将图像分域处理，结合CNN与LDA提升分类精度与训练速度
Domain-decomposed image classification algorithms using linear discriminant analysis and convolutional neural networks
- 采用分域分解策略，将图像划分为局部区域分别处理
- 相比全局模型，分类准确率提升且训练更快
- 适合需要高效高精度的图像分类任务
在众多现代计算机应用中，图像数据分类至关重要。卷积神经网络（CNN）和线性判别分析（LDA）及其改进版本是常用的监督学习方法。本文实验比较了两种基于域分解思想的CNN模型，用于不同图像分类任务。两者均受域分解方法启发，并结合迁移学习策略。结果表明，所提模型相比未使用迁移学习的全局CNN模型，在分类准确率上有所提升，同时加快了训练过程。此外，提出一种新型分域LDA策略，依赖局部化方法，并与小型神经网络结合。相较于对全输入数据应用的全局LDA，该分域方法在测试问题中表现出更高的分类准确率。
原文摘要 · Abstract (English)
In many modern computer application problems, the classification of image data plays an important role. Among many different supervised machine learning models, convolutional neural networks (CNNs) and linear discriminant analysis (LDA) as well as sophisticated variants thereof are popular techniques. In this work, two different domain decomposed CNN models are experimentally compared for different image classification problems. Both models are loosely inspired by domain decomposition methods and in addition, combined with a transfer learning strategy. The resulting models show improved classification accuracies compared to the corresponding, composed global CNN model without transfer learning and besides, also help to speed up the training process. Moreover, a novel decomposed LDA strategy is proposed which also relies on a localization approach and which is combined with a small neural network model. In comparison with a global LDA applied to the entire input data, the presented decomposed LDA approach shows increased classification accuracies for the considered test problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。