检索结果-内蒙古大学图书馆

Stereo endoscopic image super-resolution using disparity-constrained parallel attention

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Tianyi Gu, Yun Huang, Xiaolin Tu, Enmei Yang, Jie Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

With the popularity of stereo cameras in computer assisted surgery techniques, a second viewpoint would provide additional information in surgery. However, how to effectively access and use stereo information for the super-resolution (SR) purpose is often a challenge. In this paper, we propose a disparity-constrained stereo super-resolution network (DCSSRnet) to simultaneously compute a super-resolved image in a stereo image pair. In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules. Experiment results on laparoscopic images demonstrate that the proposed framework outperforms current SR methods on both quantitative and qualitative evaluations. Our DCSSRnet provides a promising solution on enhancing spatial resolution of stereo image pairs, which will be extremely beneficial for the endoscopic surgery. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power

Learning from partially labeled data 28

学校读者我要写书评

暂无评论

Learning from partially labeled data

28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2020

作者： Mehrkanoon, Siamak Huang, Xiaolin Suykens, Johan A.K. Department of Data Science and Knowledge Engineering Maastricht University Netherlands Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Department of Electrical Engineering ESAT-STADIUS KU Leuven LeuvenB-3001 Belgium

ISBN: (纸本)9782875870742

Providing sufficient labeled training data in many application domains is a laborious and costly task. Designing models that can learn from partially labeled data, or leveraging labeled data in one domain and unlabeled data in a different but related domain is of great interest in many applications. In particular, in this context one can refer to semi-supervised modelling, transfer learning, domain adaptation and multi-view learning among oth- ers. There are several possibilities for designing such models ranging from shallow to deep models. These type of models have received increasing in- terest due to their successful applications in real-life problems. This paper provides a brief overview of recent techniques in learning from partially labeled data. © ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

关键词： Neural networks

Random Fourier Features for Asymmetric kernels

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Mingzhen He, Fan Liu, Fanghui Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University 800 Dongchuan RD. Minhang District Shanghai200240 China Laboratory for Information and Inference Systems École Polytechnique Fédérale de Lausanne EPFL SV-BMC AA-B118 Lausanne1015 Switzerland

The random Fourier features (RFFs) method is a powerful and popular technique in kernel approximation for scalability of kernel methods. The theoretical foundation of RFFs is based on the Bochner theorem (Bochner, 2005) that relates symmetric, positive definite (PD) functions to probability measures. This condition naturally excludes asymmetric functions with a wide range applications in practice, e.g., directed graphs, conditional probability, and asymmetric kernels. Nevertheless, understanding asymmetric functions (kernels) and its scalability via RFFs is unclear both theoretically and empirically. In this paper, we introduce a complex measure with the real and imaginary parts corresponding to four finite positive measures, which expands the application scope of the Bochner theorem. By doing so, this framework allows for handling classical symmetric, PD kernels via one positive measure;symmetric, non-positive definite kernels via signed measures;and asymmetric kernels via complex measures, thereby unifying them into a general framework by RFFs, named AsK-RFFs. Such approximation scheme via complex measures enjoys theoretical guarantees in the perspective of the uniform convergence. In algorithmic implementation, to speed up the kernel approximation process, which is expensive due to the calculation of total mass, we employ a subset-based fast estimation method that optimizes total masses on a sub-training set, which enjoys computational efficiency in high dimensions. Our AsK-RFFs method is empirically validated on several typical large-scale datasets and achieves promising kernel approximation performance, which demonstrate the effectiveness of AsK-RFFs. © 2022, CC BY.

关键词： Computational efficiency

Generalization properties of hyper-RKHS and its applications

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2021年第1期22卷 6220-6257页

作者： Fanghui Liu Lei Shi Xiaolin Huang Jie Yang Johan A.K. Suykens Department of Electrical Engineering ESAT-STADIUS KU Leuven Leuven Belgium Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view. Algorithmically, we consider two regularized regression models with bivariate forms in this space, including kernel ridge regression (KRR) and support vector regression (SVR) endowed with hyper-RKHS, and further combine divide-and-conquer with Nyström approximation for scalability in large sample cases. This framework is general: the underlying kernel is learned from a broad class, and can be positive definite or not, which adapts to various requirements in kernel learning. Theoretically, we study the convergence behavior of regularized regression algorithms in hyper-RKHS and derive the learning rates, which goes beyond the classical analysis on RKHS due to the non-trivial independence of pairwise samples and the characterisation of hyper-RKHS. Experimentally, results on several benchmarks suggest that the employed framework is able to learn a general kernel function form an arbitrary similarity matrix, and thus achieves a satisfactory performance on classification tasks.

关键词： hyper-RKHS approximation theory kernel learning out-of-sample extensions

Indoor Elderly Fall recognition System Based on Target Detection and Self-attention Model

学校读者我要写书评

暂无评论

Indoor Elderly Fall Recognition System Based on Target Detec...

International Conference on Electronics, Communications and Information Technology (CECIT)

作者： Min Liu Xufeng Ling Jie Yang School of Health Tianhua College Shanghai Normal University Shanghai China AI School Tianhua College Shanghai Normal University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China

ISBN: (纸本)9781665437585

With the increasing aging of the society, a series of consequences caused by falls of the elderly have become a serious medical problem and a real social problem. Aiming at the fall behavior of the elderly, the research and development of human fall recognition technology has practical application value. This paper proposes a method to recognize human targets in indoor images using target detection technology, and then use the trained neural network based on Self-attention technique named Vision Transformer (ViT) to recognize the falling posture of the elderly. Firstly, the target detection model is optimized and trained for indoor scene, so that the model can accurately detect human targets in indoor scene; Next, the indoor scene human target image is preprocessed, and the indoor human pose image data set is constructed; Then, the data set is used to train the ViT depth network, and enable it to correctly classify five postures (standing, sitting, lying, bending and crawling). The experimental results show that ViT network achieves high accuracy and excellent generalization capacity for the above 5 human posture and can realize the recognition of elderly falls.

关键词： Technological innovation image recognition Target recognition Object detection Transformers Data models Robustness

Fast learning in reproducing kernel Kreĭn spaces via signed measures

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Fanghui Huang, Xiaolin Chen, Yingyi Suykens, Johan A.K. KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University China

In this paper, we attempt to solve a long-lasting open question for non-positive definite (non-PD) kernels in machine learning community: can a given non-PD kernel be decomposed into the difference of two PD kernels (termed as positive decomposition)? We cast this question as a distribution view by introducing the signed measure, which transforms positive decomposition to measure decomposition: a series of non-PD kernels can be associated with the linear combination of specific finite Borel measures. In this manner, our distribution-based framework provides a sufficient and necessary condition to answer this open question. Specifically, this solution is also computationally implementable in practice to scale non-PD kernels in large sample cases, which allows us to devise the first random features algorithm to obtain an unbiased estimator. Experimental results on several benchmark datasets verify the effectiveness of our algorithm over the existing methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

Asymmetric correlation quantization hashing for cross-modal retrieval

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Lu Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai201100 China Shanghai Jiao Tong University

Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, crossmodal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities. However, there are still some limitations to be further taken into account: (1) most current CMH methods transform real-valued data points into discrete compact binary codes under the binary constraints, limiting the capability of representation for original data on account of abundant loss of information and producing suboptimal hash codes;(2) the discrete binary constraint learning model is hard to solve, where the retrieval performance may greatly reduce by relaxing the binary constraints for large quantization error;(3) handling the learning problem of CMH in a symmetric framework, leading to difficult and complex optimization objective. To address above challenges, in this paper, a novel Asymmetric Correlation Quantization Hashing (ACQH) method is proposed. Specifically, ACQH learns the projection matrixes of heterogeneous modalities data points for transforming query into a low-dimensional real-valued vector in latent semantic space and constructs the stacked compositional quantization embedding in a coarse-to-fine manner for indicating database points by a series of learnt real-valued codeword in the codebook with the help of pointwise label information regression simultaneously. Besides, the unified hash codes across modalities can be directly obtained by the discrete iterative optimization framework devised in the paper. Comprehensive experiments on diverse three benchmark datasets have shown the effectiveness and rationality of ACQH. Copyright © 2020, The Authors. All rights reserved.

关键词： Hash functions

FDFlowNet: Fast optical flow estimation using a deep lightweight network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kong, Lingtong Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this work, we present a lightweight yet effective model for real-time optical flow estimation, termed FDFlowNet (fast deep flownet). We achieve better or similar accuracy on the challenging KITTI and Sintel benchmarks while being about 2 times faster than PWC-Net. This is achieved by a carefully-designed structure and newly proposed components. We first introduce an U-shape network for constructing multi-scale feature which benefits upper levels with global receptive field compared with pyramid network. In each scale, a partial fully connected structure with dilated convolution is proposed for flow estimation that obtains a good balance among speed, accuracy and number of parameters compared with sequential connected and dense connected structures. Experiments demonstrate that our model achieves state-of-the-art performance while being fast and lightweight. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical flows

Self-adapting RF Stealth Signal Design Method in RATR

学校读者我要写书评

暂无评论

Transactions of Nanjing University of Aeronautics and Astronautics 2021年第6期38卷 1020-1027页

作者： XIAO Yongsheng HUANG Lizhen HE Fengshou ZHOU Jianjiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong UniversityNanchang 330063P.R.China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106P.R.China Leihua Electronic Technology Research Institute Aviation Industry Corporation of ChinaLtd.Wuxi 214063P.R.China

Combining the mutual information theory and the sequential hypothesis testing(SHT)method,a selfadapting radio frequency(RF)stealth signal design method is proposed. The channel information is gained through the radar echo and feeds back to the radar system,and then the radar system adaptively designs the transmission waveform. So the close-loop system is formed. The correlations between these transmission waveforms are decreased because of the adaptive change of these transmission waveforms,and the number of illuminations is reduced for adopting the SHT,which lowers the transmission power of the radar system. The radar system using the new method possesses the RF stealth performance. Aiming at the application of radar automatic target recognition(RATR),experimental simulations show the effectiveness and feasibility of the proposed method.

关键词： radio frequency stealth sequential hypothesis testing mutual information close-loop system