检索结果-内蒙古大学图书馆

Semi-Supervised Skin Lesion Segmentation Based on Pseudo-Labels

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2025年第2期52卷 325-332页

作者： Mu, Bo Wei, JingXin Zhang, Yujun School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

In recent years, deep learning has significantly advanced skin lesion segmentation. However, annotating medical image data is specialized and costly, while obtaining unlabeled medical data is easier. To address this challenge, we propose a semi-supervised learning strategy to improve segmentation accuracy by combining a small amount of annotated data with a larger volume of unlabeled data. Our approach employs a teacher-student model framework. In this framework, the teacher model generates pseudo-labels for the unlabeled data, and the student model is trained using both these pseudo-labels and the limited true labels. To improve the student model’s learning capacity, we introduce auxiliary segmentation heads that provide joint guidance during training. We use the crossentropy (CE) loss function to quantify the discrepancies between the segmentation outputs of the main head and auxiliary heads. Since pseudo-labels generated by the teacher model may contain noise, we developed a mechanism to identify and exclude uncertain regions in each unlabeled image. This reduces pseudolabel noise and mitigates its negative impact on the student model. Our method demonstrates significant improvements in skin lesion segmentation on the publicly available ISIC2018 dataset, achieving Dice coefficients of 87.84% and 88.73% with only 5% and 10% of the total annotated data, respectively, outperforming existing methods. © (2025), (International Association of Engineers). All rights reserved.

关键词： Self-supervised learning

Vision-Text Bidirectional Collaborative Image Captioning Algorithm

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2025年第2期52卷 515-523页

作者： Li, Mei-Qi Zhou, Zi-Wei School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Image captioning is an interdisciplinary research hotspot at the intersection of computer vision and natural language processing, representing a multimodal task that integrates core technologies from both fields. This task requires the use of computer vision techniques to analyze and extract key visual features from images, followed by the application of natural language processing techniques to generate descriptive text that is syntactically and semantically aligned with human cognition. This process poses a significant challenge for computers. Existing models mostly ignore the relative positional information of visual objects and struggle to efficiently capture the complex relationships between visual and textual data. To address these challenges, we propose a vision-to-text bidirectional collaborative image captioning method. This approach extracts both visual features and positional information of objects, allowing the model to better understand the spatial relationships between objects. The CEW word embedding approach encodes textual information more profoundly, enhancing semantic expression and contextual understanding. In the decoding phase, a bidirectional cross-attention mechanism strengthens the interaction between vision and text, leading to improved accuracy in image understanding. The model is trained and tested on the MSCOCO 2014 dataset and compared with several popular models. Experimental results demonstrate that the proposed method achieves significant improvements on the CIDEr and BLEU-1 evaluation metrics with an increase of 1.5 and 1.1, respectively. In addition, we conduct ablation experiments, quantitative analysis, and qualitative analysis to comprehensively validate the effectiveness and stability of the proposed algorithm. © (2025), (International Association of Engineers). All rights reserved.

关键词： Embeddings

A Dangerous Driving Behavior Detection Method Based on Improved YOLOv8s

学校读者我要写书评

暂无评论

engineering Letters 2025年第3期33卷 721-731页

作者： Zhou, Tong Zhang, Xiaoxia Chen, Huilong School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Detecting dangerous driving behavior is a critical research area focused on identifying and preventing actions that could lead to traffic accidents, such as smoking, drinking, yawning, and drowsiness, through technical methods. Advanced computer vision and machine learning technologies enable efficient detection models to monitor and analyze driver behavior, improving road safety. Due to challenges posed by complex environments, this paper introduces an enhanced detection algorithm, YOLOv8s-CDS, to improve the identification of dangerous driving behaviors. First, the ConvNeXt V2 module is integrated with the C2f module to form C2fNeb2, optimizing feature extraction for behaviors like smoking or phone use. Second, the DASI (Dimension-Aware Selective Integration) module enhances detection accuracy through multi-scale fusion and dimension perception. Additionally, the SCConv module replaces the Conv module in the Bottleneck, forming C2fSCConv, which reduces spatial redundancy and improves detection efficiency.A comprehensive experimental analysis of dangerous driving image datasets demonstrates that the mean average precision (mAP) of the YOLOv8s-CDS algorithm is 91.20%, which is 2.4% higher than that of the YOLOv8s algorithm. Compared to other object detection algorithms, such as Faster R-CNN, YOLOv5s, YOLOv7s, YOLOX and YOLOv8, YOLOv8s-CDS demonstrates greater practicality in detecting dangerous driving behaviors, contributing to a reduction in traffic accidents and enhancing the safety of life and property. © 2025, International Association of Engineers. All rights reserved.

关键词： Highway accidents

The Improved Unet Semantic Segmentation Network for Remote Sensing Images

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2025年第4期52卷 1187-1195页

作者： Zhu, Hang Zhao, Ji School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

With the development of artificial intelligence, deep learning has been increasingly used to achieve automatic detection of geographic information, replacing manual interpretation and improving efficiency. However, remote sensing images themselves have the issue of slight inter-class variance and significant intra-class variance, making it challenging to extract valuable information. Additionally, the increasing resolution and size of remote sensing images in recent years have introduced more complexity in the types of information, further increasing the difficulty of extracting valuable data. This paper proposes an improved Unet semantic segmentation network (referred to as RAUnet). First, in the encoder, continuous convolutional blocks are enhanced to extract features. At the same time, the EMAM multi-scale attention module is employed for cross-channel learning, capturing information from different feature channels of the target and using the surrounding feature information to assist in distinguishing target information. To capture multi-directional long-range dependencies, the Lo2 module is used for long-range modeling, which captures not only local contextual information but also long-range dependencies. In the decoder, a Dysample upsampling module is used to restore feature details, and in the skip connection layer, features are added for feature fusion. Experimental results show that compared to mainstream models, the proposed method achieves superior segmentation results on the Potsdam and Vihingen datasets. © (2025), (International Association of Engineers). All rights reserved.

关键词： Semantic Segmentation

Real-time all-frequency global llumination with radiance caching

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第5期10卷 923-936页

作者： Youxin Xing Gaole Pan Xiang Chen Ji Wu Lu Wang Beibei Wang School of Software Shandong UniversityJinan 250101China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China

Global illumination(GI)plays a crucial role in rendering realistic results for virtual exhibitions,such as virtual car *** scenarios usually include all-frequency bidirectional reflectance distribution functions(BRDFs),although their geometries and light configurations may be *** allfrequency BRDFs in real time remains challenging due to the complex light *** approaches,including precomputed radiance transfer,light probes,and the most recent path-tracing-based approaches(ReSTIR PT),cannot satisfy both quality and performance requirements ***,we propose a practical hybrid global illumination approach that combines ray tracing and cached GI by caching the incoming radiance with *** approach can produce results close to those of ofline renderers at the cost of only approximately 17 ms at runtime and is robust over all-frequency *** approach is designed for applications involving static lighting and geometries,such as virtual exhibitions.

关键词： real-time global illumination all-frequency BRDFs Haar wavelets radiance caching

YOLOv7-DSE: An Efficient Safety Equipment Detection Network

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2024年第6期51卷 572-581页

作者： Ren, Jiaxin Cui, Wenhua Tao, Ye Shi, Tianwei School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Safety equipment detection is an important application of object detection, receiving widespread attention in fields such as smart construction sites and video surveillance. Significant progress has been made in object detection due to the rapid development of deep learning. Multi-scale targets and complex scenes increase the likelihood of false positives and missed detections, which can affect the accuracy of the detection. To address this issue, this study proposes YOLOv7-DSE. It is a small complex target scene detection network based on the improved YOLOv7. Also, we have created a private dataset of safety equipment. First, we enhanced the ELAN and MP backbone networks. Backbone is replaced by ordinary convolution by the depthwise separable convolution. We enabled the backbone network to extract deeper image features without increasing the amount of parameters and computation. Simultaneously, the model incorporates the EIOU loss function to improve its convergence speed and positioning effect. Secondly, we propose a new ELAN-SPD structure in the head network. Based on the ELAN structure, a space-to-depth convolutional layer is added to fully downsample the feature map, preserving all learnable features. Our network model can better detect objects with significant size differences faced with complex scenes. YOLOv7-DSE achieved the mAP of 82.38%, surpassing the original YOLOv7 with 2.64%. The YOLOv7-DSE model has a minor size compared to the baseline model. Our improvement has reduced the model parameters by 22.4%. © (2024), (International Association of Engineers). All rights reserved.

关键词： Object detection

Multi-label, Classification-based Prediction of Breast Cancer Metastasis Directions

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2025年第1期52卷 1-10页

作者： Wang, Tingting Fan, Qi Tan, Liang Zhang, Beier School of Computer and Software Engineering Anhui Institute of Information Technology China School of Computer Science and Technology Huaibei Normal University China School of Computer and Software Engineering Anhui Institute of Information Technology China School of Computer Science and Technology Huaibei Normal University China

Predicting the metastatic direction of primary breast cancer (BC), thus assisting physicians in precise treatment, strict follow-up, and effectively improving the prognosis. The clinical data of 293,946 patients with primary BC diagnosed between 2010 and 2015 were collected from the Surveillance, Epidemiology, and End Results database. Multiple interpolations and Multi-label Synthetic Minority Over-sampling Technique methods were used for data analysis, and machine learning model was established for multi-label classification. Finally, Surgical information, lymph node status, distant metastasis, tumor size, chemotherapy, histological type, and radiotherapy had significant influence as inputs. Compared with the k-nearest neighbor model, average accuracies of the decision tree and random forest (RF) models increased from 88.84% to 93.59% and 94.14%, respectively. Their average precision, recall rate, F1 score, area under the receiver operating characteristic curve and weighted-F1 increased from 87.24% to 95.85% and 94.74%, 87.73% to 90.40% and 91.76%, 87.07% to 92.16% and 93.45%, 97.11% to 99.53% and 99.95%, 82.13% to 89.44% and 90.48%, respectively. In conclusion, the RF model, which showed the best performance, can be used in multi-label prediction of BC metastasis directions, and can assist physicians in diagnosing and treating patients with primary BC. © (2025), (International Association of Engineers). All rights reserved.

关键词： Lung cancer

Application of Face Detection and Recognition Algorithm Based on Deep Learning in Automatic Interception of Target Person Video Clips

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2024年第10期51卷 1546-1559页

作者： Wang, Zhibiao Tao, Ye Liu, Xu Yu, Jiayi Cui, Wenhua School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Current automatic segment extraction techniques for identifying target characters in videos have several limitations, including low accuracy, slow processing speeds, and poor adaptability to diverse scenes. This paper introduces an optimized algorithm to address these issues that enhance the RetinaFace and FaceNet models. We selected RetinaFace for face detection, employing MobileNetV1-0.25 as the backbone network and simplifying its Feature Pyramid Network (FPN) structure to boost detection speeds. Analysis of 460 images with a 720P resolution demonstrated an average speed improvement of 20.6%. For face recognition, we utilized FaceNet with MobileNetV3 as the backbone, augmenting its feature extraction capability by integrating four Receptive Field Block (RFB) structures and replacing the Squeeze-and-Excitation (SE) module with the Convolutional Block Attention Module (CBAM). Experimental results indicate that our enhancements elevate the maximum accuracy to 97%, outperforming the original model. Additionally, we integrated these refined algorithms and conducted disintegration experiments on segment extraction in 10 videos, evaluating various metrics. The findings show improvements in both precision and recall. We also compared our algorithm against the Dlib model;our system achieved an overall interception accuracy of 79.94%, surpassing Dlib’s 75.55%. This confirms the enhanced performance and feasibility of our proposed algorithm. © (2024), (International Association of Engineers). All rights reserved.

关键词： Face recognition

An infrastructure software perspective toward computation offloading between executable specifications and foundation models

学校读者我要写书评

暂无评论

science China(Information sciences) 2025年第4期68卷 380-382页

作者： Dezhi RAN Mengzhou WU Yuan CAO Assaf MARRON David HAREL Tao XIE Key Laboratory of High Confidence Software Technologies (PKU) Ministry of Education School of Computer SciencePeking University School of Electronics Engineering and Computer Science Peking University Department of Computer Science and Applied Mathematics Weizmann Institute of Science

Foundation models(FMs) [1] have revolutionized software development and become the core components of large software systems. This paradigm shift, however, demands fundamental re-imagining of software engineering theories and methodologies [2]. Instead of replacing existing software modules implemented by symbolic logic, incorporating FMs' capabilities to build software systems requires entirely new modules that leverage the unique capabilities of ***, while FMs excel at handling uncertainty, recognizing patterns, and processing unstructured data, we need new engineering theories that support the paradigm shift from explicitly programming and maintaining user-defined symbolic logic to creating rich, expressive requirements that FMs can accurately perceive and implement.

关键词：