Image classification and training with severe data loss
Image classification and training with severe data loss
复制标题
DOI：
10.1117/12.2633172
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Dillon Marquard;Kyle Wright;Roummel F. Marcia
中科院分区：
文献类型：
--
作者：
Dillon Marquard;Kyle Wright;Roummel F. Marcia
图像分类是机器学习中的一类重要问题，广泛应用于医学、生态学、天文学和国防等许多现实应用中。卷积神经网络（CNN）是为具有网格结构的输入而设计的机器学习技术，例如，图像，其特征是空间相关的。因此，CNN已被证明是许多图像分类问题的高效方法，并且在许多图像分类和对象检测竞赛中始终优于其他方法。使用机器学习对图像进行分类的一个特殊挑战是以丢失像素的形式丢失测量数据，这发生在存在场景遮挡或成像系统中的光电探测器部分损坏的情况下。在这种情况下，即使对输入图像的扰动很小，CNN模型的性能也会恶化或变得不可靠。在这项工作中，我们研究了提高CNN模型在缺失数据图像分类中的性能的技术。特别是，我们探索了各种数据变化的训练，这些数据变化模拟了数据丢失，以产生更强大的分类器。通过优化分类交叉熵损失函数，我们通过在MNIST数据集上的数值实验证明，使用这些合成改变进行训练可以提高CNN模型的分类准确性。
Image classification forms an important class of problems in machine learning and is widely used in many realworld applications, such as medicine, ecology, astronomy, and defense. Convolutional neural networks (CNNs) are machine learning techniques designed for inputs with grid structures, e.g., images, whose features are spatially correlated. As such, CNNs have been demonstrated to be highly effective approaches for many image classification problems and have consistently outperformed other approaches in many image classification and object detection competitions. A particular challenge involved in using machine learning for classifying images is measurement data loss in the form of missing pixels, which occurs in settings where scene occlusions are present or where the photodetectors in the imaging system are partially damaged. In such cases, the performance of CNN models tends to deteriorate or becomes unreliable even when the perturbations to the input image are small. In this work, we investigate techniques for improving the performance of CNN models for image classification with missing data. In particular, we explore training on a variety of data alterations that mimic data loss for producing more robust classifiers. By optimizing the categorical cross-entropy loss function, we demonstrate through numerical experiments on the MNIST dataset that training with these synthetic alterations can enhance the classification accuracy of our CNN models.