Nuo Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nuo Wei has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Lei Lyu
Shandong Normal University
1 shared publication - Minglei Shu
The College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China
1 shared publication - Tianlei Gao
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong, China
1 shared publication - Xiaoyun Xie
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
1 shared publication - Yushui Geng
Qilu University of Technology (Shandong Academy of Sciences)
1 shared publication
Latest Publications
- Open Access
Category Name Expansion and an Enhanced Multimodal Fusion Framework for Few-Shot Learning
With the advancement of image processing techniques, few-shot learning (FSL) has gradually become a key approach to addressing the problem of data scarcity. However, existing FSL methods often rely on unimodal information under limited sample conditions, making it difficult to capture fine-grained differences between categories. To address this issue, we propose a multimodal few-shot learning method based on category name expansion and image feature enhancement. By integrating the expanded category text with image features, the proposed method enriches the semantic representation of categories and enhances the model’s sensitivity to detailed features. To further improve the quality of cross-modal information transfer, we introduce a cross-modal residual connection strategy that aligns features across layers through progressive fusion. This approach enables the fused representations to maximize mutual information while reducing redundancy, effectively alleviating the information bottleneck caused by uneven entropy distribution between modalities and enhancing the model’s generalization ability. Experimental results demonstrate that our method achieves superior performance on both natural image datasets (CIFAR-FS and FC100) and a medical image dataset.
Open AccessCategory Name Expansion and an Enhanced Multimodal Fusion Framework for Few-Shot Learning
With the advancement of image processing techniques, few-shot learning (FSL) has gradually become a key approach to addressing the problem of data scarcity. However, existing FSL methods often rely on unimodal information under limited sample conditions, making it difficult to capture fine-grained differences between categories. To address this issue, we propose a multimodal few-shot learning method based on category name expansion and image feature enhancement. By integrating the expanded category text with image features, the proposed method enriches the semantic representation of categories and enhances the model’s sensitivity to detailed features. To further improve the quality of cross-modal information transfer, we introduce a cross-modal residual connection strategy that aligns features across layers through progressive fusion. This approach enables the fused representations to maximize mutual information while reducing redundancy, effectively alleviating the information bottleneck caused by uneven entropy distribution between modalities and enhancing the model’s generalization ability. Experimental results demonstrate that our method achieves superior performance on both natural image datasets (CIFAR-FS and FC100) and a medical image dataset.