paper-with-me

Papers

Convolutional neural networks with low-rank regularization

2015-11-19 · Cheng Tai, Tong Xiao, Yi Zhang, Xiaogang Wang, Weinan E

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank tensor decomposition for removing the redundancy in the convolution kernels. The algorithm finds the exact global optimizer of the decomposition and is more effective than iterative methods. Based on the decomposition, we further propose a new method for training low-rank constrained CNNs from scratch. Interestingly, while achieving a significant speedup, sometimes the low-rank constrained CNNs delivers significantly better performance than their non-constrained counterparts. On the CIFAR-10 dataset, the proposed low-rank NIN model achieves $91.31\%$ accuracy (without data augmentation), which also improves upon state-of-the-art result. We evaluated the proposed method on CIFAR-10 and ILSVRC12 datasets for a variety of modern CNNs, including AlexNet, NIN, VGG and GoogleNet with success. For example, the forward time of VGG-16 is reduced by half while the performance is still comparable. Empirical success suggests that low-rank tensor decompositions can be a very useful tool for speeding up large CNNs.

📄 PDF Abstract BibTeX arXiv:1511.06067

Code (2)

chengtaipu/lowrankcnn 공식 구현
Aldiom/nn_benchmark tf

Tasks

Data AugmentationTensor Decomposition

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Average Pooling 설명 없음
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Inception Module An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
How do I speak to a person at Expedia?-/+/ To make a reservation or communicate with Expedia, the quickest option is typically to call their customer service at +1-805-330-4056 or +1-805-330-4056. You can also use the live…

Similar Papers 제목 키워드 기반

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

2022-01-27 · Noam Razin, Asaf Maman, Nadav Cohen

In the pursuit of explaining implicit regularization in deep learning, prominent focus was given to matrix and tensor factorizations, which correspond to simplified neural networks. It was shown that these models exhibit…

Tensor Regression Networks with various Low-Rank Tensor Approximations

2017-12-27 · Xingwei Cao, Guillaume Rabusseau

Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposing low tensor rank structure on the weight matrices of fully connected layers. I…

regression

On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks

2019-01-29 · Peter Langenberg, Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

Recently, there has been an abundance of works on designing Deep Neural Networks (DNNs) that are robust to adversarial examples. In particular, a central question is which features of DNNs influence adversarial robustnes…

Adversarial Robustness

Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning

2021-10-18 · Uche Osahor, Nasser M. Nasrabadi

In few-shot classification, the primary goal is to learn representations from a few samples that generalize well for novel classes. In this paper, we propose an efficient low displacement rank (LDR) regularization strate…

Data AugmentationDiversityFew-Shot Learning

Convolutional Neural Network Compression Based on Low-Rank Decomposition

2024-08-29 · Yaping He, Linhao Jiang, Di wu

Deep neural networks typically impose significant computational loads and memory consumption. Moreover, the large parameters pose constraints on deploying the model on edge devices such as embedded systems. Tensor decomp…

Model CompressionNeural Network CompressionTensor Decomposition