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 2011.14759cs.CVcs.LG
收藏

尺度协变与尺度不变的高斯导数网络

Scale-covariant and scale-invariant Gaussian derivative networks

KTH Royal Institute of Technology(KTH皇家理工学院)

Tony Lindeberg

AI总结:

本文结合尺度空间理论与深度学习,构建级联参数化尺度空间操作的网络,证明其尺度协变性,加尺度通道最大池化实现尺度不变性,在MNISTLargeScale数据集上验证了良好的尺度泛化性能。

摘要:

本文提出了一种结合尺度空间理论与深度学习的混合方法,通过级联耦合参数化的尺度空间操作构建深度学习架构。通过在多个尺度通道间共享学习到的参数,并利用尺度空间基元在尺度变换下的变换特性,所得网络被证明具备尺度协变性。此外,通过在多个尺度通道上执行最大池化,所得的图像分类网络架构也被证明具备尺度不变性。我们在MNISTLargeScale数据集上研究了此类网络的性能,该数据集包含由原始MNIST图像缩放得到的样本:训练数据的缩放因子为4,测试数据的缩放因子为16。实验表明,该方法能够实现尺度泛化,在分类训练数据中未出现的尺度的模式时仍能取得良好性能。

英文摘要:

This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale channels, and by using the transformation properties of the scale-space primitives under scaling transformations, the resulting network becomes provably scale covariant. By in addition performing max pooling over the multiple scale channels, a resulting network architecture for image classification also becomes provably scale invariant. We investigate the performance of such networks on the MNISTLargeScale dataset, which contains rescaled images from original MNIST over a factor of 4 concerning training data and over a factor of 16 concerning testing data. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.

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。

↑