检索结果-内蒙古大学图书馆

PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Deng, Zhongchen Yang, Zhechen Chen, Chi Zeng, Cheng Meng, Yan Yang, Bisheng School of Computer Science and Information Engineering Hubei University Hubei Wuhan430062 China School of Artificial Intelligence Hubei University Hubei Wuhan430062 China Ministry of Education Hubei Wuhan430062 China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Hubei Wuhan430072 China Engineering Research Center of Space-Time Data Capturing and Smart Application The Ministry of Education of P.R.C. Hubei Wuhan430072 China Institute of Geospatial Intelligence Wuhan University Hubei Wuhan430072 China

Plane instance segmentation from RGB-D data is a crucial research topic for many downstream tasks, such as indoor 3D reconstruction. However, most existing deep-learning-based methods utilize only information within the RGB bands, neglecting the important role of the depth band in plane instance segmentation. Based on EfficientSAM, a fast version of the Segment Anything Model (SAM), we propose a plane instance segmentation network called PlaneSAM, which can fully integrate the information of the RGB bands (spectral bands) and the D band (geometric band), thereby improving the effectiveness of plane instance segmentation in a multimodal manner. Specifically, we use a dual-complexity backbone, with primarily the simpler branch learning D-band features and primarily the more complex branch learning RGB-band features. Consequently, the backbone can effectively learn D-band feature representations even when D-band training data is limited in scale, retain the powerful RGB-band feature representations of EfficientSAM, and allow the original backbone branch to be fine-tuned for the current task. To enhance the adaptability of our PlaneSAM to the RGB-D domain, we pretrain our dual-complexity backbone using the segment anything task on large-scale RGB-D data through a self-supervised pretraining strategy based on imperfect pseudo-labels. To support the segmentation of large planes, we optimize the loss function combination ratio of EfficientSAM. In addition, Faster R-CNN is used as a plane detector, and its predicted bounding boxes are fed into our dual-complexity network as prompts, thereby enabling fully automatic plane instance segmentation. Experimental results show that the proposed PlaneSAM sets a new state-of-the-art (SOTA) performance on the ScanNet dataset, and outperforms previous SOTA approaches in zero-shot transfer on the 2D-3D-S, Matterport3D, and ICL-NUIM RGB-D datasets, while only incurring a 10% increase in computational overhead compared to EfficientSAM. Ou

关键词： 3D reconstruction

Rethinking CNN-based pansharpening: Guided colorization of panchromatic images via GANs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ozcelik, Furkan Alganci, Ugur Sertel, Elif Unal, Gozde Department of Computer Engineering ITU-AI: Artificial Intelligence and Data Science Research and Application Center Turkey Turkey

Convolutional Neural Networks (CNN)-based approaches have shown promising results in pansharpening of satellite images in recent years. However, they still exhibit limitations in producing high-quality pansharpening outputs. To that end, we propose a new self-supervised learning framework, where we treat pansharpening as a colorization problem, which brings an entirely novel perspective and solution to the problem compared to existing methods that base their solution solely on producing a super-resolution version of the multispectral image. Whereas CNN-based methods provide a reduced resolution panchromatic image as input to their model along with reduced resolution multispectral images, hence learn to increase their resolution together, we instead provide the grayscale transformed multispectral image as input, and train our model to learn the colorization of the grayscale input. We further address the fixed downscale ratio assumption during training, which does not generalize well to the full-resolution scenario. We introduce a noise injection into the training by randomly varying the downsampling ratios. Those two critical changes, along with the addition of adversarial training in the proposed PanColorization Generative Adversarial Networks (PanColorGAN) framework, help overcome the spatial detail loss and blur problems that are observed in CNN-based pansharpening. The proposed approach outperforms the previous CNN-based and traditional methods as demonstrated in our experiments. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Keser, Reyhan Kevser Ayanzadeh, Aydin Aghdam, Omid Abdollahi Kilcioglu, Caglar Toreyin, Behcet Ugur Ure, Nazim Kemal Research Group Informatics Institute Istanbul Technical University Turkey Department of Computer Science and Electrical Engineering University of Maryland Baltimore County United States Arcelik Research and Development Turkey Artificial Intelligence and Data Science Application and Research Center Istanbul Technical University Turkey

One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our method is applicable for any student network, once it is applied on a chosen teacher network. The proposed approach is validated in CIFAR-100 and ImageNet datasets, using various teacher-student pairs and numerous hint distillation methods. Our results show that hint points selected by our algorithm results in superior compression performance compared to state-of-the-art knowledge distillation algorithms on the same student models and datasets. © 2021, CC BY-NC-ND.

关键词： Distillation

RETRACTED ARTICLE: Obstacles Uncovering System for Slender Pathways Using Unmanned Aerial Vehicles with Automatic Image Localization Technique

学校读者我要写书评

暂无评论

International Journal of Computational intelligence systems 2023年第1期16卷 1-14页

作者： Selvarajan, Shitharth Manoharan, Hariprasath Khadidos, Alaa O. Shankar, Achyut Khadidos, Adil O. Onyema, Edeh Michael Department of Computer Science Kebri Dehar University Kebri Dehar Ethiopia School of Built Environment Engineering and Computing Leeds Beckett University Leeds UK Department of Electronics and Communication Engineering Panimalar Engineering College Chennai India Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Center of Research Excellence in Artificial Intelligence and Data Science King Abdulaziz University Jeddah Saudi Arabia Secure Cyber Systems Research Group (SCSRG) WMG University of Warwick Coventry UK School of Computer Science Engineering Lovely Professional University Phagwara India Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Mathematics and Computer Science Coal City University Enugu Nigeria

In this study, unidentified flying machines are built with real-time monitoring in mid-course settings for obstacle avoidance in mind. The majority of the currently available methods are implemented as comprehensive monitoring systems, with significant success in monitored applications like bridges, railways, etc. So, the predicted model is developed exclusively for specific monitoring settings, as opposed to the broad conditions that are used by the current approaches. Also, in the design model, the first steps are taken by limiting the procedure to specific heights, and the input thrust that is provided for take up operation is kept to a minimum. Due to the improved altitudes, the velocity and acceleration units have been cranked up on purpose, making it possible to sidestep intact objects. In addition, Advanced Image Mapping Localization (AIML) is used to carry out the implementation process, which identifies stable sites at the correct rotation angle. Besides, Cyphal protocol integration improves the security of the data-gathering process by transmitting information gathered from sensing devices. The suggested system is put to the test across five different case studies, where the designed Unmanned aerial vehicle can able to detect 25 obstacles in the narrow paths in considered routs but existing approach can able to identify only 14 obstacle in the same routes.

关键词：

Undamped soliton-like domain wall motion in sliding ferroelectrics

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shi, Yubai Gao, Yuxiang He, Ri Wang, Hua Zhang, Binwen Zhong, Zhicheng CAS Key Laboratory of Magnetic Materials and Devices Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Center for Quantum Matter School of Physics Zhejiang University Hangzhou310058 China School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China Fujian Key Laboratory of Functional Marine Sensing Materials Center for Advanced Marine Materials and Smart Sensors College of Material and Chemical Engineering Minjiang University Fuzhou350108 China

Sliding ferroelectricity, which is a unique polarity recently discovered in bilayer van der Waals materials, achieves polarization switching through in-plane interlayer sliding. The unique mechanism, combining intralayer stiffness and interlayer slipperiness, leads to wider domain walls (DWs) and faster DW motion compared to conventional ferroelectrics. Herein, using machine-learning-assisted molecular dynamics simulations and field theory analysis, we find the DW in classical sliding ferroelectric bilayer 3R-MoS2 system exhibits uniformly accelerated motion under an external field, like the Newtonian particle with undamped motion. Remarkably, DW velocity remains constant even after the external field removal, completely deviating from the velocity breakdown observed in conventional ferroelectrics. We further propose an experimental approach to validate this undamped soliton-like DW behavior in sliding ferroelectric systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Van der Waals forces

GENERALIZATION IN data-DRIVEN MODELS OF PRIMARY VISUAL CORTEX 9

学校读者我要写书评

暂无评论

GENERALIZATION IN DATA-DRIVEN MODELS OF PRIMARY VISUAL CORTE...

9th International Conference on Learning Representations, ICLR 2021

作者： Lurz, Konstantin-Klemens Bashiri, Mohammad Willeke, Konstantin Jagadish, Akshay K. Wang, Eric Walker, Edgar Y. Cadena, Santiago A. Muhammad, Taliah Cobos, Erick Tolias, Andreas S. Ecker, Alexander S. Sinz, Fabian H. Institute for Bioinformatics and Medical Informatics University of Tübingen Germany International Max Planck Research School for Intelligent Systems Tübingen Germany Bernstein Center for Computational Neuroscience University of Tübingen Germany Department for Neuroscience Baylor College of Medicine HoustonTX United States Center for Neuroscience and Artificial Intelligence Baylor College of Medicine HoustonTX United States Department of Computer Science Campus Institute Data Science University of Göttingen Germany

Deep neural networks (DNN) have set new standards at predicting responses of neural populations to visual input. Most such DNNs consist of a convolutional network (core) shared across all neurons which learns a representation of neural computation in visual cortex and a neuron-specific readout that linearly combines the relevant features in this representation. The goal of this paper is to test whether such a representation is indeed generally characteristic for visual cortex, i.e. generalizes between animals of a species, and what factors contribute to obtaining such a generalizing core. To push all non-linear computations into the core where the generalizing cortical features should be learned, we devise a novel readout that reduces the number of parameters per neuron in the readout by up to two orders of magnitude compared to the previous state-of-the-art. It does so by taking advantage of retinotopy and learns a Gaussian distribution over the neuron's receptive field position. With this new readout we train our network on neural responses from mouse primary visual cortex (V1) and obtain a gain in performance of 7% compared to the previous state-of-the-art network. We then investigate whether the convolutional core indeed captures general cortical features by using the core in transfer learning to a different animal. When transferring a core trained on thousands of neurons from various animals and scans we exceed the performance of training directly on that animal by 12%, and outperform a commonly used VGG16 core pre-trained on imagenet by 33%. In addition, transfer learning with our data-driven core is more data-efficient than direct training, achieving the same performance with only 40% of the data. Our model with its novel readout thus sets a new state-of-the-art for neural response prediction in mouse visual cortex from natural images, generalizes between animals, and captures better characteristic cortical features than current task-driven pre-training appro

关键词： Neurons

Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Jing Cheng, Jian Li, Cheng Fan, Wenxin Zou, Juan Wu, Ruoyou Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Peng Cheng Laboratory Guangdong Shenzhen China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Yuhang District Hangzhou China

Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the in vivo human brain. However, to effectively capture the intricate characteristics of water diffusion at various directions and scales, it is important to employ comprehensive q-space sampling. Unfortunately, this requirement leads to long scan times, limiting the clinical applicability of dMRI. To address this challenge, we propose SSOR, a Simultaneous q-Space sampling Optimization and Reconstruction framework. We jointly optimize a subset of q-space samples using a continuous representation of spherical harmonic functions and a reconstruction network. Additionally, we integrate the unique properties of diffusion magnetic resonance imaging (dMRI) in both the q-space and image domains by applying l1-norm and total-variation *** experiments conducted on HCP data demonstrate that SSOR has promising strengths both quantitatively and qualitatively and exhibits robustness to noise. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Temporal networks provide a unifying understanding of the evolution of cooperation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Aming Meng, Yao Zhou, Lei Masuda, Naoki Wang, Long Center for Systems and Control College of Engineering Peking University Beijing100871 China Center for Multi-Agent Research Institute for Artificial Intelligence Peking University Beijing100871 China School of Automation Beijing Institute of Technology Beijing100081 China Department of Mathematics State University of New York at Buffalo BuffaloNY14260 United States Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo BuffaloNY14260 United States

Understanding the evolution of cooperation in structured populations represented by networks is a problem of long research interest, and a most fundamental and widespread property of social networks related to cooperation phenomena is that the node’s degree (i.e., number of edges connected to the node) is heterogeneously distributed. Previous results indicate that static heterogeneous (i.e., degree-heterogeneous) networks promote cooperation in stationarity compared to static regular (i.e., degree-homogeneous) networks if equilibrium dynamics starting from many cooperators and defectors is employed. However, the above conclusion reverses if we employ non-equilibrium stochastic processes to measure the fixation probability for cooperation, i.e., the probability that a single cooperator successfully invades a population. Here we resolve this conundrum by analyzing the fixation of cooperation on temporal (i.e., time-varying) networks. We theoretically prove and numerically confirm that on both synthetic and empirical networks, contrary to the case of static networks, temporal heterogeneous networks can promote cooperation more than temporal regular networks in terms of the fixation probability of cooperation. Given that the same conclusion is known for the equilibrium fraction of cooperators on temporal networks, the present results provide a unified understanding of the effect of temporal degree heterogeneity on promoting cooperation across two main analytical frameworks, i.e., equilibrium and non-equilibrium ones. Copyright © 2023, The Authors. All rights reserved.

关键词： Heterogeneous networks

Imitation dynamics on networks with incomplete information

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xiaochen Zhou, Lei McAvoy, Alex Li, Aming Center for Systems and Control College of Engineering Peking University Beijing100871 China School of Automation Beijing Institute of Technology Beijing100081 China School of Data Science and Society University of North Carolina at Chapel Hill Chapel HillNC27599 United States Department of Mathematics University of North Carolina at Chapel Hill Chapel HillNC27599 United States Center for Multi-Agent Research Institute for Artificial Intelligence Peking University Beijing100871 China

Imitation is an important learning heuristic in animal and human societies. Previous explorations report that the fate of individuals with cooperative strategies is sensitive to the protocol of imitation, leading to a conundrum about how different styles of imitation quantitatively impact the evolution of cooperation. Here, we take a different perspective on the personal and external social information required by imitation. We develop a general model of imitation dynamics with incomplete information in networked systems, which unifies classical update rules including the death-birth and pairwise-comparison rule on complex networks. Under pairwise interactions, we find that collective cooperation is most promoted if individuals neglect personal information. If personal information is considered, cooperators evolve more readily with more external information. Intriguingly, when interactions take place in groups on networks with low degrees of clustering, using more personal and less external information better facilitates cooperation. Our unifying perspective uncovers intuition by examining the rate and range of competition induced by different information situations. © 2023, CC BY.

关键词： Complex networks