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 2206.09414cs.CVcs.AIcs.LG
收藏

基于高光谱图像迁移学习的地形分类:一项比较研究

Terrain Classification using Transfer Learning on Hyperspectral Images: A Comparative study

Indian Institute of Information Technology, Allahabad(阿拉哈巴德印度信息技术学院)

Uphar Singh, Kumar Saurabh, Neelaksh Trehan, Ranjana Vyas, O. P. Vyas

AI总结:

提出基于PCA降维和迁移学习的高光谱图像地形分类方法,比较CNN与MLP架构,发现迁移学习能大幅减少训练时间且不明显影响准确率。

摘要:

与RGB图像相比,高光谱图像包含更多的通道,因此包含更多关于图像中实体的信息。卷积神经网络(CNN)和多层感知机(MLP)已被证明是有效的图像分类方法。然而,它们存在训练时间长和需要大量标注数据才能达到预期效果的问题。在处理高光谱图像时,这些问题变得更加复杂。为了减少训练时间并降低对大型标注数据集的依赖,我们提出使用迁移学习方法。高光谱数据集使用PCA预处理到较低维度,然后对其应用深度学习模型进行分类。该模型学习到的特征随后被迁移学习模型用于在未见过的数据集上解决新的分类问题。我们对CNN和多个MLP架构模型进行了详细比较,以确定最适合该目标的最佳架构。结果表明,层的扩展并不总是导致准确率提高,而是经常导致过拟合,并且增加训练时间。通过应用迁移学习方法,训练时间得到了更大程度的减少,而不是仅仅通过在大型数据集上直接训练新模型来解决问题,同时准确率没有受到太大影响。

英文摘要:

A Hyperspectral image contains much more number of channels as compared to a RGB image, hence containing more information about entities within the image. The convolutional neural network (CNN) and the Multi-Layer Perceptron (MLP) have been proven to be an effective method of image classification. However, they suffer from the issues of long training time and requirement of large amounts of the labeled data, to achieve the expected outcome. These issues become more complex while dealing with hyperspectral images. To decrease the training time and reduce the dependence on large labeled dataset, we propose using the method of transfer learning. The hyperspectral dataset is preprocessed to a lower dimension using PCA, then deep learning models are applied to it for the purpose of classification. The features learned by this model are then used by the transfer learning model to solve a new classification problem on an unseen dataset. A detailed comparison of CNN and multiple MLP architectural models is performed, to determine an optimum architecture that suits best the objective. The results show that the scaling of layers not always leads to increase in accuracy but often leads to overfitting, and also an increase in the training time.The training time is reduced to greater extent by applying the transfer learning approach rather than just approaching the problem by directly training a new model on large datasets, without much affecting the accuracy.

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。

↑