MIA-Mind: A Multidimensional Interactive Attention Mechanism Based on MindSpore
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908339918602240 |
|---|---|
| author | Qin, Zhenkai Liang, Jiaquan Fang, Qiao |
| author_facet | Qin, Zhenkai Liang, Jiaquan Fang, Qiao |
| contents | Attention mechanisms have significantly advanced deep learning by enhancing feature representation through selective focus. However, existing approaches often independently model channel importance and spatial saliency, overlooking their inherent interdependence and limiting their effectiveness. To address this limitation, we propose MIA-Mind, a lightweight and modular Multidimensional Interactive Attention Mechanism, built upon the MindSpore framework. MIA-Mind jointly models spatial and channel features through a unified cross-attentive fusion strategy, enabling fine-grained feature recalibration with minimal computational overhead. Extensive experiments are conducted on three representative datasets: on CIFAR-10, MIA-Mind achieves an accuracy of 82.9\%; on ISBI2012, it achieves an accuracy of 78.7\%; and on CIC-IDS2017, it achieves an accuracy of 91.9\%. These results validate the versatility, lightweight design, and generalization ability of MIA-Mind across heterogeneous tasks. Future work will explore the extension of MIA-Mind to large-scale datasets, the development of ada,ptive attention fusion strategies, and distributed deployment to further enhance scalability and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19080 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIA-Mind: A Multidimensional Interactive Attention Mechanism Based on MindSpore Qin, Zhenkai Liang, Jiaquan Fang, Qiao Computer Vision and Pattern Recognition Artificial Intelligence Attention mechanisms have significantly advanced deep learning by enhancing feature representation through selective focus. However, existing approaches often independently model channel importance and spatial saliency, overlooking their inherent interdependence and limiting their effectiveness. To address this limitation, we propose MIA-Mind, a lightweight and modular Multidimensional Interactive Attention Mechanism, built upon the MindSpore framework. MIA-Mind jointly models spatial and channel features through a unified cross-attentive fusion strategy, enabling fine-grained feature recalibration with minimal computational overhead. Extensive experiments are conducted on three representative datasets: on CIFAR-10, MIA-Mind achieves an accuracy of 82.9\%; on ISBI2012, it achieves an accuracy of 78.7\%; and on CIC-IDS2017, it achieves an accuracy of 91.9\%. These results validate the versatility, lightweight design, and generalization ability of MIA-Mind across heterogeneous tasks. Future work will explore the extension of MIA-Mind to large-scale datasets, the development of ada,ptive attention fusion strategies, and distributed deployment to further enhance scalability and robustness. |
| title | MIA-Mind: A Multidimensional Interactive Attention Mechanism Based on MindSpore |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.19080 |