检索结果-内蒙古大学图书馆

2D-3D Feature Co-Embedding Network with Sparse Annotation for 3D Medical Image Segmentation

学校读者我要写书评

暂无评论

2D-3D Feature Co-Embedding Network with Sparse Annotation fo...

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Mingzhu Guo, Shuyu Wang, Ziwei Jiao, Jianhang Bai, Tian Jilin University College of Computer Science and Technology Changchun China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China Jilin University College of Software Changchun China The Second Norman Bethune Hospital Jilin University Department of Orthopedics Changchun China

ISBN: (纸本)9798350386226

Supervised methods on 3D medical image segmentation need large amounts of annotated data, but annotating is time-consuming. Also, existing 3D segmentation methods capture more global structural information but overlook local detailed features, which negatively impacts the segmentation of small tissues. In this paper, we propose a novel weakly-supervised 2D-3D Feature Co-Embedding Network (2D-3D CoENet) that includes 2D and 3D encoding layers, simultaneously extracting 2D local detailed and 3D global structural features. To reduce annotation costs, we use fewer labeled slices as ground truth and pseudo-labels are generated by 2D-3D CoENet for other slices. Additionally, multi-view learning is introduced to capture more 2D local detailed information, and a Multi-view Semantic Consistency loss (MSC loss) is proposed to constrain features from multiple perspectives. To further enhance the local detailed texture features, we propose an Edge Enhancement Module (EEM) in the 3D segmentation network to enhance the edge detail features. Our experimental results on the SKI10 dataset and OAI ZIB dataset demonstrate that our method outperforms the SOTA weakly-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound results. © 2024 IEEE.

关键词： Medical imaging

Automated Binary Classification of Diabetic Retinopathy by Convolutional Neural Networks 1st

学校读者我要写书评

暂无评论

Automated Binary Classification of Diabetic Retinopathy by C...

1st International Conference of Advanced Computing and Informatics, ICACIN 2020

作者： Skouta, Ayoub Elmoufidi, Abdelali Jai-Andaloussi, Said Ochetto, Ouail Computer Science Modeling Systems and Decision Support Department of Mathematics and Computer Science Faculty of Science Aïn Chock Hassan II University Casablanca Morocco Laboratory of Information Processing and Decision Support Department of Computer Science Faculty of Sciences and Technics Sultan Moulay Slimane University Beni Mellal Morocco Laboratory of Computer Science Modeling Systems and Decision Support FSJES Ain-Chock Hassan II University Casablanca Morocco

ISBN: (纸本)9789811560477

This paper proposes a binary classification method for high-resolution retinal images by using convolutional neural networks. The convolutional neural network is first, formed to recognize and classify the fundus images of the eye as normal retina or proliferative diabetic retina. We are training proposed network by using a graphics processor and a public dataset available on the Kaggle Web site. An increase in data makes possible the identification of complex characteristics involved in the classification task. Our proposed convolutional neural networks achieve an accuracy of 95.5% on 1000 images of the normal retina and 1000 images of proliferative diabetic retina for training and 200 images of the normal retina and 200 images of proliferative diabetic retina for testing. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolutional neural networks

Rethinking Label-specific Features for Label Distribution Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xu, Suping Dai, Chuyi Shang, Lin Shao, Changbin Yang, Xibei Pedrycz, Witold Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Department of Computer Science and Technology Nanjing University Nanjing210023 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Jiangsu University of Science and Technology Zhenjiang212003 China

Label distribution learning (LDL) is an emerging learning paradigm designed to capture the relative importance of labels for each instance. Label-specific features (LSFs), constructed by LIFT, have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label to re-characterize instances. However, directly introducing LIFT into LDL tasks can be suboptimal, as the prototypes it collects primarily reflect intra-cluster relationships while neglecting interactions among distinct clusters. Additionally, constructing LSFs using multi-perspective information, rather than relying solely on Euclidean distance, provides a more robust and comprehensive representation of instances, mitigating noise and bias that may arise from a single distance perspective. To address these limitations, we introduce Structural Anchor Points (SAPs) to capture inter-cluster interactions. This leads to a novel LSFs construction strategy, LIFT-SAP, which enhances LIFT by integrating both distance and direction information of each instance relative to SAPs. Furthermore, we propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution. Extensive experiments on 15 real-world datasets demonstrate the effectiveness of LIFT-SAP over LIFT, as well as the superiority of LDL-LIFT-SAP compared to seven other well-established algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Clustering algorithms

AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yunhao Xiao, Zhen Yang, Lin Meng, Dan Zhou, Xin Fan, Heng Zhang, Libo The Department of State Key Laboratory of Computer Science Institute of Software Chinese Academy of Science China Turing Quantum Company United States OPPO Research Institute The Department of Computer Science and Engineering University of North Texas Denton United States

Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender, hairstyle, body shape, and clothing features, which contain rich and high-level information, have been less explored. To address this gap, we propose a simple, effective, and generic method to predict pedestrian attributes to support general Re-ID embedding. We first introduce AttMOT, a large, highly enriched synthetic dataset for pedestrian tracking, containing over 80k frames and 6 million pedestrian IDs with different time, weather conditions, and scenarios. To the best of our knowledge, AttMOT is the first MOT dataset with semantic attributes. Subsequently, we explore different approaches to fuse Re-ID embedding and pedestrian attributes, including attention mechanisms, which we hope will stimulate the development of attribute-assisted MOT. The proposed method AAM demonstrates its effectiveness and generality on several representative pedestrian multi-object tracking benchmarks, including MOT17 and MOT20, through experiments on the AttMOT dataset. When applied to state-of-the-art trackers, AAM achieves consistent improvements in MOTA, HOTA, AssA, IDs, and IDF1 scores. For instance, on MOT17, the proposed method yields a +1.1 MOTA, +1.7 HOTA, and +1.8 IDF1 improvement when used with FairMOT. To encourage further research on attribute-assisted MOT, we will release the AttMOT dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

Deep Perspective Transformation Based Vehicle Localization on Bird’s Eye View

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mahyar, Abtin Motamednia, Hossein Rahmati, Dara Department of Computer and Data Sciences Shahid Beheshti University Tehran Iran High Performance Computing Laboratory School of Computer Science Institute for Research in Fundamental Sciences Tehran Iran Faculty of Computer Science and engineering Shahid Beheshti University Tehran Iran

An accurate understanding of a self-driving vehicle’s surrounding environment is crucial for its navigation system. To enhance the effectiveness of existing algorithms and facilitate further research, it is essential to provide comprehensive data to the routing system. Traditional approaches rely on installing multiple sensors to simulate the environment, leading to high costs and complexity. In this paper, we propose an alternative solution by generating a top-down representation of the scene, enabling the extraction of distances and directions of other cars relative to the ego vehicle. We introduce a new synthesized dataset that offers extensive information about the ego vehicle and its environment in each frame, providing valuable resources for similar downstream tasks. Additionally, we present an architecture that transforms perspective view RGB images into bird’s-eye-view maps with segmented surrounding vehicles. This approach offers an efficient and cost-effective method for capturing crucial environmental information for self-driving cars. 1 © 2023, CC BY.

关键词： Birds

Incompatibility as a Resource for Programmable Quantum Instruments

学校读者我要写书评

暂无评论

PRX Quantum 2024年第1期5卷 010340-010340页

作者： Kaiyuan Ji Eric Chitambar Center for Quantum Information Institute for Interdisciplinary Information Sciences Tsinghua University Beijing 100084 China School of Electrical and Computer Engineering Cornell University Ithaca New York 14850 USA Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois at Urbana-Champaign Urbana Illinois 61801 USA

Quantum instruments represent the most general type of quantum measurement, as they incorporate processes with both classical and quantum outputs. In many scenarios, it may be desirable to have some “on-demand” device that is capable of implementing one of many possible instruments whenever the experimenter desires. We refer to such objects as programmable instrument devices (PIDs), and this paper studies PIDs from a resource-theoretic perspective. A physically important class of PIDs are those that do not require quantum memories to implement, and these are naturally “free” in this resource theory. Additionally, these free objects correspond precisely to the class of unsteerable channel assemblages in the study of channel steering. The traditional notion of measurement incompatibility emerges as a resource in this theory since any PID controlling an incompatible family of instruments requires a quantum memory to build. We identify an incompatibility preorder between PIDs based on whether one can be transformed into another using processes that do not require additional quantum memories. Necessary and sufficient conditions are derived for when such transformations are possible based on how well certain guessing games can be played using a given PID. Ultimately our results provide an operational characterization of incompatibility, and they offer semi-device-independent tests for incompatibility in the most general types of quantum instruments.

关键词： Quantum communication, protocols & technology Quantum correlations in quantum information Quantum correlations, foundations & formalism Quantum information processing Quantum measurements Quantum memories Quantum networks Resource theories

Ultrahigh-coherence microcomb generation and low-noise amplification using integrated photonics

学校读者我要写书评

暂无评论

Ultrahigh-coherence microcomb generation and low-noise ampli...

2024 IEEE Photonics Conference, IPC 2024

作者： Zhang, Xuguang Zhou, Zixuan Guo, Yijun Zhuang, Minxue Jin, Warren Shen, Bitao Chen, Yujun Huang, Jiahui Hu, Weiwei Shu, Haowen Bowers, John E. Wang, Xingjun Chang, Lin University of California Santa Barbara Department of Electrical and Computer Engineering Santa BarbaraCA United States Peking University State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Beijing China Peking University Frontiers Science Center for Nano-Optoelectronics Beijing China

ISBN: (纸本)9798350361957

We demonstrate a high-coherence parallel integrated light source utilizing a self-injection locked microcomb and injection locking amplification. Our strategy exhibits a record high on-chip gain of 60 dB, nearly 0 dB noise factor, which enable more than 30 highly coherent channels in integrated photonics whose linewidths down to 10 Hz, power exceeding 20 dBm per line and a wall plug efficiency of 19%. © 2024 IEEE.

关键词： Photonic integrated circuits

An Empirical Study on the Language Modal in Visual Question Answering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Peng, Daowan Wei, Wei Mao, Xian-Ling Fu, Yuanyuan Chen, Dangyang Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China China Department of Computer Science and Technology Beijing Institute of Technology China Ping An Property & Casualty Insurance Company of China Ltd China

Generalization beyond in-domain experience to out-of-distribution data is of paramount significance in the AI domain. Of late, state-of-the-art Visual Question Answering (VQA) models have shown impressive performance on in-domain data, partially due to the language priors bias which, however, hinders the generalization ability in practice. This paper attempts to provide new insights into the influence of language modality on VQA performance from an empirical study perspective. To achieve this, we conducted a series of experiments on six models. The results of these experiments revealed that, 1) apart from prior bias caused by question types, there is a notable influence of postfix-related bias in inducing biases, and 2) training VQA models with word-sequence-related variant questions demonstrated improved performance on the out-of-distribution benchmark, and the LXMERT even achieved a 10-point gain without adopting any debiasing methods. We delved into the underlying reasons behind these experimental results and put forward some simple proposals to reduce the models’ dependency on language priors. The experimental results demonstrated the effectiveness of our proposed method in improving performance on the out-of-distribution benchmark, VQA-CPv2. We hope this study can inspire novel insights for future research on designing bias-reduction approaches. © 2023, CC BY.

关键词： Benchmarking

Accelerating Robotics Test and Evaluation with a Streamlined Simulation Process 1

学校读者我要写书评

暂无评论

Joint Mechanical Systems and Robotics and RoManSy Symposium, MSR-RoManSy 2024

作者： Adipudi, Vikram Carey, Kevin Harrison, Andre Herrmann, Jeffrey W. Lawrence, Craig Michaelis, James Porter, Adam Institute for Systems Research University of Maryland College ParkMD United States DEVCOM Army Research Laboratory AdelphiMD United States ARLIS University of Maryland College ParkMD United States Department of Computer Science University of Maryland College ParkMD United States

ISBN: (数字)9783031606182

ISBN: (纸本)9783031606175

Simulation is a popular approach for testing and evaluating robotic systems, but it is also a challenge due to the complexity of the autonomy stack (the software that runs the robot) and its interactions with the simulation software. This paper describes software tools that streamline the process of creating and running simulation models with unmanned ground vehicles that are using the ARL ground autonomy stack. Using these tools simplifies the tasks that are needed to conduct a simulation study by employing a map-based user interface, providing a checklist for selecting the topics that should be recorded, and automatically iterating over different combinations of configurations and maps. The streamlined process can accelerate the development of safe, reliable robotic systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： computer aided software engineering