Point cloud completion is crucial in point cloud processing, as it can repair and refine incomplete 3D data, ensuring more accurate models. However, current point cloud completion methods commonly face a challenge: th...
详细信息
In the analysis of drone aerial images, object detection tasks are particularly challenging, especially in the presence of complex terrain structures, extreme differences in target sizes, suboptimal shooting angles, a...
详细信息
In the analysis of drone aerial images, object detection tasks are particularly challenging, especially in the presence of complex terrain structures, extreme differences in target sizes, suboptimal shooting angles, and varying lighting conditions, all of which exacerbate the difficulty of recognition. In recent years, the DETR model based on the Transformer architecture has eliminated traditional post-processing steps such as NMS(Non-Maximum Suppression), thereby simplifying the object detection process and improving detection accuracy, which has garnered widespread attention in the academic community. However, DETR has limitations such as slow training convergence, difficulty in query optimization, and high computational costs, which hinder its application in practical fields. To address these issues, this paper proposes a new object detection model called OptiDETR. This model first employs a more efficient hybrid encoder to replace the traditional Transformer encoder. The new encoder significantly enhances feature processing capabilities through internal and cross-scale feature interaction and fusion logic. Secondly, an IoU (Intersection over Union) aware query selection mechanism is introduced. This mechanism adds IoU constraints during the training phase to provide higher-quality initial object queries for the decoder, significantly improving the decoding performance. Additionally, the OptiDETR model integrates SW-Block into the DETR decoder, leveraging the advantages of Swin Transformer in global context modeling and feature representation to further enhance the performance and efficiency of object detection. To tackle the problem of small object detection, this study innovatively employs the SAHI algorithm for data augmentation. Through a series of experiments, It achieved a significant performance improvement of more than two percentage points in the mAP (mean Average Precision) metric compared to current mainstream object detection models. Furthermore, ther
This paper focuses on the finite-time control(FTC) of the composite formation consensus(CFC)problems for multi-robot systems(MRSs). The CFC problems are firstly proposed for MRSs under the complex network topology of ...
详细信息
This paper focuses on the finite-time control(FTC) of the composite formation consensus(CFC)problems for multi-robot systems(MRSs). The CFC problems are firstly proposed for MRSs under the complex network topology of cooperative or cooperative-competitive networks. Regarding the problems of FTC and CFC on multiple Lagrange systems(MLSs), coupled sliding variables are introduced to deal with the robustness and consistent convergence. Then, the adaptive finite-time protocols are given based on the displacement approaches. With the premised FTC, tender-tracking methods are further developed for the problems of tracking information disparity. Stability analyses of those MLSs mentioned above are clarified with Lyapunov candidates considering the coupled sliding vectors, which provide new verification for tender-tracking systems. Under the given coupled-sliding-variable-based finite-time protocols, MLSs distributively adjust the local formation error to achieve global CFC and perform uniform convergence in time-varying tracking. Finally, simulation experiments are conducted while providing practical solutions for the theoretical results.
The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation *** their trans...
详细信息
The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation *** their transformative impact in fields such as machine translation and intelligent dialogue systems,LLMs face significant *** challenges include safety,security,and privacy concerns that undermine their trustworthiness and effectiveness,such as hallucinations,backdoor attacks,and privacy *** works often conflated safety issues with security *** contrast,our study provides clearer and more reasonable definitions for safety,security,and privacy within the context of *** on these definitions,we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety,security,and privacy in ***,we explore the unique research challenges posed by LLMs and suggest potential avenues for future research,aiming to enhance the robustness and reliability of LLMs in the face of emerging threats.
In this work, VoteDroid a novel fine-tuned deep learning models-based ensemble voting classifier has been proposed for detecting malicious behavior in Android applications. To this end, we proposed adopting the random...
详细信息
Integrated circuits (ICs) are ubiquitous and a crucial component of electronic systems, from satellites and military hardware to consumer devices and cell phones. The computing system’s foundation of trust is the IC....
详细信息
In an Internet of Things (IoT) assisted Wireless Sensor Network (WSN), the location of the Base Station (BS) remains important. BS serves as the central hub for data collection, aggregation and communication within th...
详细信息
To mitigate the challenges posed by data uncertainty in Full-Self Driving (FSD) systems. This paper proposes a novel feature extraction learning model called Adaptive Region of Interest Optimized Pyramid Network (ARO)...
详细信息
Recognizing and analyzing medical images is crucial for disease early detection and treatment planning with appropriate treatment options based on the patient's individual needs and disease history. Deep learning ...
详细信息
Recognizing and analyzing medical images is crucial for disease early detection and treatment planning with appropriate treatment options based on the patient's individual needs and disease history. Deep learning technologies are widely used in the field of healthcare because they can analyze images rapidly and precisely. However, because each object on the image has the potential to hold illness information in medical images, it is critical to analyze the images with minimal information loss. In this context, Capsule Network (CapsNet) architecture is an important approach that aims to reduce information loss by storing the location and properties of objects in images as capsules. However, because CapsNet maintains information on each object in the image, the existence of several objects in complicated images can impair CapsNet's performance. This work proposes a new model called HMedCaps to improve the performance of CapsNet. In the proposed model, it is aimed to develop a deeper and hybrid structure by using Residual Block and FractalNet module together in the feature extraction layer. While it is aimed to obtain rich feature maps by increasing the number of features extracted by deepening the network, it is aimed to prevent the vanishing gradient problem that may occur in the network with increasing depth with these modules with skip connections. Furthermore, a new squash function is proposed to make distinctive capsules more prominent by customizing capsule activation. The CIFAR10 dataset of complex images, RFMiD dataset of retinal images, and Blood Cell Count Dataset dataset of blood cell images were used to evaluate the study. When the proposed model was compared with the basic CapsNet and studies in the literature, it was observed that the performance in complex images was improved and more accurate classification results were obtained in the field of medical image analysis. The proposed hybrid HMedCaps architecture has the potential to make more accurate dia
Text Summarization is a process to abridge a long-size document into condensed form by comprising all the prime information and central theme. Researchers proposed numerous approaches for automatic text summarization,...
详细信息
暂无评论