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 1707.01786cs.CV
收藏

用于视频分类的张量训练循环神经网络

Tensor-Train Recurrent Neural Networks for Video Classification

Ludwig Maximilian University of Munich(慕尼黑大学);Siemens AG(西门子股份公司)

Yinchong Yang, Denis Krompass, Volker Tresp

摘要:

循环神经网络及其变体在诸如自然语言处理等序列建模任务中表现出了良好的性能。然而,这些模型,原来是不切实际的,难以训练时,暴露于非常高维的输入,由于大的输入隐藏的权重矩阵。这可能阻止了RNN在涉及非常高输入维度的任务中的大规模应用,例如视频建模;当前的方法使用各种特征提取器来降低输入维度。为了应对这一挑战,我们提出了一种新的,更通用和有效的方法,通过使用与权重本身同时训练的Tensor-Train分解来分解输入到隐藏权重矩阵。我们使用多个真实世界的视频数据集在分类任务上测试了我们的模型,并使用最先进的模型实现了具有竞争力的性能,尽管我们的模型架构的复杂性要低几个数量级。我们相信,所提出的方法为使用RNN架构对高维序列数据进行建模提供了一种新颖的基本构建块,并开辟了许多可能性,可以将NLP等其他领域的表达性和高级架构转移到高维序列数据建模中。

英文摘要:

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very high-dimensional inputs due to the large input-to-hidden weight matrix. This may have prevented RNNs' large-scale application in tasks that involve very high input dimensions such as video modeling; current approaches reduce the input dimensions using various feature extractors. To address this challenge, we propose a new, more general and efficient approach by factorizing the input-to-hidden weight matrix using Tensor-Train decomposition which is trained simultaneously with the weights themselves. We test our model on classification tasks using multiple real-world video datasets and achieve competitive performances with state-of-the-art models, even though our model architecture is orders of magnitude less complex. We believe that the proposed approach provides a novel and fundamental building block for modeling high-dimensional sequential data with RNN architectures and opens up many possibilities to transfer the expressive and advanced architectures from other domains such as NLP to modeling high-dimensional sequential 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。

↑