计算机科学
深度学习
卷积神经网络
人工智能
医学影像学
人工神经网络
图像分割
分割
机器学习
航程(航空)
图像(数学)
模式识别(心理学)
复合材料
材料科学
作者
Adrian Celaya,Jonas Actor,Muthusivarajan Rajarajeswari,Evan D. H. Gates,Caroline D. Chung,Dawid Schellingerhout,Beatrice M. Rivière,David Fuentes
标识
DOI:10.1109/tmi.2022.3224873
摘要
Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by throttling the growth of the number of channels in convolutional neural networks. We demonstrate that, for a range of segmentation and classification tasks, PocketNet architectures produce results comparable to that of conventional neural networks while reducing the number of parameters by multiple orders of magnitude, using up to 90% less GPU memory, and speeding up training times by up to 40%, thereby allowing such models to be trained and deployed in resource-constrained settings.
科研通智能强力驱动
Strongly Powered by AbleSci AI