Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition

Pan, Yu; Xu, Jing; Wang, Maolin; Ye, Jinmian; Wang, Fei; Bai, Kun; Xu, Zenglin

doi:10.1609/aaai.v33i01.33014683

Cited by 82 publications

(71 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, for fairer comparison and validation of search results, we implement this experiment in Pytorch and remove the tricks in the Keras package. Additionally, through Keras implement, our searched TR-LSTM achieve 64.5% accuracy with a compression ratio 48, which is better than 63.8% with a compression ratio 25 [17].…”

Section: Experiments On Hmdb51 and Ucf11mentioning

confidence: 91%

“…Wenqi et al [26] compress both the fully connected layers and the convolutional layers of CNN with the equal rank elements for whole network. Yu et al [17] replace the over-parametric input-to-hidden layer of LSTM with TRF, when dealing with high-dimensional input data. Rank of these models are determined via multiple manual attempts by manipulation, which requires much time.…”

Section: Rank Fixedmentioning

confidence: 99%

“…By replacing each matrix of the affine matrices W * ∈ R I ×O of input vector x ∈ R I with TRF in LSTM, we implement the TR-LSTM model as introduced by Yu et al [17]. Similar to TR-CNN, the nodes are combined by input nodes U (i) and output nodes V ( j) , and the decomposition needs to follow…”

Section: Tr-lstmmentioning

confidence: 99%

“…With a ring-like structure as shown in Fig. 3, TR can significantly reduce the parameters of convolutional neural network (CNN) [26] and recurrent neural network (RNN) [17], and even can achieve better results than uncompressed models in some tasks. Thus, tensor ring is increasingly being researched.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Heuristic rank selection with progressively searching tensor ring network

Pan

Chen

et al. 2021

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Recently, tensor ring networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named progressively searching tensor ring network search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100, UCF11 and HMDB51, achieving the state-of-the-art performance.

show abstract

Section: Experiments On Hmdb51 and Ucf11mentioning

confidence: 91%

Section: Rank Fixedmentioning

confidence: 99%

Section: Tr-lstmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Heuristic rank selection with progressively searching tensor ring network

Pan

Chen

et al. 2021

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The tensor train format was employed in Novikov et al (2015) to reduce the parameters in fully connected layers. Several tensor decomposition methods were also applied to compress RNNs (Tjandra, Sakti, and Nakamura 2018;Ye et al 2018;Pan et al 2019). In spite of the empirical success of low-rank matrix and tensor approaches, theoretical studies for learning efficiency are still limited.…”

Section: Introductionmentioning

confidence: 99%

Compact Autoregressive Network

Wang

Huang

Zhao

et al. 2020

AAAI

View full text Add to dashboard Cite

Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the massive amount of parameters in the network leads to expensive computational cost and low learning efficiency. The problem can be alleviated slightly by introducing one more narrow hidden layer to the network, but the sample size required to achieve a certain training error is still substantial. To address this challenge, we rearrange the weight matrices of a linear autoregressive network into a tensor form, and then make use of Tucker decomposition to represent low-rank structures. This leads to a novel compact autoregressive network, called Tucker AutoRegressive (TAR) net. Interestingly, the TAR net can be applied to sequences with long-range dependence since the dimension along the sequential order is reduced. Theoretical studies show that the TAR net improves the learning efficiency, and requires much fewer samples for model training. Experiments on synthetic and real-world datasets demonstrate the promising performance of the proposed compact network.

show abstract

Skeleton‐Guided Action Recognition with Multistream 3D Convolutional Neural Network for Elderly‐Care Robot

Zhang,

Zhou

2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

With the arrival of a global aging society, elderly‐care robots are becoming more and more attractive and can provide better caring services through action recognition. This article presents a skeleton‐guided action recognition framework with multistream 3D convolutional neural network. Two parallel dual‐stream lightweight networks are proposed to enhance the feature extraction ability of human action and meanwhile reduce computation. Two different modes of skeleton input video are constructed to improve the recognition accuracy by decision fusion. The backbone networks adopt Resnet‐18, the feature fusion layer and sliding window mechanism are both designed, and two cross‐entropy losses are used to supervise their training. A dataset (named elder care action recognition (EC‐AR)) with different categories of action is built. The experimental results on HMDB‐51 and EC‐AR datasets both demonstrate that the proposed framework outperforms the existing methods. The developed method is also applied to a prototype of elderly‐care robots, and the test results in home scenarios show that it still has high recognition accuracy and good real‐time performance.

show abstract

Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition

Cited by 82 publications

References 28 publications

Heuristic rank selection with progressively searching tensor ring network

Heuristic rank selection with progressively searching tensor ring network

Compact Autoregressive Network

Skeleton‐Guided Action Recognition with Multistream 3D Convolutional Neural Network for Elderly‐Care Robot

Contact Info

Product

Resources

About