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 1708.04347cs.CV
收藏

用于训练深度神经网络的径向变换图像增强

Image Augmentation using Radial Transform for Training Deep Neural Networks

University of Toronto(多伦多大学);St. Michael’s Hospital(圣迈克尔医院)

Hojjat Salehinejad, Shahrokh Valaee, Timothy Dowdell, Joseph Barfett

摘要:

深度学习模型具有大量的自由参数,这些自由参数必须通过在大量训练数据样本上对模型进行有效训练来估计,以提高其泛化性能。在实际应用中,可用于训练这些网络的数据通常是有限的或不平衡的。我们提出了一种基于极坐标系中径向变换的图像增强采样方法,以便于从有限的源数据中训练深度学习模型。这种逐像素变换通过从每个像素生成新图像来提供原始图像在极坐标系中的表示。该技术可以生成多达原始图像中像素数量的径向变换图像,以增加表示不佳的图像类的多样性。我们的实验表明,在使用径向变换图像训练深度卷积神经网络时,泛化性能有所提高。

英文摘要:

Deep learning models have a large number of free parameters that must be estimated by efficient training of the models on a large number of training data samples to increase their generalization performance. In real-world applications, the data available to train these networks is often limited or imbalanced. We propose a sampling method based on the radial transform in a polar coordinate system for image augmentation to facilitate the training of deep learning models from limited source data. This pixel-wise transform provides representations of the original image in the polar coordinate system by generating a new image from each pixel. This technique can generate radial transformed images up to the number of pixels in the original image to increase the diversity of poorly represented image classes. Our experiments show improved generalization performance in training deep convolutional neural networks with radial transformed images.

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。

↑