The proceedings contain 8 papers. The topics discussed include: multi-view autoencoders for fake news detection;identifying school shooter threats through online texts;detecting cyberbullying in Thai memes: a multimod...
ISBN:
(纸本)9798331508418
The proceedings contain 8 papers. The topics discussed include: multi-view autoencoders for fake news detection;identifying school shooter threats through online texts;detecting cyberbullying in Thai memes: a multimodal approach using deep learning;optimizing Chinese-to-English translation using large language models;RIAND: robustness-improved and accelerated neural-deduplication;conceptual in-context learning and chain of concepts: solving complex conceptual problems using large language models;analyzing the cognitive impact of trauma from a metaphorical perspective: a case study on the attempted assassination of Donald Trump;and SUPERB-EP: evaluating encoder pooling techniques in self-supervised learning models for speech classification.
The proceedings contain 12 papers. The topics discussed include: reconstructing weighted social networks after a node deleted with substitute node selection;ConText Mining: complementing topic models with few-shot in-...
ISBN:
(纸本)9798331519742
The proceedings contain 12 papers. The topics discussed include: reconstructing weighted social networks after a node deleted with substitute node selection;ConText Mining: complementing topic models with few-shot in-context learning to generate interpretable topics;assessing personalized AI mentoring with large language models in the computing field;filtering hallucinations and omissions in large language models through a cognitive architecture;logical reasoning with LLMs via few-shot prompting and fine-tuning: a case study on turtle soup puzzles;synthetic feature augmentation improves generalization performance of language models;advancing natural language to SQL: a comparative study of open source LLMs on benchmark datasets;and To NER or not to NER? a case study of low-resource deontic modalities in EU legislation.
Remote Sensing (RS) is applied for a variety of purposes, thanks to the large availability of heterogeneous data. Furthermore, the growing number of CubeSat missions is encouraging increasingly advanced, flexible, and...
详细信息
ISBN:
(纸本)9798350360332;9798350360325
Remote Sensing (RS) is applied for a variety of purposes, thanks to the large availability of heterogeneous data. Furthermore, the growing number of CubeSat missions is encouraging increasingly advanced, flexible, and configurable RS missions, that also include the use of Artificial intelligence (AI) on-board. Indeed, specific hardware allows advanced processing on-board the satellites even if the computational capability is not the same as on the ground. In the context of on-board processing, the compression of acquired images is crucial because permits to save bandwidth for data transmission. We propose an AI-based lossy image compression algorithm for multispectral images that can be executed on-board a CubeSat. The algorithm is based on a Convolutional AutoEncoder (CAE) Neural Network (NN). In lossy compression part of the information stored in the original image is lost. Therefore, the results evaluation includes the assessment of the usability of the decompressed images for common applications.
As routine pathology moves into the digital age;the spread of high-efficiency and high-resolution tissue scanners opens up the possibility of routine analysis of three-dimensional samples containing fluorescent geneti...
详细信息
ISBN:
(纸本)9798350329537;9798350329520
As routine pathology moves into the digital age;the spread of high-efficiency and high-resolution tissue scanners opens up the possibility of routine analysis of three-dimensional samples containing fluorescent genetic signals. One of these cornerstones is confocal microscopy, with the help of which cell nuclei and their signals can be imaged in three dimensions. This article presents a novel deep learning-based algorithm for detecting signals within three-dimensional confocal microscopy images. By leveraging the power of convolutional neural networks, our approach significantly improves the accuracy and efficiency of signal detection compared to traditional imageprocessing methods, especially in the case of thick sections. We demonstrate the algorithmic effectiveness through validation on various samples, highlighting its potential to advance research in biology and medicine.
With the rapid development of artificial intelligence, particularly the rise of deep learning, the importance of Explainable Artificial intelligence has become increasingly prominent. Among its key techniques, counter...
详细信息
With the rapid development of artificial intelligence, particularly the rise of deep learning, the importance of Explainable Artificial intelligence has become increasingly prominent. Among its key techniques, counterfactual explanation plays a crucial role in understanding the decision-making mechanisms of opaque models. However, the high dimensionality and complex feature patterns of image data pose significant challenges for the task of generating counterfactuals for images. Existing literature has proposed various algorithms based on different assumptions, many of which rely on the existence of appropriate generative models. Some of these assumptions, particularly the assumption regarding the existence of generative models, may be overly stringent. To address this issue, this letter introduces a novel assumption-free image counterfactual generation algorithm, DFO-S, based on Score Matching and gradient-free optimization techniques. The proposed method achieves high-quality counterfactual generation without relying on generative models. Through extensive empirical analysis, we demonstrate the significant superiority of our method in terms of performance.
The aim of my project is to offer an automation solution for examining solid-state passive detectors frequently used in particle physics. Since the detector surface often exceeds the field of view of microscopes, the ...
详细信息
images captured in low-light conditions usually suffer from degradation problems. Recently, numerous deep learning-based methods are proposed for low-light image enhancement. They either focus on performance improveme...
详细信息
images captured in low-light conditions usually suffer from degradation problems. Recently, numerous deep learning-based methods are proposed for low-light image enhancement. They either focus on performance improvement with negligence of computational complicity, or are extremely computationally efficient networks with poor performance. In this work, we intend to figure out a solution, which strikes a balance between computational cost and performance. Moreover, we observe that different regions of an image contain different amounts of information, where the region with less information is easier to restore than that with more information. Hence, we propose to crop a low-light image into patches and classify these patches into "simple", "medium" and "hard" categories based on their involved information. Then, we enhance different patch categories with different network complexities, therefore, a Category-specific processing Network (CSPN) is proposed to achieve the computational complexity and performance balance. The patch classification is implemented by the proposed Grey-Level Co-occurrence Matrix (GLCM) entropy-based algorithm, which measures the content complexity of an image by analyzing the statistics of the difference between pixels. As the frequency domain contains exclusive feature information that is beneficial for improving image quality, the wavelet transform is introduced during the enhancement. Extensive experimental results demonstrate the superiority of our proposed CSPN over other state-of-the-art methods in various datasets with the least amount of computational cost.
Aerial image classification is crucial across multiple sectors, including environmental monitoring, agriculture, and urban planning. However, processing large-scale aerial imagery efficiently poses challenges in model...
详细信息
Aerial image classification is crucial across multiple sectors, including environmental monitoring, agriculture, and urban planning. However, processing large-scale aerial imagery efficiently poses challenges in model performance, computational efficiency, and scalability. This research introduces a novel convolutional neural network (CNN) architecture tailored for cactus identification from aerial photographs. The proposed cloud-based pipeline enhances training efficiency through scalable data storage, preprocessing, and distributed training across platforms such as Amazon Web Services (AWS), Google Cloud Platform (GCP), and Microsoft Azure. This comparative analysis demonstrates the model's computational efficiency, shorter training durations, and cost-effectiveness. The model integrates residual connections and depthwise separable convolutions, achieving 96.7% accuracy on the aerial cactus identification dataset. The results highlight the model's high performance, cost-efficiency, and scalability, making it suitable for real-world aerial image classification tasks. Future work aims to further optimize the model using advanced techniques and extend its application to multi-class classification challenges.
Low-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerba...
详细信息
Low-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerbated by the computational demands of processing spatial dependencies under such conditions. We present a novel transformer-based framework that enhances efficiency by utilizing depthwise separable convolutions instead of conventional approaches. Additionally, an original feed-forward network design reduces the computational overhead while maintaining high performance. Experimental results demonstrate that this method achieves competitive results, providing a practical and effective solution for enhancing images captured in low-light environments.
Conventional wisdom in model-based computational imaging incorporates physics-based imaging models, noise characteristics, and image priors into a unified Bayesian framework. Rapid advances in deep learning have inspi...
详细信息
Conventional wisdom in model-based computational imaging incorporates physics-based imaging models, noise characteristics, and image priors into a unified Bayesian framework. Rapid advances in deep learning have inspired a new generation of data-driven computational imaging systems with performances even better than those of their model-based counterparts. However, the design of learning-based algorithms for computational imaging often lacks transparency, making it difficult to optimize the entire imaging system in a complete manner.
暂无评论