Mesh : Humans Neural Networks, Computer Plankton Machine Learning Software Algorithms

来  源:   DOI:10.1093/bioinformatics/btac703

Abstract:
In recent years, Deep Learning (DL) has been increasingly used in many fields, in particular in image recognition, due to its ability to solve problems where traditional machine learning algorithms fail. However, building an appropriate DL model from scratch, especially in the context of ecological studies, is a difficult task due to the dynamic nature and morphological variability of living organisms, as well as the high cost in terms of time, human resources and skills required to label a large number of training images. To overcome this problem, Transfer Learning (TL) can be used to improve a classifier by transferring information learnt from many domains thanks to a very large training set composed of various images, to another domain with a smaller amount of training data. To compensate the lack of \'easy-to-use\' software optimized for ecological studies, we propose the EcoTransLearn R-package, which allows greater automation in the classification of images acquired with various devices (FlowCam, ZooScan, photographs, etc.), thanks to different TL methods pre-trained on the generic ImageNet dataset.
EcoTransLearn is an open-source package. It is implemented in R and calls Python scripts for image classification step (using reticulate and tensorflow libraries). The source code, instruction manual and examples can be found at https://github.com/IFREMER-LERBL/EcoTransLearn.
Supplementary data are available at Bioinformatics online.
摘要:
结论:近年来,深度学习(DL)已经越来越多地应用于许多领域,特别是在图像识别中,由于它能够解决传统机器学习算法失败的问题。然而,从头开始构建适当的DL模型,特别是在生态学研究的背景下,由于生物体的动态性质和形态变异性,是一项艰巨的任务,以及时间上的高成本,大量培训图像标签所需的人力资源和技能。为了克服这个问题,迁移学习(TL)可用于通过传输从许多领域学习的信息来改进分类器,这要归功于由各种图像组成的非常大的训练集。到另一个具有较少量训练数据的域。为了弥补缺乏“易于使用的”优化生态研究软件,我们提出了EcoTransLearnR包,这使得用各种设备(FlowCam,ZooScan,照片,等。),这要归功于在通用ImageNet数据集上预先训练的不同TL方法。
方法:EcoTransLearn是一个开源软件包。它在R中实现,并调用Python脚本进行图像分类步骤(使用网状和tensorflow库)。源代码,可以在https://github.com/IFREMER-LERBL/EcoTransLearn上找到使用说明书和示例。
背景:补充数据可在Bioinformatics在线获得。
公众号