microcontroller (MCU). In an era where intelligence is rapidly shifting from the cloud to the edge, this high complexity imposes serious challenges to the adoption of CapsNets at the very edge. To tackle this issue, we present an API for the execution of quantized CapsNets in Arm Cortex-M and RISC-V MCUs. Our software kernels extend the Arm CMSIS-NN and RISC-V PULP-NN to support capsule operations with 8-bit integers as operands. Along with it, we propose a framework to perform post-training quantization of a CapsNet. Results show a reduction in memory footprint of almost 75%, with accuracy loss ranging from 0.07% to 0.18%. In terms of throughput, our Arm Cortex-M API enables the execution of primary capsule and capsule layers with medium-sized kernels in just 119.94 and 90.60 milliseconds (ms), respectively (STM32H755ZIT6U, Cortex-M7 @ 480 MHz). For the GAP-8 SoC (RISC-V RV32IMCXpulp @ 170 MHz), the latency drops to 7.02 and 38.03 ms, respectively.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 6 Oct 2021.

Builds on

18 of 43 references.

References · 18

  1. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  2. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  3. 2017Dynamic Routing Between Capsulescited by 689
  4. 2017One pixel attack for fooling deep neural networkscited by 582
  5. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  6. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
  7. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  8. 2019Stacked Capsule Autoencoderscited by 82
  9. 2016Learning to Perform Physics Experiments via Deep Reinforcement Learningcited by 47
  10. 2019PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processorscited by 35
  11. 2021Quantization and Deployment of Deep Neural Networks on Microcontrollerscited by 21
  12. 2017A Berkeley View of Systems Challenges for AIcited by 15
6 more
  1. 2020Q-CapsNets: A Specialized Framework for Quantizing Capsule Networkscited by 6
  2. 2018Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networkscited by 5
  3. 2018Towards Linear Time Neural Machine Translation with Capsule Networkscited by 4
  4. 2020DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardwarecited by 4
  5. 2018Galaxy morphology prediction using capsule networkscited by 1
  6. 2019Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Designcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025Decentor-V: Lightweight ML Training on Low-Power RISC-V Edge Devicescited by 1
  2. 2024David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep Edgecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Enabling Capsule Networks at the Edge through Approximate Softmax and Squash Operations
  2. 2024Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge
  3. 2025Batch Normalization-Free Fully Integer Quantized Neural Networks via Progressive Tandem Learning
  4. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
  5. 202616-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs
  6. 2022Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
  7. 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge
  8. 2023Performance Characterization of using Quantization for DNN Inference on Edge Devices: Extended Version