The Positive Effect of Attention Module in Few-Shot Learning for Plant Disease Recognition

Hong Lin, Rita Tse, Su Kit Tang, Zhen Ping Qiang, Giovanni Pau

研究成果: Conference contribution同行評審

7 引文 斯高帕斯(Scopus)

摘要

Few-shot learning is good solution for plant disease recognition which can generalize to new categories by using few samples. However, the features extracted from few shots are limited. Attention is a technique for focusing on the significant features which can help to obtain better feature representation. In this work, we use a naive metric-based few-shot learning network as the baseline method, exploit the effect of different kinds of attention module: channel attention, spatial attention and hybrid attention. In experiments, we choose the representative modules of each attention category to show their effects in few-shot learning paradigm: SE, ASPP, CBAM and Triplet Attention. We conduct experiments with two data settings of PlantVillage, and illustrate the usage these attention modules in Residual Networks. The results indicate that the different attention modules can improve recognition accuracy to varying degrees. Attention can be used as effective improvement of feature representation under few-shot condition.

原文English
主出版物標題2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面114-120
頁數7
ISBN(電子)9781665499163
DOIs
出版狀態Published - 2022
事件5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022 - Chengdu, China
持續時間: 19 8月 202221 8月 2022

出版系列

名字2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

Conference

Conference5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022
國家/地區China
城市Chengdu
期間19/08/2221/08/22

指紋

深入研究「The Positive Effect of Attention Module in Few-Shot Learning for Plant Disease Recognition」主題。共同形成了獨特的指紋。

引用此