检索结果-内蒙古大学图书馆

BiLSTM-Autoencoder Architecture for Stance Prediction

学校读者我要写书评

暂无评论

BiLSTM-Autoencoder Architecture for Stance Prediction

2020 International Conference on Data Science and engineering, ICDSE 2020

作者： Padnekar, S Meena Kumar, G Santhosh Deepak, P. Cochin University of Science and Technology Artificial Intelligence and Computer Vision Lab Department of Computer Science Kochi India Queen's University School of Electronics Electrical Engineering and Computer Science Belfast United Kingdom

ISBN: (纸本)9781728189192

The recent surge in the abundance of fake news appearing on social media and news websites poses a potential threat to high-quality journalism. Misinformation hurts people, society, science, and democracy. This reason has led many researchers to develop techniques to identify fake news. In this paper, we discuss a stance prediction technique using the Deep Learning approach, which can be used as a factor to determine the authenticity of news articles. The Fake News Stance Prediction is the process of automatically classifying the stance of a news article towards a target into one of the following classes: Agree, Disagree, Discuss, Unrelated. The stance prediction task's input is the news articles containing a pair: a headline as the target and a body as a claim. This paper proposes a deep learning architecture using Bi-directional Long Short Term Memory and Autoencoder for stance prediction. We illustrate, through empirical studies, that the method is reasonably accurate at predicting stance, achieving a classification accuracy as high as 94%. The proposed stance detection method would be useful for assessing the credibility of news articles. © 2020 IEEE.

关键词： Forecasting

Enhancing Medical Image Segmentation with TransCeption: A Multi-Scale Feature Fusion Approach

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Azad, Reza Jia, Yiwei Aghdam, Ehsan Khodapanah Cohen-Adad, Julien Merhof, Dorit The Institute of Imaging and Computer Vision RWTH Aachen University Aachen52074 Germany The Department of Electrical Engineering Shahid Beheshti University Tehran*** Iran The Mila Quebec AI Institute Canada The Functional Neuroimaging Unit CRIUGM University of Montreal Canada The NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montreal MontrealH3T 1J4 Canada The Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg93053 Germany The Fraunhofer Institute for Digital Medicine MEVIS Bremen28359 Germany

While CNN-based methods have been the cornerstone of medical image segmentation due to their promising performance and robustness, they suffer from limitations in capturing long-range dependencies. Transformer-based approaches are currently prevailing since they enlarge the reception field to model global contextual correlation. To further extract rich representations, some extensions of the U-Net employ multi-scale feature extraction and fusion modules and obtain improved performance. Inspired by this idea, we propose TransCeption for medical image segmentation, a pure transformer-based U-shape network featured by incorporating the inception-like module into the encoder and adopting a contextual bridge for better feature fusion. The design proposed in this work is based on three core principles: (1) The patch merging module in the encoder is redesigned with ResInception Patch Merging (RIPM). Multi-branch transformer (MB transformer) adopts the same number of branches as the outputs of RIPM. Combining the two modules enables the model to capture a multi-scale representation within a single stage. (2) We construct an Intra-stage Feature Fusion (IFF) module following the MB transformer to enhance the aggregation of feature maps from all the branches and particularly focus on the interaction between the different channels of all the scales. (3) In contrast to a bridge that only contains token-wise self-attention, we propose a Dual Transformer Bridge that also includes channel-wise self-attention to exploit correlations between scales at different stages from a dual perspective. Extensive experiments on multi-organ and skin lesion segmentation tasks present the superior performance of TransCeption compared to previous work. The code is publicly available on GitHub. © 2023, CC BY.

关键词： Merging

vision Transformer Hashing for Image Retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dubey, Shiv Ram Singh, Satish Kumar Chu, Wei-Ta Computer Vision and Biometrics Lab Indian Institute of Information Technology Allahabad India Department of Computer Science and Information Engineering National Cheng Kung University Taiwan

Deep learning has shown a tremendous growth in hashing techniques for image retrieval. Recently, Transformer has emerged as a new architecture by utilizing self-attention without convolution. Transformer is also extended to vision Transformer (ViT) for the visual recognition with a promising performance on ImageNet. In this paper, we propose a vision Transformer based Hashing (VTS) for image retrieval. We utilize the pre-trained ViT on ImageNet as the backbone network and add the hashing head. The proposed VTS model is fine tuned for hashing under six different image retrieval frameworks, including Deep Supervised Hashing (DSH), HashNet, Greedy-Hash, Improved Deep Hashing Network (IDHN), Deep Polarized Network (DPN) and Central Similarity Quantization (CSQ) with their objective functions. We perform the extensive experiments on CIFAR10, ImageNet, NUS-Wide, and COCO datasets. The proposed VTS based image retrieval outperforms the recent state-of-the-art hashing techniques with a great margin. We also find the proposed VTS model as the backbone network is better than the existing networks, such as AlexNet and ResNet. The code is released at https://***/shivram1987/visionTransformerHashing. Copyright © 2021, The Authors. All rights reserved.

关键词： Image retrieval

Deep Gaussian processes for few-shot segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Johnander, Joakim Edstedt, Johan Danelljan, Martin Felsberg, Michael Khan, Fahad Shahbaz Computer Vision Laboratory Dept. of Electrical Engineering Linköping University Sweden Zenseact Ab Sweden Computer Vision Lab Eth Zurich Switzerland Mohamed Bin Zayed University of Ai ARE United Arab Emirates

Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A common approach is to model each class with a single prototype. While conceptually simple, these methods suffer when the target appearance distribution is multi-modal or not linearly separable in feature space. To tackle this issue, we propose a few-shot learner formulation based on Gaussian process (GP) regression. Through the expressivity of the GP, our approach is capable of modeling complex appearance distributions in the deep feature space. The GP provides a principled way of capturing uncertainty, which serves as another powerful cue for the final segmentation, obtained by a CNN decoder. We further exploit the end-to-end learning capabilities of our approach to learn the output space of the GP learner, ensuring a richer encoding of the segmentation mask. We perform comprehensive experimental analysis of our few-shot learner formulation. Our approach sets a new state-of-the-art for 5-shot segmentation, with mIoU scores of 68.1 and 49.8 on PASCAL-5i and COCO-20i, respectively. © 2021, CC BY-NC-SA.

关键词： Gaussian distribution

Meta-Learning based Degradation Representation for Blind Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xia, Bin Tian, Yapeng Zhang, Yulun Hang, Yucheng Yang, Wenming Liao, Qingmin The Department of Electronic Engineering Shenzhen International Graduate School Tsinghua University Shenzhen518055 China The Department of Computer Science The University of Texas at Dallas RichardsonTX75080 United States The Computer Vision Lab ETH Zürich Zürich8092 Switzerland

Blind image super-resolution (blind SR) aims to generate high-resolution (HR) images from low-resolution (LR) input images with unknown degradations. To enhance the performance of SR, the majority of blind SR methods introduce an explicit degradation estimator, which helps the SR model adjust to unknown degradation scenarios. Unfortunately, it is impractical to provide concrete labels for the multiple combinations of degradations (e.g., blurring, noise, or JPEG compression) to guide the training of the degradation estimator. Moreover, the special designs for certain degradations hinder the models from being generalized for dealing with other degradations. Thus, it is imperative to devise an implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of ground-truth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDAT is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired LR and HR images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images. Furthermore, we introduce an RDAN module that is capable of discerning regional degradations, allowing IDR to adaptively influence various texture patterns. Extensive experiments under classic and real-world degradation settings show that MRDA achieves SOTA performance and can generalize to various deg

关键词： Distillation

Probing Three-Dimensional Magnetic Fields: II - An Interpretable Convolutional Neural Network

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Yue Lazarian, A. Wu, Yan Fu, Chengcheng Department of Physics University of Wisconsin-Madison MadisonWI53706 United States Department of Astronomy University of Wisconsin-Madison MadisonWI53706 United States Computer Vision Lab ETH Zurich 8092 Switzerland College of Electronics and Information Engineering Tongji University Shanghai201804 China

Observing 3D magnetic fields, including orientation and strength, within the interstellar medium is vital but notoriously difficult. However, recent advances in our understanding of anisotropic magnetohydrodynamic (MHD) turbulence demonstrate that MHD turbulence and 3D magnetic fields leave their imprints on the intensity features of spectroscopic observations. Leveraging these theoretical frameworks, we propose a novel Convolutional Neural Network (CNN) model to extract this embedded information, enabling the probe of 3D magnetic fields. This model examines the plane-of-the-sky magnetic field orientation (Φ), the magnetic field’s inclination angle (y) relative to the line-of-sight, and the total magnetization level (MA1) of the cloud. We train the model using synthetic emission lines of 13CO (J = 1 - 0) and C18O (J = 1 - 0), generated from 3D MHD simulations that span conditions from sub-Alfvénic to super-Alfvénic molecular clouds. Our tests confirm that the CNN model effectively reconstructs the 3D magnetic field topology and magnetization. The median uncertainties are under 5◦ for both Φand y, and less than 0.2 for MA in sub-Alfvénic conditions (MA ≈ 0.5). In super-Alfvénic scenarios (MA ≈ 2.0), they are under 15◦ for Φ and y, and 1.5 for MA. We applied this trained CNN model to the L1478 molecular cloud. Results show a strong agreement between the CNN-predicted magnetic field orientation and that derived from Planck 353 GHz polarization. The CNN approach enabled us to construct the 3D magnetic field map for L1478, revealing a global inclination angle of ≈ 76◦ and a global MA of ≈ 1.07. Copyright © 2023, The Authors. All rights reserved.

关键词： Neural network models

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yan, Weixiang Liu, Haitian Wang, Yunkun Li, Yunzhe Chen, Qian Wang, Wen Lin, Tingyu Zhao, Weishan Zhu, Li Sundaram, Hari Deng, Shuiguang University of California Santa Barbara United States School of Software Engineering Xi'an Jiaotong University China Zhejiang University China University of Illinois Urbana-Champaign United States Alibaba Group China Computer Vision Lab TU Wien Austria University of Chinese Academy of Sciences China

Large Language Models (LLMs) have demonstrated remarkable performance on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities of LLMs suffer from severe limitations. First, most benchmarks are insufficient as they focus on a narrow range of popular programming languages and specific tasks, whereas real-world software development scenarios show a critical need to implement systems with multilingual and multitask programming environments to satisfy diverse requirements. Second, most benchmarks fail to consider the actual executability and the consistency of execution results of the generated code. To bridge these gaps between existing benchmarks and expectations from practical applications, we introduce CodeScope, an execution-based, multilingual, multitask, multidimensional evaluation benchmark for comprehensively measuring LLM capabilities on coding tasks. CodeScope covers 43 programming languages and eight coding tasks. It evaluates the coding performance of LLMs from three dimensions (perspectives): length, difficulty, and efficiency. To facilitate execution-based evaluations of code generation, we develop MultiCodeEngine, an automated code execution engine that supports 14 programming languages. Finally, we systematically evaluate and analyze eight mainstream LLMs and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks. The CodeScope benchmark and code are publicly available at https://***/WeixiangYAN/CodeScope. © 2023, CC BY-SA.

关键词： Software design

Semantic Visual Simultaneous Localization and Mapping: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Kaiqi Xiao, Junhao Liu, Jialing Tong, Qiyi Zhang, Heng Liu, Ruyu Zhang, Jianhua Ajoudani, Arash Chen, Shengyong Institute of Computer Vision College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Human-Robot Interfaces and Interaction Lab Istituto Italiano di Tecnologia Genoa Italy National University of Defense Technology China Università di Genova Genoa Italy School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Institute of Computer Vision School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

Visual Simultaneous Localization and Mapping (vSLAM) has achieved great progress in the computer vision and robotics communities, and has been successfully used in many fields such as autonomous robot navigation and AR/VR. However, vSLAM cannot achieve good localization in dynamic and complex environments. Numerous publications have reported that, by combining with the semantic information with vSLAM, the semantic vSLAM systems have the capability of solving the above problems in recent years. Nevertheless, there is no comprehensive survey about semantic vSLAM. To fill the gap, this paper first reviews the development of semantic vSLAM, explicitly focusing on its strengths and differences. Secondly, we explore three main issues of semantic vSLAM: the extraction and association of semantic information, the application of semantic information, and the advantages of semantic vSLAM. Then, we collect and analyze the current state-of-the-art SLAM datasets which have been widely used in semantic vSLAM systems. Finally, we discuss future directions that will provide a blueprint for the future development of semantic vSLAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jung, Harim Oh, Myeong-Seok Yang, Cheoljong Lee, Seong-Whan Dept. Artificial Intelligence Korea University Seoul Korea Republic of Dept. Computer Engineering Korea University Seoul Korea Republic of Vision AI Lab AI Center NCSOFT Seongnam Korea Republic of

Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. However, image classification and object detection are essentially different tasks and there is no guarantee that the optimal backbone for classification is also optimal for object detection. Recent neural architecture search (NAS) research has demonstrated that automatically designing a backbone specifically for object detection helps improve the overall accuracy. In this paper, we introduce a neural architecture adaptation method that can optimize the given backbone for detection purposes, while still allowing the use of pre-trained parameters. We propose to adapt both the micro- and macro-architecture by searching for specific operations and the number of layers, in addition to the output channel dimensions of each block. It is important to find the optimal channel depth, as it greatly affects the feature representation capability and computation cost. We conduct experiments with our searched backbone for object detection and demonstrate that our backbone outperforms both manually designed and searched state-of-the-art backbones on the COCO dataset. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection