返回
FMAS-TransUNet: A deep learning approach for complex microstructure agglomeration recognition
DOI:10.1016/j.neucom.2026.133632.png)
摘要
En 中文
• FMAS-TransUNet将Swin Transformer集成到U-Net中以增强特征提取。• 双层上采样和特征重校准模块提升识别精度。• 在专用SEM纤维母粒数据集上达到95.65%的精度。• 提供用于可靠团聚物识别的自动化解决方案。
Keyword:
FMAS-TransUNet
Swin Transformer
U-Net
feature extraction
agglomeration recognition
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Enhanced YOLOv8-Based Model with Context Enrichment Module for Crowd Counting in Complex Drone Imagery基于上下文增强模块的改进YOLOv8模型,用于复杂无人机图像中的 crowd counting
Detection of Cardiovascular Diseases in ECG Images Using Machine Learning and Deep Learning Methods基于机器学习和深度学习方法的心电图像心血管疾病检测
Deep-learning image enhancement and fibre segmentation from time-resolved computed tomography of fibre-reinforced composites基于光纤增强复合材料的时间分辨计算机断层扫描的深度学习图像增强与纤维分割

