检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Hu, Yanting Gao, Xinbo Li, Jie Huang, Yuanfei Wang, Hanzi Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xian710071 China State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xian710071 China Fujian Key Laboratory of Sensing and Computing for Smart City School of Information Science and Engineering Xiamen University China

The deep convolutional neural networks have achieved significant improvements in accuracy and speed for single image super-resolution. However, as the depth of network grows, the information flow is weakened and the training becomes harder and harder. On the other hand, most of the models adopt a single-stream structure with which integrating complementary contextual information under different receptive fields is difficult. To improve information flow and to capture sufficient knowledge for reconstructing the high-frequency details, we propose a cascaded multi-scale cross network (CMSC) in which a sequence of subnetworks is cascaded to infer high resolution features in a coarse-to-fine manner. In each cascaded subnetwork, we stack multiple multi-scale cross (MSC) modules to fuse complementary multi-scale information in an efficient way as well as to improve information flow across the layers. Meanwhile, by introducing residual-features learning in each stage, the relative information between high-resolution and low-resolution features is fully utilized to further boost reconstruction performance. We train the proposed network with cascaded-supervision and then assemble the intermediate predictions of the cascade to achieve high quality image reconstruction. Extensive quantitative and qualitative evaluations on benchmark datasets illustrate the superiority of our proposed method over state-of-the-art super-resolution methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution

arXiv

引用

arXiv 2021年

作者： Huang, Yuanfei Li, Jie Hu, Yanting Gao, Xinbo Huang, Hua School of Artificial Intelligence Beijing Normal University Beijing100875 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi’an710071 China School of Medical Engineering and Technology Xinjiang Medical University Urumqi830011 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China School of Electronic Engineering Xidian University Xi’an710071 China

Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors. To address it, this paper proposes a transitional learning method for blind SR using an end-to-end network without any additional iterations in inference, and explores an effective representation for unknown degradation. To begin with, we analyze and demonstrate the transitionality of degradations as interpretable prior information to indirectly infer the unknown degradation model, including the widely used additive and convolutive degradations. We then propose a novel Transitional Learning method for blind Super-Resolution (TLSR), by adaptively inferring a transitional transformation function to solve the unknown degradations without any iterative operations in inference. Specifically, the end-to-end TLSR network consists of a degree of transitionality (DoT) estimation network, a homogeneous feature extraction network, and a transitional learning module. Quantitative and qualitative evaluations on blind SR tasks demonstrate that the proposed TLSR achieves superior performances and costs fewer complexities against the state-of-the-art blind SR methods. The code is available at ***/YuanfeiHuang/TLSR. Copyright © 2021, 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

image-specific convolutional kernel modulation for single image super-resolution

arXiv

引用

arXiv 2021年

作者： Huang, Yuanfei Li, Jie Hu, Yanting Huang, Hua Gao, Xinbo School of Artificial Intelligence Beijing Normal University Beijing100875 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi’an710071 China School of Medical Engineering and Technology Xinjiang Medical University Urumqi830011 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China School of Electronic Engineering Xidian University Xi’an710071 China

—Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples. Yet intuitively, each image has its representation, and is expected to acquire an adaptive model. For this issue, we propose a novel image-specific convolutional kernel modulation (IKM) by exploiting the global contextual information of image or feature to generate an attention weight for adaptively modulating the convolutional kernels, which outperforms the vanilla convolution and several existing attention mechanisms while embedding into the state-of-the-art architectures without any additional parameters. Particularly, to optimize our IKM in mini-batch training, we introduce an image-specific optimization (IsO) algorithm, which is more effective than the conventional mini-batch SGD optimization. Furthermore, we investigate the effect of IKM on the state-of-the-art architectures and exploit a new backbone with U-style residual learning and hourglass dense block learning, terms U-Hourglass Dense Network (U-HDN), which is an appropriate architecture to utmost improve the effectiveness of IKM theoretically and experimentally. Extensive experiments on single image super-resolution show that the proposed methods achieve superior performances over state-of-the-art methods. Code is available at ***/YuanfeiHuang/IKM. Copyright © 2021, The Authors. All rights reserved.

关键词： Modulation

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention Guided Dual-Teacher Adaptive Knowledge Distillation for image Classification

SSRN

引用

SSRN 2023年

作者： Ma, Dongtong Zhang, Kaibing Cao, Qizhi Li, Jie Gao, Xinbo School of Electronics and Information Xi’an Polytechnic University Xi'An710048 China School of Computer Science Xi’an Polytechnic University Xi'An710048 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi’an710071 China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China

Knowledge distillation (KD) refers to transferring the knowledge learned from a teacher network with complex architecture and strong learning ability to another student network with light-weight and weak learning ability through a specific distillation strategy. However, most existing KD approaches to image classification often employ a single teacher network to guide the training of the student network. When the teacher network makes an erroneous prediction, the transferred knowledge will deteriorate the performance of the student network. To address or mitigate the above issue, we develop a novel KD approach called Coordinate Attention Guided Dual-Teacher Adaptive Knowledge Distillation (CAG-DAKD), to deliver more discriminative and comprehensive knowledge obtained from two teacher networks to a compact student network. Specifically, we integrate the positive prediction distribution of two teacher networks according to whether the two teacher networks predict correctly and the magnitude of the cross-entropy to deliver better output distribution to guide the student network. Furthermore, to distill the most valuable knowledge from the first teacher network that has a similar architecture to the student network, a coordinate attention mechanism is introduced into different layers of the first teacher network so that the student network can effectively learn more discriminative feature representations. We conduct extensive experiments on three standard image classification datasets: CIFAR10, CIFAR100, and imageNet to verify the superiority of the proposed method over other state-of-the-art competitors. © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Interactive curved planar reformation based on snake model

引用

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society 2008年第8期32卷 662-9页

作者： Xinrong Lv Xinbo Gao Hua Zou Video/Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an 710071 China. lxr1182@***

Visualization of tortuous tissues such as tracheas plays a very important role in medical image processing. Displaying them in a curved plane for diagnosis is a better function which is called curved planar reformation (CPR). In this manuscript, we use snake model to generate contours of tubular structures in all slices selected by users of medical volume data sets. Then, centerline of these structures can be obtained. CPR of these structures segmented by snake model is realized based on the obtained contours and centerlines. We use B-spline to generate a contour along tubular structures through points determined by mouse in three view planes. An improved method is used to initialize a snake contours before using gradient vector flow (GVF) snake model generating the final contour. A head aneurysm data set scanned with computed tomography (CT) is used to illustrate the performance of our CPR method. Furthermore some enhancements are introduced to our method: adjustment of window width and window level, rotating CPR.

关键词： Curved planar reformation Tubular structures B-spline GVF snake Computed tomography

来源：评论

学校读者我要写书评

暂无评论

Learning to Rank for Blind image Quality Assessment

引用

IEEE Transactions on Neural Networks and Learning systems 2015年第10期26卷 2275-2290页

作者： Gao, Fei Tao, Dacheng Gao, Xinbo Li, Xuelong Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an710071 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology 235 Jones Street Sydney UltimoNSW2007 Australia State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an710071 China State Key Laboratory of Transient Optics and Photonics Xi'An Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi710119 China

Blind image quality assessment (BIQA) aims to predict perceptual image quality scores without access to reference images. State-of-the-art BIQA methods typically require subjects to score a large number of images to train a robust model. However, subjective quality scores are imprecise, biased, and inconsistent, and it is challenging to obtain a large-scale database, or to extend existing databases, because of the inconvenience of collecting images, training the subjects, conducting subjective experiments, and realigning human quality evaluations. To combat these limitations, this paper explores and exploits preference image pairs (PIPs) such as the quality of image Iais better than that of image Ibfor training a robust BIQA model. The preference label, representing the relative quality of two images, is generally precise and consistent, and is not sensitive to image content, distortion type, or subject identity;such PIPs can be generated at a very low cost. The proposed BIQA method is one of learning to rank. We first formulate the problem of learning the mapping from the image features to the preference label as one of classification. In particular, we investigate the utilization of a multiple kernel learning algorithm based on group lasso to provide a solution. A simple but effective strategy to estimate perceptual image quality scores is then presented. Experiments show that the proposed BIQA method is highly effective and achieves a performance comparable with that of state-of-the-art BIQA algorithms. Moreover, the proposed method can be easily extended to new distortion categories. © 2012 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

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：