WEKO3
アイテム
Data-Driven Channel Pruning towards Local Binary Convolution Inverse Bottleneck Network Based on Squeeze-and-Excitation Optimization Weights
https://tokushima-u.repo.nii.ac.jp/records/2009423
https://tokushima-u.repo.nii.ac.jp/records/2009423f62711da-f526-4f61-ac3f-85e3a0ff4350
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
electronics_10_11_1329.pdf (1.89 MB)
|
.png)
|
| Item type | 文献 / Documents(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2021-12-20 | |||||||||||||
| アクセス権 | ||||||||||||||
| アクセス権 | open access | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| 出版社版DOI | ||||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.3390/electronics10111329 | |||||||||||||
| 言語 | ja | |||||||||||||
| 関連名称 | 10.3390/electronics10111329 | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | VoR | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Data-Driven Channel Pruning towards Local Binary Convolution Inverse Bottleneck Network Based on Squeeze-and-Excitation Optimization Weights | |||||||||||||
| 言語 | en | |||||||||||||
| 著者 |
Feng, Duo
× Feng, Duo
× 任, 福継
WEKO
401
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | This paper proposed a model pruning method based on local binary convolution (LBC) and squeeze-and-excitation (SE) optimization weights. We first proposed an efficient deep separation convolution model based on the LBC kernel. By expanding the number of LBC kernels in the model, we have trained a larger model with better results, but more parameters and slower calculation speed. Then, we extract the SE optimization weight value of each SE module according to the data samples and score the LBC kernel accordingly. Based on the score of each LBC kernel corresponding to the convolution channel, we performed channel-based model pruning, which greatly reduced the number of model parameters and accelerated the calculation speed. The model pruning method proposed in this paper is verified in the image classification database. Experiments show that, in the model using the LBC kernel, as the number of LBC kernels increases, the recognition accuracy will increase. At the same time, the experiment also proved that the recognition accuracy is maintained at a similar level in the small parameter model after channel-based model pruning by the SE optimization weight value. | |||||||||||||
| 言語 | en | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | model pruning | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | local binary convolution | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | squeeze-and-excitation optimization | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | image classification | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | depthwise convolution | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | mobile inverse bottleneck | |||||||||||||
| 書誌情報 |
en : Electronics 巻 10, 号 11, p. 1329, 発行日 2021-06-01 |
|||||||||||||
| 収録物ID | ||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||
| 収録物識別子 | 20799292 | |||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | MDPI | |||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | ||||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). | |||||||||||||
| EID | ||||||||||||||
| 識別子 | 375989 | |||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
