Tensor Contraction Layers for Parsimonious Deep Nets
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(2017)
摘要
Tensors offer a natural representation for many kinds of data frequently encountered in machine learning. Images, for example, are naturally represented as third order tensors, where the modes correspond to height, width, and channels. Tensor methods are noted for their ability to discover multi-dimensional dependencies, and tensor decompositions in particular, have been used to produce compact low-rank approximations of data. In this paper, we explore the use of tensor contractions as neural network layers and investigate several ways to apply them to activation tensors. Specifically, we propose the Tensor Contraction Layer (TCL), the first attempt to incorporate tensor contractions as end-to-end trainable neural network layers. Applied to existing networks, TCLs reduce the dimensionality of the activation tensors and thus the number of model parameters. We evaluate the TCL on the task of image recognition, augmenting two popular networks (AlexNet, VGG). The resulting models are trainable end-to-end. Applying the TCL to the task of image recognition, using the CIFAR100 and ImageNet datasets, we evaluate the effect of parameter reduction via tensor contraction on performance. We demonstrate significant model compression without significant impact on the accuracy and, in some cases, improved performance.
更多查看译文
关键词
tensor contraction layers,parsimonious deep nets,tensor decompositions,multidimensional dependencies,low-rank data approximation,activation tensors,tensor contraction layer,TCL,neural network layer training,dimensionality reduction,image recognition,AlexNet,VGG,CIFAR100 datasets,ImageNet datasets,parameter reduction,tensor contraction,model compression
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络