# Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks

arXiv: https://arxiv.org/abs/2209.15287 · HTML: https://mlsanity.com/paper/2209.15287/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [Cross-Modal Self-Attention Network for Referring Image Segmentation](https://mlsanity.com/paper/1904.04745/) (2019)
- [Scaling Local Self-Attention for Parameter Efficient Visual Backbones](https://mlsanity.com/paper/2103.12731/) (2021)
- [Training and Inference with Integers in Deep Neural Networks](https://mlsanity.com/paper/1802.04680/) (2018)
- [FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference](https://mlsanity.com/paper/2101.05615/) (2021)
- [Quantisation and Pruning for Neural Network Compression and Regularisation](https://mlsanity.com/paper/2001.04850/) (2020)
- [Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition](https://mlsanity.com/paper/2112.11438/) (2021)
- [SUMNet: Fully Convolutional Model for Fast Segmentation of Anatomical Structures in Ultrasound Volumes](https://mlsanity.com/paper/1901.06920/) (2019)

## Built on by (most cited first, 2 of 2)

- [Investigation of Energy-efficient AI Model Architectures and Compression Techniques for "Green" Fetal Brain Segmentation](https://mlsanity.com/paper/2405.15778/) (2024)
- [Aggregating empirical evidence from data strategy studies: a case on model quantization](https://mlsanity.com/paper/2505.00816/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks have played a significant role in various medical imaging tasks like classification and segmentation. They provide state-of-the-art performance compared to classical image processing algorithms. However, the major downside of these methods is the high computational complexity, reliance on high-performance hardware like GPUs and the inherent black-box nature of the model. In this paper, we propose quantised stand-alone self-attention based models as an alternative to traditional CNNs. In the proposed class of networks, convolutional layers are replaced with stand-alone self-attention layers, and the network parameters are quantised after training. We experimentally validate the performance of our method on classification and segmentation tasks. We observe a 50-80% reduction in model size, 60-80% lesser number of parameters, 40-85% fewer FLOPs and 65-80% more energy efficiency during inference on CPUs. The code will be available at href https://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Networkhttps://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Network.