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 1805.00987cs.LGcs.NEstat.ML
收藏

X-CNN跨模态连接拓扑的自动推断

Automatic Inference of Cross-modal Connection Topologies for X-CNNs

University of Cambridge(剑桥大学)

Laurynas Karazija, Petar Veličković, Pietro Liò

摘要:

本文介绍了一种从基本卷积网络(CNN)和训练数据学习交叉模态卷积神经网络(X-CNN)架构的方法,以降低设计成本并使交叉模态网络能够在稀疏数据环境中应用。提出了两种构建X-CNN的方法。基础方法通过使用在基础CNN上执行的测量和提供的数据,以数据驱动的方式学习拓扑。迭代方法通过组合学习过程执行拓扑的进一步优化,同时学习拓扑和训练网络。这些方法在手工设计的X-CNN及其基础变体的例子中进行了评估,显示出优越的性能,在某些情况下,获得了额外的9%的准确度。从进一步的考虑,我们得出结论,所提出的方法需要更少的时间比任何手动方法,同时也显着降低了设计的复杂性。这些方法的应用是完全自动化的,并在Xsertion库中实现。

英文摘要:

This paper introduces a way to learn cross-modal convolutional neural network (X-CNN) architectures from a base convolutional network (CNN) and the training data to reduce the design cost and enable applying cross-modal networks in sparse data environments. Two approaches for building X-CNNs are presented. The base approach learns the topology in a data-driven manner, by using measurements performed on the base CNN and supplied data. The iterative approach performs further optimisation of the topology through a combined learning procedure, simultaneously learning the topology and training the network. The approaches were evaluated agains examples of hand-designed X-CNNs and their base variants, showing superior performance and, in some cases, gaining an additional 9% of accuracy. From further considerations, we conclude that the presented methodology takes less time than any manual approach would, whilst also significantly reducing the design complexity. The application of the methods is fully automated and implemented in Xsertion library.

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。

↑