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

Duc Quang Vu, Ngan T.H. Le, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

9 引文 斯高帕斯(Scopus)

摘要

While most existing deep neural networks (DNN) architectures are proposed for increasing performance, they also raise overall model complexity. However, practical applications require lightweight DNN models, that are able to run real-time in edge computing devices. In this work, we present a simple and elegant unsupervised distillation learning paradigm to train a lightweight network to human action recognition called (2+1)D Distilled ShuffleNet. Leveraging the distilling technique, the proposed method allows us to create a lightweight DNN model that achieves high accuracy and real-time speed. Our lightweight (2+1)D Distilled ShuffleNet is designed as an unsupervised paradigm; it does not require labelled data during distilling knowledge from the teacher to the student. Furthermore, to help the student be more "intelligent", we propose to distill the knowledge from two different teachers, i.e., 2D teacher and 3D teacher. The experimental results have shown that our lightweight (2+1)D Distilled ShuffleNet outperforms other state-of-the-art distillation networks with 86.4% and 59.9% top-1 accuracy on UCF101 and HMDB51 datasets, respectively, whereas the inference running time is at 47.16 FPS on CPU with only 17.1M parameters and 12.07 GFLOPs.

原文???core.languages.en_GB???
主出版物標題2022 26th International Conference on Pattern Recognition, ICPR 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面3197-3203
頁數7
ISBN(電子)9781665490627
DOIs
出版狀態已出版 - 2022
事件26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canada
持續時間: 21 8月 202225 8月 2022

出版系列

名字Proceedings - International Conference on Pattern Recognition
2022-August
ISSN(列印)1051-4651

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???26th International Conference on Pattern Recognition, ICPR 2022
國家/地區Canada
城市Montreal
期間21/08/2225/08/22

指紋

深入研究「(2+1)D Distilled ShuffleNet: A Lightweight Unsupervised Distillation Network for Human Action Recognition」主題。共同形成了獨特的指紋。

引用此