Since the emergence of research on improving the length extrapolation capabilities of large models in 2021, some studies have made modifications to the scaling factor in the scaled dot-product attention mechanism as p...
详细信息
Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts...
详细信息
In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge wi...
详细信息
Complex networks enable to represent and characterize the interactions between entities in various complex systems which widely exist in the real world and usually generate vast amounts of data about all the elements,...
详细信息
Multi-modality image fusion aims at fusing modality-specific (complementarity) and modality-shared (correlation) information from multiple source images. To tackle the problem of the neglect of inter-modal information...
详细信息
Histological image classification plays a crucial role in cancer diagnosis. However, the acquisition of well-labeled histological images is prohibitively expensive, and obtaining rare abnormal samples is challenging. ...
Histological image classification plays a crucial role in cancer diagnosis. However, the acquisition of well-labeled histological images is prohibitively expensive, and obtaining rare abnormal samples is challenging. Therefore, applying few-shot learning methods to histological image classification tasks holds significant clinical value. Nevertheless, existing research predom-inantly relies on coarse-grained image classification approaches based on natural image datasets, which struggle to address the fine-grained challenges encountered in histological image classification, such as intra-class diversity and inter-class similarity. To tackle this issue, this study proposes a novel few-shot fine-grained classification method for histological images, named “Category-Aware Feature Map Reconstruction Network.” This method employs channel weights to localize the differences between inter-class and intra-class regions, composed of intra-class channel weights and inter-class channel weights, collectively referred to as category-aware weights. Specifically, intra-class channel weights indicate the matching degree of salient regions within the support set of a particular class, while inter-class channel weights represent the degree of containing distinct information between classes. The category-aware weights are utilized to transform the support feature maps and query feature maps, generating feature maps that capture differentiating details between categories. Finally, the distance between the transformed query feature map and support feature map is calculated to achieve probabilistic predictions for the categories. On a histological few-shot dataset, this method achieves an accuracy of 90.23% using ResNet-12 as the feature extractor, surpassing the baseline model by 5.24% and outperforming other few-shot methods by at least 10% in the 5-way 10-shot experimental setting. The proposed method exhibits exceptional performance on histological image few-shot datasets, playing a
Pseudo-Boolean optimization (PBO) is usually used to model combinatorial optimization problems, especially for some real-world applications. Despite its significant importance in both theory and applications, there ar...
详细信息
Named entity recognition (NER) in electronic medical records (EMRs) is critical for identifying medical entities, constructing medical knowledge graphs, and supporting clinical decision-making. However, the scarcity o...
详细信息
ISBN:
(数字)9798350386226
ISBN:
(纸本)9798350386233
Named entity recognition (NER) in electronic medical records (EMRs) is critical for identifying medical entities, constructing medical knowledge graphs, and supporting clinical decision-making. However, the scarcity of EMR datasets and the challenges posed by the complexity of Chinese medical texts hinder progress in this area. To address these issues, we introduce CMR-NER, a nested named entity recognition model that enhances entity prediction by integrating multiple features and considering a global view of entity boundaries. Leveraging the robust generalization capabilities of the large language model, CMR-NER involves collaboration with medical experts to ensure accuracy and reduce annotation costs. Additionally, we present HF-NER, a high-quality dataset specifically curated for Chinese EMR entity recognition focusing on heart failure. This dataset, constructed through a methodology combining ChatGPT’s capabilities and expert validation, is a significant contribution to the field. It facilitates a comprehensive evaluation of CMR-NER. Experimental results demonstrate that our approach achieves comparable or superior performance to existing methods, underscoring its effectiveness in this challenging domain.
Image localization using local features has attracted a lot of attention in recent mobile robots research. A novel, fast local invariant feature in affine transformation is proposed in this article, called AIFLC (Affi...
详细信息
Image localization using local features has attracted a lot of attention in recent mobile robots research. A novel, fast local invariant feature in affine transformation is proposed in this article, called AIFLC (Affine invariant feature based on local color). We adopt affine moment invariants to build affine invariant descriptors. Moreover, we use color gradient based center moment instead of original pixel values in order to enhance discriminative power and robustness of descriptor in photometric transformations. Simulation results show that the run time of AIFLC using optimal selection parameters is about 1/3 of classical SIFT algorithm. Using the standard evaluation images and the ones taken by mobile robots, we experimentally demonstrate that the AIFLC outperforms the state-of-art approaches such as SIFT and SURF in terms of image scaling, rotation, viewpoint changing, and blur transformations.
User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. ...
详细信息
暂无评论