A Data and Compute Efficient Design for Limited-Resources Deep Learning

2020/04/21 by Mirgahney Mohamed, Mohamed, Mirgahney, Gabriele Cesa +5 · 1 citation
Computer Science · Medicine · #Advanced Neural Network Applications #COVID-19 diagnosis using AI #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2004.09691

openalex publication_date 2020/04/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Thanks to their improved data efficiency, equivariant neural networks have gained increased interest in the deep learning community. They have been successfully applied in the medical domain where symmetries in the data can be effectively exploited to build more accurate and robust models. To be able to reach a much larger body of patients, mobile, on-device implementations of deep learning solutions have been developed for medical applications. However, equivariant models are commonly implemented using large and computationally expensive architectures, not suitable to run on mobile devices. In this work, we design and test an equivariant version of MobileNetV2 and further optimize it with model quantization to enable more efficient inference. We achieve close-to state of the art performance on the Patch Camelyon (PCam) medical dataset while being more computationally efficient.

Citations

• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Quantizing deep convolutional networks for efficient inference: A whitepaper
• Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
• Deep Learning With Edge Computing: A Review
• RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
• General E(2)-Equivariant Steerable CNNs
• Attentive Group Equivariant Convolutional Networks

Cited by

• Measuring the Impact of Rotation Equivariance on Aerial Object Detection

Related

• EffNet: An Efficient Structure for Convolutional Neural Networks
• CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks
• DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks
• MNN: A Universal and Efficient Inference Engine
• QuantU-Net: Efficient Wearable Medical Imaging Using Bitwidth as a Trainable Parameter