arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.01034cs.CVstat.ML
收藏

FrequentNet:一种用于图像分类的新型可解释深度学习模型

FrequentNet: A Novel Interpretable Deep Learning Model for Image Classification

Zhejiang University(浙江大学);Microsoft(微软);Instacart;Cornell University(康奈尔大学)

Yifei Li, Kuangyan Song, Yiming Sun, Liao Zhu

摘要:

本文提出了一种新的基线深度学习模型,更有利于图像分类。与卷积神经网络(CNN)实践不同,在卷积神经网络(CNN)实践中,通过反向传播来训练滤波器以表示图像的不同模式,我们受到“PCANet:A Simple深度学习Baseline for图像分类?从频域中的基向量(如傅立叶系数或小波)中选择滤波器向量,而无需反向传播。研究人员已经证明,频域中的那些基础通常可以提供物理见解,这通过分析所选择的频率来增加模型的可解释性。此外,与CNN的“黑箱”训练过程相比,训练过程也将更加省时、数学上清晰和可解释。

英文摘要:

This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different patterns of an image, we are inspired by a method called "PCANet" in "PCANet: A Simple Deep Learning Baseline for Image Classification?" to choose filter vectors from basis vectors in frequency domain like Fourier coefficients or wavelets without back propagation. Researchers have demonstrated that those basis in frequency domain can usually provide physical insights, which adds to the interpretability of the model by analyzing the frequencies selected. Besides, the training process will also be more time efficient, mathematically clear and interpretable compared with the "black-box" training process of CNN.

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。

↑