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 2108.07600cs.LGcs.CV
收藏

通过互逆线性变换的直接领域自适应

Direct domain adaptation through reciprocal linear transformations

King Abdullah University of Science and Technology(阿卜杜拉国王科技大学)

Tariq Alkhalifah, Oleg Ovcharenko

摘要:

我们提出了一个直接的领域自适应(DDA)的方法来丰富训练的监督神经网络的合成数据的功能,从现实世界的数据。该过程涉及对NN模型的输入特征的一系列线性操作,无论它们来自源域还是目标域,如下:1)输入数据(即图像)与来自该域的所有图像的随机拾取的样本像素(或多个像素)或所有图像的所有随机拾取的样本像素(或多个像素)的平均值的互相关。2)所得数据与来自另一域的自相关输入图像的平均值的卷积。在训练阶段,如预期的那样,输入图像来自源域,并且从目标域评估自相关图像的均值。在推理/应用阶段,输入图像来自目标域,自相关图像的均值从源域计算。所提出的方法仅操作来自源域和目标域的数据,并且不显式地干扰训练工作流和网络架构。包括在MNIST数据集上训练卷积神经网络和在MNIST-M数据集上测试网络的应用在测试数据上实现了70%的准确度。主成分分析(PCA),以及t-SNE,表明从源和目标域的输入功能,建议的直接变换后,与原始MNIST和MNIST-M输入功能相比,与主成分共享类似的属性。

英文摘要:

We propose a direct domain adaptation (DDA) approach to enrich the training of supervised neural networks on synthetic data by features from real-world data. The process involves a series of linear operations on the input features to the NN model, whether they are from the source or target domains, as follows: 1) A cross-correlation of the input data (i.e. images) with a randomly picked sample pixel (or pixels) of all images from that domain or the mean of all randomly picked sample pixel (or pixels) of all images. 2) The convolution of the resulting data with the mean of the autocorrelated input images from the other domain. In the training stage, as expected, the input images are from the source domain, and the mean of auto-correlated images are evaluated from the target domain. In the inference/application stage, the input images are from the target domain, and the mean of auto-correlated images are evaluated from the source domain. The proposed method only manipulates the data from the source and target domains and does not explicitly interfere with the training workflow and network architecture. An application that includes training a convolutional neural network on the MNIST dataset and testing the network on the MNIST-M dataset achieves a 70% accuracy on the test data. A principal component analysis (PCA), as well as t-SNE, show that the input features from the source and target domains, after the proposed direct transformations, share similar properties along with the principal components as compared to the original MNIST and MNIST-M input features.

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。

↑