A Contrastive Learning Approach to Auroral Identification and Classification
A Contrastive Learning Approach to Auroral Identification and Classification
复制标题
DOI：
10.1109/icmla52953.2021.00128
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Jeremiah W. Johnson;Swathi Hari;D. Hampton;H. Connor;A. Keesee
中科院分区：
文献类型：
--
作者：
Jeremiah W. Johnson;Swathi Hari;D. Hampton;H. Connor;A. Keesee
在基准计算机视觉任务上，无监督学习算法开始达到与监督算法相当的精度，但它们在实际应用中的有效性尚未得到证明。在这项工作中，我们提出了一种新的无监督学习在极光图像分类任务中的应用。具体地说，我们修改和调整了表示法的简单对比学习框架(SimCLR)算法，以学习最近发布的极光图像数据集中的极光图像表示，该数据集中使用了来自事件和亚暴期间大尺度相互作用的时间历史(THEMIS)的图像数据。我们证明：(A)适合于图像的学习表示的简单线性分类器实现了最先进的分类性能，将分类精度比当前基准提高了近10个百分点；以及(B)学习表示自然地聚成了比现有人工分配的类别更多的簇，这表明现有的分类过于粗糙，可能会模糊极光类型、近地太阳风条件和地球表面地磁扰动之间的重要联系。此外，我们的模型比以前在这个数据集上的基准要轻得多，需要的参数数量在面积上不到25%。我们的方法超过了行动目的的既定门槛，表明已做好部署和使用的准备。
Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated. In this work, we present a novel application of unsupervised learning to the task of auroral image classification. Specifically, we modify and adapt the Simple framework for Contrastive Learning of Representations (SimCLR) algorithm to learn representations of auroral images in a recently released auroral image dataset constructed using image data from Time History of Events and Macroscale Interactions during Substorms (THEMIS) all–sky imagers. We demonstrate that (a) simple linear classifiers fit to the learned representations of the images achieve state–of–the–art classification performance, improving the classification accuracy by almost 10 percentage points over the current benchmark; and (b) the learned representations naturally cluster into more clusters than exist manually assigned categories, suggesting that existing categorizations are overly coarse and may obscure important connections between auroral types, near–earth solar wind conditions, and geomagnetic disturbances at the earth’s surface. Moreover, our model is much lighter than the previous benchmark on this dataset, requiring in the area of fewer than 25% of the number of parameters. Our approach exceeds an established threshold for operational purposes, demonstrating readiness for deployment and utilization.