Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification
This article has been retracted, and the retraction notice can be found here: http://dx.doi.org/10.4108/eai.8-4-2022.173792. Attention mechanism is widely used in fine-grained image classification. Most of the existing methods are to construct an attention weight map for simple weighted processing...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
European Alliance for Innovation (EAI)
2022-01-01
|
| Series: | EAI Endorsed Transactions on Scalable Information Systems |
| Subjects: | |
| Online Access: | https://publications.eai.eu/index.php/sis/article/view/338 |
| _version_ | 1798027620698292224 |
|---|---|
| author | Rui Yang Dahai Li |
| author_facet | Rui Yang Dahai Li |
| author_sort | Rui Yang |
| collection | DOAJ |
| description |
This article has been retracted, and the retraction notice can be found here: http://dx.doi.org/10.4108/eai.8-4-2022.173792.
Attention mechanism is widely used in fine-grained image classification. Most of the existing methods are to construct an attention weight map for simple weighted processing of features, but there are problems of low efficiency and slow convergence. Therefore, this paper proposes a multi-channel attention fusion mechanism based on the deep neural network model which can be trained end-to-end. Firstly, the different regions corresponding to the object are described by the attention diagram. Then the corresponding higher order statistical characteristics are extracted to obtain the corresponding representation. In many standard fine-grained image classification test tasks, the proposed method works best compared with other methods.
|
| first_indexed | 2024-04-11T18:54:19Z |
| format | Article |
| id | doaj.art-9d16dc66726f4ab49398bc54d9bbac05 |
| institution | Directory Open Access Journal |
| issn | 2032-9407 |
| language | English |
| last_indexed | 2024-04-11T18:54:19Z |
| publishDate | 2022-01-01 |
| publisher | European Alliance for Innovation (EAI) |
| record_format | Article |
| series | EAI Endorsed Transactions on Scalable Information Systems |
| spelling | doaj.art-9d16dc66726f4ab49398bc54d9bbac052022-12-22T04:08:15ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Scalable Information Systems2032-94072022-01-019410.4108/eai.27-1-2022.173165Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classificationRui Yang0Dahai Li1Zhengzhou University of Science and Technology Henan Intelligent Information Processing and Control Engineering Technology Research Center This article has been retracted, and the retraction notice can be found here: http://dx.doi.org/10.4108/eai.8-4-2022.173792. Attention mechanism is widely used in fine-grained image classification. Most of the existing methods are to construct an attention weight map for simple weighted processing of features, but there are problems of low efficiency and slow convergence. Therefore, this paper proposes a multi-channel attention fusion mechanism based on the deep neural network model which can be trained end-to-end. Firstly, the different regions corresponding to the object are described by the attention diagram. Then the corresponding higher order statistical characteristics are extracted to obtain the corresponding representation. In many standard fine-grained image classification test tasks, the proposed method works best compared with other methods. https://publications.eai.eu/index.php/sis/article/view/338Multichannel attention mechanismresult fusionfine-grained image classificationgate recurrent unit memory network |
| spellingShingle | Rui Yang Dahai Li Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification EAI Endorsed Transactions on Scalable Information Systems Multichannel attention mechanism result fusion fine-grained image classification gate recurrent unit memory network |
| title | Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification |
| title_full | Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification |
| title_fullStr | Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification |
| title_full_unstemmed | Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification |
| title_short | Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification |
| title_sort | multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine grained image classification |
| topic | Multichannel attention mechanism result fusion fine-grained image classification gate recurrent unit memory network |
| url | https://publications.eai.eu/index.php/sis/article/view/338 |
| work_keys_str_mv | AT ruiyang multichannelattentionmechanismsfusionbasedongaterecurrentunitmemorynetworkforfinegrainedimageclassification AT dahaili multichannelattentionmechanismsfusionbasedongaterecurrentunitmemorynetworkforfinegrainedimageclassification |