1 中国科学院光电技术研究所,四川 成都 610209
2 中国科学院大学电子电气与通信工程学院,北京 100049
To improve the performance of few-shot classification, we present a general and flexible method named Multi-Scale Attention and Domain Adaptation Network (MADA). Firstly, to tackle the problem of limited samples, a masked autoencoder is used to image augmentation. Moreover, it can be inserted as a plug-and-play module into a few-shot classification. Secondly, the multi-scale attention module can adapt feature vectors extracted by embedding function to the current classification task. Multi-scale attention machine strengthens the discriminative image region by focusing on relating samples in both base class and novel class, which makes prototypes more accurate. In addition, the embedding function pays attention to the task-specific feature. Thirdly, the domain adaptation module is used to address the domain shift caused by the difference in data distributions of the two domains. The domain adaptation module consists of the metric module and the margin loss function. The margin loss pushes different prototypes away from each other in the feature space. Sufficient margin space in feature space improves the generalization performance of the method. The experimental results show the classification accuracy of the proposed method is 67.45% for 5-way 1-shot and 82.77% for 5-way 5-shot on the miniImageNet dataset. The classification accuracy is 70.57% for 5-way 1-shot and 85.10% for 5-way 5-shot on the tieredImageNet dataset. The classification accuracy of our method is better than most previous methods. After dimension reduction and visualization of features by using t-SNE, it can be concluded that domain drift is alleviated, and prototypes are more accurate. The multi-scale attention module enhanced feature representations are more discriminative for the target classification task. In addition, the domain adaptation module improves the generalization ability of the model.
小样本图像识别 注意力机制 领域自适应 相似性度量 few-shot image classification attention mechanism domain adaptation similarity metric
1 天津理工大学 电子信息工程学院, 天津 300384
2 天津理工大学材料物理研究所 显示材料与光电器件教育部重点实验室, 天津 300384
用ZnS量子点与poly-4-vinyl-phenol (PVP)复合,通过简单的旋涂法制备了结构为ITO/ZnS∶PVP/Al的一次写入多次读取(WORM)的有机双稳态器件。器件起始状态为OFF态,通过正向电压的作用,器件由OFF态转变为ON态,并且在正向或反向电压的作用下,器件始终保持在ON态,表现出良好的一次写入多次读取的存储特性。与不含ZnS量子点的器件相比,含有ZnS量子点的器件表现出明显的双稳态特性,其电流开关比达到104,这说明ZnS量子点在器件中起到存储介质的作用。通过对器件电流-电压(I-V)特性的测试,详细讨论了器件的双稳态特性以及载流子传输机制,并且用不同的传导理论模型分析了器件在ON态和OFF态的电流传导机制。器件I-t曲线表明器件在大气环境中具有良好的永久保持特性。
有机双稳态器件 ZnS量子点 电荷传输机制 聚乙烯基吡咯烷酮 OBD ZnS quantum dots charge-transport mechanism poly-4-vinyl-phenol