Efficient Still Image Action Recognition by the Combination of Ensemble Learning and Knowledge Distillation

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Saleknia Amir Hossein; Ayatollahi Ahmad

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: INTERNATIONAL CONFERENCE ON WEB RESEARCH
Year:2023 | Issue:9

Download Full-Text

View:

Download:

Information Seminar Paper

Title

Efficient Still Image Action Recognition by the Combination of Ensemble Learning and Knowledge Distillation

Author(s)

Saleknia Amir Hossein | Ayatollahi Ahmad

Keywords

Action Recognition

Still Image

Ensemble Learning

Knowledge Distillation

Abstract

Deep neural networks have demonstrated outstanding performance in various image classification tasks, yet Action Recognition from Still Images is challenging due to lack of temporal information, scarcity of data, large intra-class variations, and high similarity between different actions. To overcome these problems, Ensemble Learning appears to be one of the most straightforward approaches. However, ensemble models are computationally inefficient, especially when they are based on a combination of deep neural networks. In order to deal with this issue, we first construct an ensemble model by combining three separately trained deep convolutional neural networks. Then by utilizing this ensemble model as a teacher we train a light-weight student network based on the new Knowledge Distillation framework. This light-weight model achieves 94. 32% MAP on the Stanford40 dataset, demonstrating its superiority over many existing methods despite its high computational efficiency.

Cites

No record.

References

No record.

Cite

APA: Copy

Saleknia, Amir Hossein, & Ayatollahi, Ahmad. (). . . SID. https://sid.ir/paper/1046861/en

Vancouver: Copy

Saleknia Amir Hossein, Ayatollahi Ahmad. . . Available from: https://sid.ir/paper/1046861/en

IEEE: Copy

Amir Hossein Saleknia, and Ahmad Ayatollahi, “,” presented at the . , [Online]. Available: https://sid.ir/paper/1046861/en

Related Journal Papers