检索结果-内蒙古大学图书馆

URL: Combating Label Noise for Lung Nodule Malignancy Grading

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ai, Xianze Liao, Zehui Xia, Yong Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China

Due to the complexity of annotation and inter-annotator variability, most lung nodule malignancy grading datasets contain label noise, which inevitably degrades the performance and generalizability of models. Although researchers adopt the label-noise-robust methods to handle label noise for lung nodule malignancy grading, they do not consider the inherent ordinal relation among classes of this task. To model the ordinal relation among classes to facilitate tackling label noise in this task, we propose a Unimodal-Regularized Label-noise-tolerant (URL) framework. Our URL contains two stages, the Supervised Contrastive Learning (SCL) stage and the Memory pseudo-labels generation and Unimodal regularization (MU) stage. In the SCL stage, we select reliable samples and adopt supervised contrastive learning to learn better representations. In the MU stage, we split samples with multiple annotations into multiple samples with a single annotation and shuffle them into different batches. To handle label noise, pseudo-labels are generated using the similarity between each sample and the central feature of each class, and temporal ensembling is used to obtain memory pseudo-labels that supervise the model training. To model the ordinal relation, we introduce unimodal regularization to keep the ordinal relation among classes in the predictions. Moreover, each lung nodule is characterized by three orthographic views. Experiments conducted on the LIDC-IDRI dataset indicate the superiority of our URL over other competing methods. Code is available at https://***/axz520/URL. © 2023, CC BY-NC-ND.

关键词： Grading

Research progress on low-carbon technologies and assessment methods in cement industry 21st

学校读者我要写书评

暂无评论

Research progress on low-carbon technologies and assessment ...

21st Chinese Materials Conference, CMC 2020

作者： Zhao, Haitao Liu, Yu Li, Xiaoqing Hao, Liwei National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of Technology Beijing100124 China Beijing Building Materials Academy of Sciences Research State Key Laboratory of Solid Waste Reuse for Building Materials Beijing100041 China

ISBN: (纸本)9783035717389

As one of the pillar industries for social development and economic construction, cement manufacture is energy and carbon-intensive, whose greenhouse gas (GHG) emissions account for more than 6% of total global man-made GHG emission annually. With the growing attention on the problem of global warming, researching and promoting low-carbon manufacturing technologies to reduce GHG emissions have become the main trend in the development of cement industry under the new era. The low-carbon technologies were sorted out for cement production reported in recent years,the mainstream methods of GHG accounting and assessment such as life cycle assessment (LCA) and carbon footprint analysis (CFA) were introduced, meanwhilethe articles in the field of low-carbon technology and assessment methods in cement production were reviewed. Moreover, the merits and demerits of various assessment methods and applicable fields were discussed in order to provide suggestions and supports for low-carbon transformation of cement industry. © 2021 Trans Tech Publications Ltd, Switzerland.

关键词： Cements

UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Yiwen Xie, Yutong Zhang, Jianpeng Chen, Ziyang Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China The University of Adelaide Australia DAMO Academy Alibaba Group China

The universal model emerges as a promising trend for medical image segmentation, paving up the way to build medical imaging large model (MILM). One popular strategy to build universal models is to encode each task as a one-hot vector and generate dynamic convolutional layers at the end of the decoder to extract the interested target. Although successful, it ignores the correlations among tasks and meanwhile is too late to make the model ‘aware’ of the ongoing task. To address both issues, we propose a prompt-driven Universal Segmentation model (UniSeg) for multi-task medical image segmentation using diverse modalities and domains. We first devise a learnable universal prompt to describe the correlations among all tasks and then convert this prompt and image features into a task-specific prompt, which is fed to the decoder as a part of its input. Thus, we make the model ‘aware’ of the ongoing task early and boost the task-specific training of the whole decoder. Our results indicate that the proposed UniSeg outperforms other universal models and single-task models on 11 upstream tasks. Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation. Code and model are available at https://***/yeerwen/UniSeg. Copyright © 2023, The Authors. All rights reserved.

关键词： Medical imaging

Scd-Net: An Efficient Detection Network for Pcb Defects Based on Spatial and Channel Reconstruction Convolution and Deformable Convolutions

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wang, Yuanji Wang, Wenyan Pan, Xuejuan Lu, Kun Zhang, Jun Chen, Peng Wang, Bing School of Electrical and Information Engineering Anhui University of Technology Anhui Ma’anshan243032 China School of Electrical Engineering and Automation Anhui University China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Internet Institutes of Physical Science and Information Technology Anhui University Anhui Hefei230601 China School of Chemistry and Chemical Engineering Anhui University of Technology China

The detection of defects on printed circuit boards (PCBs) is crucial for guaranteeing the quality and performance of electronic products. However, due to the size of defects is quite small in high-resolution industrial acquisition images, existing detection models are unable to identify them accurately and effectively. This study introduces a new detection model, SCD-Net, which improves the accuracy, effectiveness and robustness of PCB defect detection systems. By combining the proposed modules CNISC and DCCN with the YOLOv8s network structure, the model can reduce computational costs and improve detection accuracy. Furthermore, replacing the original loss function with a new SIoU function helps the model converge faster to improve performance. In comparison to other PCB detection models, this model achieves a PCB defect detection accuracy of up to 98.0%, a model size of 19.2M, and an detection speed of 79.1 FPS, providing a feasible solution for PCB defect detection. © 2024, The Authors. All rights reserved.

关键词： Convolution

Identifying Flight Trajectory Patterns via a Density-Aided Hierarchical Clustering Algorithm 5th

学校读者我要写书评

暂无评论

Identifying Flight Trajectory Patterns via a Density-Aided H...

5th China Aviation Science and technology Conference, 2021

作者： Zhang, Zhuxi Chen, Yichong Fang, Jing Zhou, Xueyang An, Yuhang Zhu, Xi National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Beihang University Beijing100191 China Unit 32751 Beijing China School of Electronics and Information Engineering Beihang University Beijing100191 China Aviation Data Communication Corporation Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Research Institute for Frontier Science Beihang University Beijing100191 China

ISBN: (纸本)9789811674228

Identifying flight trajectory patterns is a vital task that helps controllers better understand the flight operation mechanism, so as to effectively recognize flight anomalies and manage traffic flow, etc. However, flight operation is sensitively affected by the weather and instant airspace regulation, making the flight trajectory pattern too intertwined to be easily distinguished. In this work, we propose a trajectory pattern identification method based on a density-aided hierarchical clustering algorithm. This method employs a weighted trajectory clustering mechanism to keep the minor trajectory patterns from being improperly "swallowed" by other large trajectory patterns. Experimental results show that the proposed method can explicitly distinguish different trajectory patterns and achieve more accurate results than existing approaches. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xing, Yinghui Qu, Litao Zhang, Shizhou Zhang, Kai Zhang, Yanning Ran, Lingyan Zhang, Xiuwei Yin, Hanlin The Shaanxi Provincial Key Laboratory of Speech and Image Information Processing The National Engineering Laboratory for Integrated Aerospace-GroundOcean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710072 China The Research Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution. When taking original MS and PAN images as inputs, they always obtain sub-optimal results due to the scale variation. In this paper, we propose to explore the self-supervised representation of pansharpening by designing a cross-predictive diffusion model, named CrossDiff. It has two-stage training. In the first stage, we introduce a cross-predictive pretext task to pre-train the UNet structure based on conditional DDPM, while in the second stage, the encoders of the UNets are frozen to directly extract spatial and spectral features from PAN and MS, and only the fusion head is trained to adapt for pansharpening task. Extensive experiments show the effectiveness and superiority of the proposed model compared with state-of-the-art supervised and unsupervised methods. Besides, the cross-sensor experiments also verify the generalization ability of proposed self-supervised representation learners for other satellite’s datasets. We will release our code for reproducibility. © 2024, CC BY.

关键词： Deep learning

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

学校读者我要写书评

暂无评论

IEEE Transactions on Fuzzy Systems 2025年

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

Boundary-Aware Network for Abdominal Multi-Organ Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Shishuai Liao, Zehui Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China

Automated abdominal multi-organ segmentation is a crucial yet challenging task in the computer-aided diagnosis of abdominal organ-related diseases. Although numerous deep learning models have achieved remarkable success in many medical image segmentation tasks, accurate segmentation of abdominal organs remains challenging, due to the varying sizes of abdominal organs and the ambiguous boundaries among them. In this paper, we propose a boundary-aware network (BA-Net) to segment abdominal organs on CT scans and MRI scans. This model contains a shared encoder, a boundary decoder, and a segmentation decoder. The multi-scale deep supervision strategy is adopted on both decoders, which can alleviate the issues caused by variable organ sizes. The boundary probability maps produced by the boundary decoder at each scale are used as attention to enhance the segmentation feature maps. We evaluated the BA-Net on the Abdominal Multi-Organ Segmentation (AMOS) Challenge dataset and achieved an average Dice score of 89.29% for multi-organ segmentation on CT scans and an average Dice score of 71.92% on MRI scans. The results demonstrate that BA-Net is superior to nnUNet on both segmentation tasks. © 2022, CC BY-NC-ND.

关键词： Computerized tomography

Label Propagation for 3D Carotid Vessel Wall Segmentation and Atherosclerosis Diagnosis

学校读者我要写书评

暂无评论

arXiv 2022年

Carotid vessel wall segmentation is a crucial yet challenging task in the computer-aided diagnosis of atherosclerosis. Although numerous deep learning models have achieved remarkable success in many medical image segmentation tasks, accurate segmentation of carotid vessel wall on magnetic resonance (MR) images remains challenging, due to limited annotations and heterogeneous arteries. In this paper, we propose a semi-supervised label propagation framework to segment lumen, normal vessel walls, and atherosclerotic vessel wall on 3D MR images. By interpolating the provided annotations, we get 3D continuous labels for training 3D segmentation model. With the trained model, we generate pseudo labels for unlabeled slices to incorporate them for model training. Then we use the whole MR scans and the propagated labels to re-train the segmentation model and improve its robustness. We evaluated the label propagation framework on the CarOtid vessel wall SegMentation and atherosclerOsis diagnosiS (COSMOS) Challenge dataset and achieved a QuanM score of 83.41% on the testing dataset, which got the 1-st place on the online evaluation leaderboard. The results demonstrate the effectiveness of the proposed framework. © 2022, CC BY-NC-ND.

关键词： Magnetic resonance