检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Xin Jin, Xin Fu, Jun Yu, Xiaoyuan Tong, Bei Chen, Zhibo The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The Eastern Institute for Advanced Study China Huawei Cloud China

Collecting amounts of distorted/clean image pairs in the real world is non-trivial, which seriously limits the practical applications of these supervised learning-based methods on real-world image super-resolution (RealSR). Previous works usually address this problem by leveraging unsupervised learning-based technologies to alleviate the dependency on paired training samples. However, these methods typically suffer from unsatisfactory texture synthesis due to the lack of supervision of clean images. To overcome this problem, we are the first to have a close look at the under-explored direction for RealSR, i.e., few-shot real-world image super-resolution, which aims to tackle the challenging RealSR problem with few-shot distorted/clean image pairs. Under this brand-new scenario, we propose Distortion Relation guided Transfer Learning (DRTL) for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions (i.e., synthetic distortions) to the target RealSR under the guidance of distortion relation. Concretely, DRTL builds a knowledge graph to capture the distortion relation between auxiliary distortions and target distortion (i.e., real distortions in RealSR). Based on the distortion relation, DRTL adopts a gradient reweighting strategy to guide the knowledge transfer process between auxiliary distortions and target distortions. In this way, DRTL could quickly learn the most relevant knowledge from the synthetic distortions for the target distortion. We instantiate DRTL with two commonly-used transfer learning paradigms, including pre-training and meta-learning pipelines, to realize a distortion relation-aware Few-shot RealSR. Extensive experiments on multiple benchmarks and thorough ablation studies demonstrate the effectiveness of our DRTL. Copyright © 2021, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Towards Hybrid-Optimization Video Coding

arXiv

引用

arXiv 2022年

作者： Huo, Shuai Liu, Dong Li, Li Ma, Siwei Wu, Feng Gao, Wen The Cas Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The Institute of Digital Media Peking University Beijing100871 China

Video coding is a mathematical optimization problem of rate and distortion essentially. To solve this complex optimization problem in practice, two popular video coding frameworks have been developed: block-based hybrid video coding and end-to-end learned video coding. If we rethink video coding from the perspective of optimization, we find that the existing two frameworks represent two directions of optimization solutions. Block-based hybrid video coding represents the discrete optimization solution because those irrelevant coding modes are discrete in mathematics. The discrete solution provides multiple starting points (i.e. modes) in global optimization space and then searches for the best one among them. However, the search-based optimization algorithm is not efficient enough. On the other hand, end-to-end learned video coding represents the continuous optimization solution because the optimization algorithm of deep learning, gradient descent, is based on a continuous function. The continuous solution optimizes a group of model parameters efficiently by such a numerical algorithm. However, limited by only one starting point, it is easy to fall into the local optimum. To better solve the optimization problem, we propose a hybrid of discrete and continuous optimization video coding. We regard video coding as a hybrid of the discrete and continuous optimization problem, and use both search and numerical algorithm to solve it. Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently. Finally, we search for the global optimum among those local optimums. Guided by the hybrid optimization idea, we design a hybrid optimization video coding framework, which is built on continuous deep networks entirely and also contains some discrete modes. We conduct a comprehensive set of experiments to verify the efficiency of our hybrid optimization. Compared to the continuous opti

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

HIGH QUALITY REMOTE SENSING IMAGE SUPER-RESOLUTION USING DEEP MEMORY CONNECTED NETWORK

HIGH QUALITY REMOTE SENSING IMAGE SUPER-RESOLUTION USING DEE...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Wenjia Xu Guangluan Xu Yang Wang Xian Sun Daoyu Lin Yirong Wu Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the neural network usually have small receptive fields and ignore the image detail. We propose a novel method named deep memory connected network (DMCN) based on a convolutional neural network to reconstruct high-quality super-resolution images. We build local and global memory connections to combine image detail with environmental information. To further reduce parameters and ease time-consuming, we propose down-sampling units, shrinking the spatial size of feature maps. We test DMCN on three remote sensing datasets with different spatial resolution. Experimental results indicate that our method yields promising improvements in both accuracy and visual performance over the current state-of-the-art.

关键词： Spatial resolution Remote sensing Image reconstruction Training Convolutional neural networks Satellites

来源：评论

学校读者我要写书评

暂无评论

Phase Transition Analysis for Compressive Sensing Based DoA Estimation in Automotive Radar

Phase Transition Analysis for Compressive Sensing Based DoA ...

引用

International Radar Symposium (IRS)

作者： Yan Zhang Silin Gao Mingqian Liu Bingchen Zhang Yirong Wu Chinese Academy of Sciences Aerospace Information Research Institute Beijing China University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information and Processing Application System Beijing China

ISBN: (数字)9788394942151

ISBN: (纸本)9781728157863

In automotive radar applications, the compressive sensing (CS) based DoA estimation is used in array signal processing in recent years. Sparse reconstruction has the potential to estimate the direction of arrival (DoA) with super resolution. However, failed results may be acquired via sparse reconstruction in inappropriate conditions, namely the critical condition determining success or failure must be taken into consideration. In this paper, the sparsity of the scenario and the signal-to-noise ratio (SNR) are analyzed as the main factors via phase transition diagrams. Other factors affecting the success or failure are also investigated, such as the array configuration and the sparse recovery algorithm. Simulated and experimental results demonstrate the critical conditions, in which the DoA estimation is successful or failed.

关键词： Direction-of-arrival estimation Estimation Radar applications Compressed sensing Signal resolution Signal to noise ratio Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

SFDFNet: Single-path Feature Deep Fusion Network for Fast Semantic Segmentation of SAR Images in Building Areas

SFDFNet: Single-path Feature Deep Fusion Network for Fast Se...

引用

IET International Radar Conference 2023, IRC 2023

作者： Zhang, Wenyi Dai, Xiangyu Chu, Qingwei Zhang, Jiande Ding, Hao Li, Guangzuo Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences No. 9 Dengzhuang South Road Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences No. 19 Yuquan Road Beijing China QiLu Aerospace Information Research Institute No. 44 Industry North Road Jinan China

ISBN: (纸本)9781839539954

With the SAR satellites have gradually become one of the most important methods of Earth observation, rapid interpretation of SAR images has become particularly important. However, the unique imaging mechanism of SAR makes its interpretation very difficult. In this paper, we propose the SFDFNet, a deep learning-based fast segmentation method for SAR image buildings, to address the problem of difficult SAR image interpretation. A bottleneck layer of buffered large receptive field is designed in the downsampling process. The unique design of the number of channels reduces the amount of computation without affecting the extraction of information. Meanwhile, improving on the ECA module, a two-layer ECA module was proposed to increase the receptive field and improve the linear expression. Experiments show that the proposed network has excellent results in segmentation accuracy and inference speed. © The Institution of Engineering & technology 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Visual analyses of music history: A user-centric approach

arXiv

引用

arXiv 2017年

作者： Zhang, Jingxian Liu, Dong Media Lab Massachusetts Institute of Technology CambridgeMA02139 United States CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Music history, referring to the records of users' listening or downloading history in online music services, is the primary source for music service providers to analyze users' preferences on music and thus to provide personalized recommendations to users. In order to engage users into the service and to improve user experience, it would be beneficial to provide visual analyses of one user's music history as well as visualized recommendations to that user. In this paper, we take a user-centric approach to the design of such visual analyses. We start by investigating user needs on such visual analyses and recommendations, then propose several different visualization schemes, and perform a pilot study to collect user feedback on the designed schemes. We further conduct user studies to verify the utility of the proposed schemes, and the results not only demonstrate the effectiveness of our proposed visualization, but also provide important insights to guide the visualization design in the future. Copyright © 2017, The Authors. All rights reserved.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

DeepEraser: Deep Iterative Context Mining for Generic Text Eraser

arXiv

引用

arXiv 2024年

作者： Feng, Hao Wang, Wendi Liu, Shaokai Deng, Jiajun Zhou, Wengang Li, Houqiang The CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The University of Adelaide Australian Institute for Machine Learning Australia

In this work, we present DeepEraser, an effective deep network for generic text removal. DeepEraser utilizes a recurrent architecture that erases the text in an image via iterative operations. Our idea comes from the process of erasing pencil script, where the text area designated for removal is subject to continuous monitoring and the text is attenuated progressively, ensuring a thorough and clean erasure. Technically, at each iteration, an innovative erasing module is deployed, which not only explicitly aggregates the previous erasing progress but also mines additional semantic context to erase the target text. Through iterative refinements, the text regions are progressively replaced with more appropriate content and finally converge to a relatively accurate status. Furthermore, a custom mask generation strategy is introduced to improve the capability of DeepEraser for adaptive text removal, as opposed to indiscriminately removing all the text in an image. Our DeepEraser is notably compact with only 1.4M parameters and trained in an end-to-end manner. To verify its effectiveness, extensive experiments are conducted on several prevalent benchmarks, including SCUT-Syn, SCUT-EnsText, and Oxford Synthetic text dataset. The quantitative and qualitative results demonstrate the effectiveness of our DeepEraser over the state-of-the-art methods, as well as its strong generalization ability in custom mask text removal. The codes and pre-trained models are available at https://***/fh2019ustc/DeepEraser Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Progressive unsupervised person re-identification by tracklet association with spatio-temporal regularization

arXiv

引用

arXiv 2019年

作者： Xie, Qiaokang Zhou, Wengang Qi, Guo-Jun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Huawei Cloud EI Product Department Huawei Noah's Ark Laboratory

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model. To facilitate the study, we have collected a new 4K UHD video dataset named Campus-4K with full frames and full spatio-temporal information. Experimental results show that with the spatio-temporal constraint in the training phase, the proposed approach outperforms the state-of-the-art unsupervised methods by notable margins on DukeMTMC-reID, and achieves competitive performance to fully supervised methods on both DukeMTMC-reID and Campus-4K datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An Improved Imaging Method for Highly-Squinted SAR Based on Hyper-Optimized Admm

An Improved Imaging Method for Highly-Squinted SAR Based on ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Tiancheng Chen Yang Meng Guoru Zhou Zhe Zhang Bingchen Zhang Yirong Wu Aerospace Information Research Institute Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

Highly-squinted synthetic aperture radar (SAR) echo has the characteristic of severe range-azimuth coupling, requiring specialized imaging algorithms. applications of compressed sensing in SAR imaging can effectively improve the resolution and other indicators. However, inaccurate manual parameters can affect the algorithm output. This article proposes an improved alternating direction method of multipliers (ADMM) for solving sparse reconstruction models under highly-squinted conditions. By adaptively adjusting the penalty parameter in ADMM via hyper-gradient descent (HD), the problem caused by inaccurate manual parameter is solved. Compared with matched filtering methods and other optimization methods, this method can suppress noise and speed up convergence. The effectiveness of the proposed method can be validated through the approximate observation of both simulated scenes and real scenes captured by the GF-3 SAR satellite.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plug-And-Play TomoSAR Imaging With Prior information

Plug-And-Play TomoSAR Imaging With Prior Information

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Kun Wang Jie Li Yizhe Fan Bingchen Zhang Aerospace Information Research Institute Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Synthetic aperture radar (SAR) tomography (TomoSAR) is an advanced remote sensing technology that has the ability to acquire three-dimensional information of targets. To enhance target features, different reaularization terms, including L 1 norm, total variation norm, and morphology term, have been introduced into the TomoSAR inversion model. However, there is a lack of attention to establishing a TomoSAR imaging framework with a modular structure that provides flexibility in specifically enhancing different features. In this article, a novel 3D tomographic reconstruction framework based on plug-and-play (PnP) priors and Alternating Direction Method of Multipliers (ADMM) is proposed. The PnP-ADMM framework achieves flexibility through the selection of appropriate priors for the features of targets, leading to a trade-off between the performance of feature enhancement and computational complexity. Simulation and real data experiments verify the effectiveness of the proposed method in flexibly selecting priors for feature enhancement of specific targets.

关键词： Radar remote sensing Three-dimensional displays Morphology Tomography Apertures Convex functions Computational complexity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：