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 2303.01567cs.LGcs.CV
收藏

具有有效保证不变性的深度神经网络

Deep Neural Networks with Efficient Guaranteed Invariances

Robert Bosch GmbH(罗伯特·博世有限公司);University of Lübeck(吕贝克大学)

Matthias Rath, Alexandru Paul Condurache

摘要:

我们通过强制和保证对称变换的不变性,而不是从数据中学习,来解决提高深度神经网络的性能,特别是样本复杂度的问题。群等变卷积是获得等变表示的一种流行方法。然后使用池化操作来施加期望的对应不变性。对于旋转,已经表明使用不变积分而不是池化进一步提高了样本复杂度。在这方面的贡献,我们首先扩大不变量积分超越旋转翻转和缩放变换。然后,我们解决的问题,将多个所需的不变性到一个单一的网络。为此,我们提出了一种多流架构,其中每个流对于不同的变换是不变的,使得网络可以同时受益于多个不变性。我们证明了我们的方法与成功的实验缩放MNIST,SVHN,CIFAR-10和STL-10。

英文摘要:

We address the problem of improving the performance and in particular the sample complexity of deep neural networks by enforcing and guaranteeing invariances to symmetry transformations rather than learning them from data. Group-equivariant convolutions are a popular approach to obtain equivariant representations. The desired corresponding invariance is then imposed using pooling operations. For rotations, it has been shown that using invariant integration instead of pooling further improves the sample complexity. In this contribution, we first expand invariant integration beyond rotations to flips and scale transformations. We then address the problem of incorporating multiple desired invariances into a single network. For this purpose, we propose a multi-stream architecture, where each stream is invariant to a different transformation such that the network can simultaneously benefit from multiple invariances. We demonstrate our approach with successful experiments on Scaled-MNIST, SVHN, CIFAR-10 and STL-10.

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。

↑