Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks
This addresses the problem of energy-efficient and verifiable medical imaging for healthcare applications, though it is incremental as it builds on existing self-attention and quantization techniques.
The paper tackles the high computational complexity and black-box nature of CNNs in medical image analysis by proposing quantised self-attention models, achieving reductions of 50-80% in model size, 60-80% in parameters, 40-85% in FLOPs, and 65-80% in energy efficiency on CPUs.
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-Network}{https://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Network}.