TANet: A Tiny Plankton Classification Network for Mobile Devices
Joint Authors
Li, Xiu
Long, Rujiao
Yan, Jiangpeng
Jin, Kun
Lee, Jihae
Source
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-8, 8 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-04-03
Country of Publication
Egypt
No. of Pages
8
Main Subjects
Telecommunications Engineering
Abstract EN
This paper is devoted to a lightweight convolutional neural network based on the attention mechanism called the tiny attention network (TANet).
The TANet consists of three main parts termed as a reduction module, self-attention operation, and group convolution.
The reduction module alleviates information loss caused by the pooling operation.
The new parameter-free self-attention operation makes the model to focus on learning important parts of images.
The group convolution achieves model compression and multibranch fusion.
Using the main parts, the proposed network enables efficient plankton classification on mobile devices.
The performance of the proposed network is evaluated on the Plankton dataset collected by Oregon State University’s Hatfield Marine Science Center.
The results show that TANet outperforms other deep models in speed (31.8 ms per image), size (648 kB, the size of the hard disk space occupied by the model), and accuracy (Top-1 76.5%, Top-5 96.3%).
American Psychological Association (APA)
Li, Xiu& Long, Rujiao& Yan, Jiangpeng& Jin, Kun& Lee, Jihae. 2019. TANet: A Tiny Plankton Classification Network for Mobile Devices. Mobile Information Systems،Vol. 2019, no. 2019, pp.1-8.
https://search.emarefa.net/detail/BIM-1193852
Modern Language Association (MLA)
Li, Xiu…[et al.]. TANet: A Tiny Plankton Classification Network for Mobile Devices. Mobile Information Systems No. 2019 (2019), pp.1-8.
https://search.emarefa.net/detail/BIM-1193852
American Medical Association (AMA)
Li, Xiu& Long, Rujiao& Yan, Jiangpeng& Jin, Kun& Lee, Jihae. TANet: A Tiny Plankton Classification Network for Mobile Devices. Mobile Information Systems. 2019. Vol. 2019, no. 2019, pp.1-8.
https://search.emarefa.net/detail/BIM-1193852
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1193852