arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.01437eess.IVcs.CV
收藏

基于信息论的表示学习方法在COVID-19检测中的应用

Representation Learning with Information Theory for COVID-19 Detection

Vrije Universiteit Brussel(布鲁塞尔自由大学);Interuniversity Microelectronics Centre (IMEC)(校际微电子中心(IMEC))

Abel Díaz Berenguer, Tanmoy Mukherjee, Matias Bossa, Nikos Deligiannis, Hichem Sahli

摘要:

成功的数据表示是基于机器学习的医学成像分析的基本因素。深度学习(DL)在鲁棒的表示学习中发挥了重要作用。然而,深度模型无法推广到看不见的数据,可能会很快过度拟合复杂的模式。因此,我们可以方便地实施策略来帮助深度模型从数据中发现有用的先验知识,以学习它们的内在属性。我们的模型,我们称之为双角色网络(DRN),使用依赖最大化的方法基于最小二乘互信息(LSMI)。LSMI利用依赖性度量来确保表示不变性和局部平滑性。虽然先前的工作已经使用了信息论的措施,如互信息,已知是计算昂贵的,由于密度估计的步骤,我们的LSMI公式阐明了棘手的互信息估计的问题,并可以用来近似it. CT基于COVID-19检测和COVID-19严重性检测基准的实验证明了我们的方法的有效性。

英文摘要:

Successful data representation is a fundamental factor in machine learning based medical imaging analysis. Deep Learning (DL) has taken an essential role in robust representation learning. However, the inability of deep models to generalize to unseen data can quickly overfit intricate patterns. Thereby, we can conveniently implement strategies to aid deep models in discovering useful priors from data to learn their intrinsic properties. Our model, which we call a dual role network (DRN), uses a dependency maximization approach based on Least Squared Mutual Information (LSMI). The LSMI leverages dependency measures to ensure representation invariance and local smoothness. While prior works have used information theory measures like mutual information, known to be computationally expensive due to a density estimation step, our LSMI formulation alleviates the issues of intractable mutual information estimation and can be used to approximate it. Experiments on CT based COVID-19 Detection and COVID-19 Severity Detection benchmarks demonstrate the effectiveness of our method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑