(2+1)D Distilled ShuffleNet: A Lightweight Unsupervised Distillation Network for Human Action Recognition

Vu, Duc-Quang; Le, Ngan; Wang, Jia-Ching

doi:10.1109/icpr56361.2022.9956634

Cited by 12 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further verify the validity of this article, we produced Tables 3 – 6 . we compared the algorithms with classical ones (Vgg16 ( Sitaula & Hossain, 2021 ), Resnet50 ( Wen, Li & Gao, 2020 ), Densenet121 ( Zhang et al, 2019 ), ResNext_34×4d-50 ( Zhou, Zhao & Wu, 2021 ), ShuffleNetV2 ( Vu, Le & Wang, 2022 ) and Mobilenetv3_ large ( Chen et al, 2022 )), advanced algorithms (Conformer ( Guo et al, 2021 ), RepMLP_B224 ( Ding et al, 2021a ), RepVGG_D2se ( Ding et al, 2021b ), ConvMixer ( Ng et al, 2022 ), and Hornet-L-GF ( Rao et al, 2022 )), transformer algorithms (DeiT-base ( Touvron et al, 2021 ), PoolFormer_M48 ( Yu et al, 2022 ), SVT_large ( Fan et al, 2022 ), EfficientFormer-l7 ( Li et al, 2022b ) and MViTv2_large ( Li et al, 2022a )) and similar algorithms for experimental comparison.…”

Section: Methodsmentioning

confidence: 99%

Eye Disease Net: an algorithmic model for rapid diagnosis of diseases

Liu,

Qin,

Jiang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

With the development of science and technology and the improvement of the quality of life, ophthalmic diseases have become one of the major disorders that affect the quality of life of people. In view of this, we propose a new method of ophthalmic disease classification, ED-Net (Eye Disease Classification Net), which is composed of the ED_Resnet model and ED_Xception model, and we compare our ED-Net method with classical classification algorithms, transformer algorithm, more advanced image classification algorithms and ophthalmic disease classification algorithms. We propose the ED_Resnet module and ED_Xception module and reconstruct these two modules into a new image classification algorithm ED-Net, and compared them with classical classification algorithms, transformer algorithms, more advanced image classification algorithms and eye disease classification algorithms.

show abstract

Section: Methodsmentioning

confidence: 99%

Eye Disease Net: an algorithmic model for rapid diagnosis of diseases

Liu,

Qin,

Jiang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Further, they fixed the encoder as a teacher model in the last epoch to guide the training of the encoder from the current epoch in transfer learning phase. In the work presented in [36], Vu et al proposed an unsupervised distillation learning framework called (2 + 1)D Distilled ShuffleNet to train a lightweight model for human action recognition task. By leveraging the distillation technique, they developed (2+1)D Distilled ShuffleNet as an unsupervised approach, which did not require labeled data for training.…”

Section: Related Workmentioning

confidence: 99%

“…The SKD-SRL [33] method attains the lowest accuracy of 29.8% amongst all the comparative knowledge distillation-based methods for the HMDB51 dataset. The rest of comparative methods that include STDDCN [29], Prob-Distill [30], MHSA-KD [31], TY [34], (2+1)D Distilled ShuffleNet [36], and Self-Distillation (PPTK) [35] achieve accuracies of 66.8%, 72.2%, 57.8%, 32.8%, 59.9%, and 76.5%, respectively, for the HMDB51 dataset. Similarly, for the UCF101 dataset in Table 13, our proposed framework outperforms other comparative knowledge distillation-based methods by obtaining the best accuracies of 97.3% followed by the D3D [32] method which attains the second-best accuracy of 97.0%.…”

Section: 3mentioning

confidence: 99%

“…The TY [34] method achieves the lowest accuracy of 71.1% amongst all the comparative methods for the UCF101 dataset. The rest of comparative methods that include STDDCN [29], Prob-Distill [30], SKD-SRL [33], Progressive KD [37], (2+1)D Distilled ShuffleNet [36], Self-Distillation (PPTK) [35], and ConDi-SR [38] achieve accuracies of 93.7%, 95.7%, 71.9%, 88.8%, 86.4%, 94.6%, and 91.2%, respectively, for the UCF101 dataset. We also evaluate the performance generalization of our proposed method in comparison with the state-of-the-art knowledge-distillation based methods using confidence interval (with a confidence level of 95%) on HMDB51 and UCF101 datasets.…”

Section: 3mentioning

confidence: 99%

See 1 more Smart Citation

A 3DCNN-Based Knowledge Distillation Framework for Human Activity Recognition

Ullah

Munir

2023

J. Imaging

View full text Add to dashboard Cite

Human action recognition has been actively explored over the past two decades to further advancements in video analytics domain. Numerous research studies have been conducted to investigate the complex sequential patterns of human actions in video streams. In this paper, we propose a knowledge distillation framework, which distills spatio-temporal knowledge from a large teacher model to a lightweight student model using an offline knowledge distillation technique. The proposed offline knowledge distillation framework takes two models: a large pre-trained 3DCNN (three-dimensional convolutional neural network) teacher model and a lightweight 3DCNN student model (i.e., the teacher model is pre-trained on the same dataset on which the student model is to be trained on). During offline knowledge distillation training, the distillation algorithm trains only the student model to help enable the student model to achieve the same level of prediction accuracy as the teacher model. To evaluate the performance of the proposed method, we conduct extensive experiments on four benchmark human action datasets. The obtained quantitative results verify the efficiency and robustness of the proposed method over the state-of-the-art human action recognition methods by obtaining up to 35% improvement in accuracy over existing methods. Furthermore, we evaluate the inference time of the proposed method and compare the obtained results with the inference time of the state-of-the-art methods. Experimental results reveal that the proposed method attains an improvement of up to 50× in terms of frames per seconds (FPS) over the state-of-the-art methods. The short inference time and high accuracy make our proposed framework suitable for human activity recognition in real-time applications.

show abstract

“…Experimental results show that ShuffleNetV2 achieves a 63% speed improvement compared to ShuffleNetV1. In the latest research on ShuffleNet, a lightweight network called (2+1) D Distilled ShuffleNet is proposed in [92] for human action recognition using an unsupervised distillation learning paradigm. This network extracts knowledge from the teacher network through distillation techniques without the need for labeled data.…”

mentioning

confidence: 99%

A Review of Neural Network Lightweighting Techniques

Gong,

Zhang,

Yang

et al. 2024

Innov. technol. adv.

View full text Add to dashboard Cite

The application of portable devices based on deep learning has become increasingly widespread, which has made the deployment of complex neural networks on embedded devices a hot research topic. Neural network lightweighting is one of the key technologies for applying neural networks to embedded devices. This paper elaborates and analyzes neural network lightweighting techniques from two aspects: model pruning and network structure design. For model pruning, a comparison of methods from different periods is conducted, highlighting their advantages and limitations. Regarding network structure design, the principles of four classical lightweight network designs are described from a mathematical perspective, and the latest optimization methods for these networks are reviewed. Finally, potential research directions for lightweight neural network pruning and structure design optimization are discussed.

show abstract

(2+1)D Distilled ShuffleNet: A Lightweight Unsupervised Distillation Network for Human Action Recognition

Cited by 12 publications

References 25 publications

Eye Disease Net: an algorithmic model for rapid diagnosis of diseases

Eye Disease Net: an algorithmic model for rapid diagnosis of diseases

A 3DCNN-Based Knowledge Distillation Framework for Human Activity Recognition

A Review of Neural Network Lightweighting Techniques

Contact Info

Product

Resources

About