Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification
Abstract Graph neural networks have excellent performance and powerful representation capabilities, and have been widely used to handle Few-shot image classification problems. The feature extraction module of graph neural networks has always been designed as a fixed convolutional neural network (CNN...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-85467-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544720870801408 |
|---|---|
| author | Yongmin Liu Fengjiao Xiao Xinying Zheng Weihao Deng Haizhi Ma Xinyao Su Lei Wu |
| author_facet | Yongmin Liu Fengjiao Xiao Xinying Zheng Weihao Deng Haizhi Ma Xinyao Su Lei Wu |
| author_sort | Yongmin Liu |
| collection | DOAJ |
| description | Abstract Graph neural networks have excellent performance and powerful representation capabilities, and have been widely used to handle Few-shot image classification problems. The feature extraction module of graph neural networks has always been designed as a fixed convolutional neural network (CNN), but due to the intrinsic properties of convolution operations, its receiving domain is limited. This method has limitations in capturing global feature information and easily ignores key feature information of the image. In order to extract comprehensive and critical feature information, a new CA-MFE algorithm is proposed. The algorithm first utilizes different convolution kernels in CNN to extract multi-scale local feature information, and then based on the global feature extraction ability of attention mechanism, parallel processing of channel and spatial attention mechanism is used to extract multidimensional global feature information. This paper provides a comprehensive performance evaluation of the new model on both mini-ImageNet and tiered ImageNet datasets. Compared with the benchmark model, the classification accuracy has increased by 1.07% and 1.33% respectively; In the 5-way 5-shot task, the classification accuracy of the mini-ImageNet dataset was improved by 11.41%, 7.42%, and 5.38% compared to GNN, TPN, and dynamic models, respectively. The experimental results show that compared with the benchmark model and several representative Few-shot classification algorithm models, the new CA-MFE model has significant superior performance in processing few-shot classification data. |
| format | Article |
| id | doaj-art-1f6c86952a9244e894603828ac842451 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1f6c86952a9244e894603828ac8424512025-01-12T12:18:20ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-025-85467-4Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classificationYongmin Liu0Fengjiao Xiao1Xinying Zheng2Weihao Deng3Haizhi Ma4Xinyao Su5Lei Wu6School of Electronic Information and Physics, Central South University of Forestry Science and TechnologySchool of Electronic Information and Physics, Central South University of Forestry Science and TechnologyBusiness School of Hunan Normal UniversitySchool of Electronic Information and Physics, Central South University of Forestry Science and TechnologySchool of Electronic Information and Physics, Central South University of Forestry Science and TechnologyBangor College China, Central South University of Forestry and TechnologySchool of Electronic Information and Physics, Central South University of Forestry Science and TechnologyAbstract Graph neural networks have excellent performance and powerful representation capabilities, and have been widely used to handle Few-shot image classification problems. The feature extraction module of graph neural networks has always been designed as a fixed convolutional neural network (CNN), but due to the intrinsic properties of convolution operations, its receiving domain is limited. This method has limitations in capturing global feature information and easily ignores key feature information of the image. In order to extract comprehensive and critical feature information, a new CA-MFE algorithm is proposed. The algorithm first utilizes different convolution kernels in CNN to extract multi-scale local feature information, and then based on the global feature extraction ability of attention mechanism, parallel processing of channel and spatial attention mechanism is used to extract multidimensional global feature information. This paper provides a comprehensive performance evaluation of the new model on both mini-ImageNet and tiered ImageNet datasets. Compared with the benchmark model, the classification accuracy has increased by 1.07% and 1.33% respectively; In the 5-way 5-shot task, the classification accuracy of the mini-ImageNet dataset was improved by 11.41%, 7.42%, and 5.38% compared to GNN, TPN, and dynamic models, respectively. The experimental results show that compared with the benchmark model and several representative Few-shot classification algorithm models, the new CA-MFE model has significant superior performance in processing few-shot classification data.https://doi.org/10.1038/s41598-025-85467-4 |
| spellingShingle | Yongmin Liu Fengjiao Xiao Xinying Zheng Weihao Deng Haizhi Ma Xinyao Su Lei Wu Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification Scientific Reports |
| title | Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification |
| title_full | Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification |
| title_fullStr | Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification |
| title_full_unstemmed | Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification |
| title_short | Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification |
| title_sort | integrating deformable cnn and attention mechanism into multi scale graph neural network for few shot image classification |
| url | https://doi.org/10.1038/s41598-025-85467-4 |
| work_keys_str_mv | AT yongminliu integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification AT fengjiaoxiao integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification AT xinyingzheng integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification AT weihaodeng integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification AT haizhima integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification AT xinyaosu integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification AT leiwu integratingdeformablecnnandattentionmechanismintomultiscalegraphneuralnetworkforfewshotimageclassification |