检索结果-内蒙古大学图书馆

Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Fan He, Mingzhen Shi, Lei Huang, Xiaolin Suykens, Johan A.K. STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai200433 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

Ridgeless regression has garnered attention among researchers, particularly in light of the "Benign Overfitting" phenomenon, where models interpolating noisy samples demonstrate robust generalization. However, kernel ridgeless regression does not always perform well due to the lack of flexibility. This paper enhances kernel ridgeless regression with Locally-Adaptive-Bandwidths (LAB) RBF kernels, incorporating kernel learning techniques to improve performance in both experiments and theory. For the first time, we demonstrate that functions learned from LAB RBF kernels belong to an integral space of Reproducible Kernel Hilbert Spaces (RKHSs). Despite the absence of explicit regularization in the proposed model, its optimization is equivalent to solving an 0-regularized problem in the integral space of RKHSs, elucidating the origin of its generalization ability. Taking an approximation analysis viewpoint, we introduce an lq-norm analysis technique (with 0 © 2024, CC BY.

关键词： Vector spaces

Learn What You Need in Personalized Federated Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lv, Kexin Ye, Rui Huang, Xiaolin Yang, Jie Chen, Siheng Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Shanghai Jiao Tong University Shanghai200240 China Shanghai Jiao Tong University Shanghai200240 China Shanghai AI Laboratory Shanghai200232 China

Personalized federated learning aims to address data heterogeneity across local clients in federated learning. However, current methods blindly incorporate either full model parameters or predefined partial parameters in personalized federated learning. They fail to customize the collaboration manner according to each local client's data characteristics, causing unpleasant aggregation results. To address this essential issue, we propose Learn2pFed, a novel algorithm-unrolling-based personalized federated learning framework, enabling each client to adaptively select which part of its local model parameters should participate in collaborative training. The key novelty of the proposed Learn2pFed is to optimize each local model parameter's degree of participant in collaboration as learnable parameters via algorithm unrolling methods. This approach brings two benefits: 1) mathmatically determining the participation degree of local model parameters in the federated collaboration, and 2) obtaining more stable and improved solutions. Extensive experiments on various tasks, including regression, forecasting, and image classification, demonstrate that Learn2pFed significantly outperforms previous personalized federated learning methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Parameter estimation

Fdinet: Feature-Decomposition-Interaction Networks for Retinal Vessel Segmentation

学校读者我要写书评

暂无评论

Fdinet: Feature-Decomposition-Interaction Networks for Retin...

IEEE International Symposium on Biomedical Imaging

作者： Yuncheng Yang Jie Yang Junjun He Yun Gu Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Automated segmentation of retinal vessels is challenged by the complexity of curvilinear structures. In this work, we formulate the segmentation task as the decomposition and interaction of topological and scale features of vessels. The connectivity of the curvilinear structure is preserved by the topological properties while the scale features characterize the local morphology. Therefore, we propose a decomposition-then-interaction framework for retinal vessel segmentation. A multi-branch network is designed where the centerline map and scale map are obtained from the original segmentation ground truth to fully exploit these features. The features from auxiliary branches have interacted with cross attention which finally generates the masks of retinal vessels. Experiments on DRIVE, CHASE-DB1, and STARE datasets demonstrate the promising accuracy of the proposed method.

关键词：

OAS-Net: Occlusion aware sampling network for accurate optical flow

学校读者我要写书评

暂无评论

arXiv 2021年

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

Optical flow estimation is an essential step for many real-world computer vision tasks. Existing deep networks have achieved satisfactory results by mostly employing a pyramidal coarse-to-fine paradigm, where a key process is to adopt warped target feature based on previous flow prediction to correlate with source feature for building 3D matching cost volume. However, the warping operation can lead to troublesome ghosting problem that results in ambiguity. Moreover, occluded areas are treated equally with non occluded regions in most existing works, which may cause performance degradation. To deal with these challenges, we propose a lightweight yet efficient optical flow network, named OAS-Net (occlusion aware sampling network) for accurate optical flow. First, a new sampling based correlation layer is employed without noisy warping operation. Second, a novel occlusion aware module is presented to make raw cost volume conscious of occluded regions. Third, a shared flow and occlusion awareness decoder is adopted for structure compactness. Experiments on Sintel and KITTI datasets demonstrate the effectiveness of proposed approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical flows

CDFI: Cross Domain Feature Interaction for Robust Bronchi Lumen Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Jiasheng Zhang, Tianyi Wu, Yangqian Yang, Jie Yang, Guang-Zhong Gu, Yun The Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai China

Endobronchial intervention is increasingly used as a minimally invasive means for the treatment of pulmonary diseases. In order to reduce the difficulty of manipulation in complex airway networks, robust lumen detection is essential for intraoperative guidance. However, these methods are sensitive to visual artifacts which are inevitable during the surgery. In this work, a cross domain feature interaction (CDFI) network is proposed to extract the structural features of lumens, as well as to provide artifact cues to characterize the visual features. To effectively extract the structural and artifact features, the Quadruple Feature Constraints (QFC) module is designed to constrain the intrinsic connections of samples with various imaging-quality. Furthermore, we design a Guided Feature Fusion (GFF) module to supervise the model for adaptive feature fusion based on different types of artifacts. Results show that the features extracted by the proposed method can preserve the structural information of lumen in the presence of large visual variations, bringing much-improved lumen detection accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature extraction

Online LiDAR-Camera Extrinsic Parameters Self-checking

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wei, Pengjin Yan, Guohang Li, Yikang Fang, Kun Yang, Jie Liu, Wei The Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University China The Autonomous Driving Group Shanghai AI Laboratory China

With the development of neural networks and the increasing popularity of automatic driving, the calibration of the LiDAR and the camera has attracted more and more attention. This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks. Current research interests mainly focus on obtaining accurate calibration results through information fusion. However, they seldom analyze whether the calibrated results are correct or not, which could be of significant importance in real-world applications. For example, in large-scale production, the LiDARs and the cameras of each smart car have to get well-calibrated as the car leaves the production line, while in the rest of the car life period, the poses of the LiDARs and cameras should also get continually supervised to ensure the security. To this end, this paper proposes a self-checking algorithm to judge whether the extrinsic parameters are well-calibrated by introducing a binary classification network based on the fused information from the camera and the LiDAR. Moreover, since there is no such dataset for the task in this work, we further generate a new dataset branch from the KITTI dataset tailored for the task. Our experiments on the proposed dataset branch demonstrate the performance of our method. To the best of our knowledge, this is the first work to address the significance of continually checking the calibrated extrinsic parameters for autonomous driving. The code is open-sourced on the Github website at https://***/OpenCalib/LiDAR2camera_self-check. Copyright © 2022, The Authors. All rights reserved.

关键词： Cameras

Generating Cartoon images from Face Photos with Cycle-Consistent Adversarial Networks

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第11期69卷 2733-2747页

作者： Tao Zhang Zhanjie Zhang Wenjing Jia Xiangjian He Jie Yang School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214000China Key Laboratory of Artificial Intelligence Jiangsu214000China The Global Big Data Technologies Centre University of Technology SydneyUltimoNSW2007Australia The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong UniversityShanghai201100China

The generative adversarial network(GAN)is first proposed in 2014,and this kind of network model is machine learning systems that can learn to measure a given distribution of data,one of the most important applications is style *** transfer is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output ***-GAN is a classic GAN model,which has a wide range of scenarios in style *** its unsupervised learning characteristics,the mapping is easy to be learned between an input image and an output ***,it is difficult for CYCLE-GAN to converge and generate high-quality *** order to solve this problem,spectral normalization is introduced into each convolutional kernel of the *** convolutional kernel reaches Lipschitz stability constraint with adding spectral normalization and the value of the convolutional kernel is limited to[0,1],which promotes the training process of the proposed ***,we use pretrained model(VGG16)to control the loss of image content in the position of l1 *** avoid overfitting,l1 regularization term and l2 regularization term are both used in the object loss *** terms of Frechet Inception Distance(FID)score evaluation,our proposed model achieves outstanding performance and preserves more discriminative *** results show that the proposed model converges faster and achieves better FID scores than the state of the art.

关键词： Generative adversarial network spectral normalization Lipschitz stability constraint VGG16 l1 regularization term l2 regularization term Frechet inception distance

Evaluation of low-dose CT supervised learning algorithms with transformer-based model observer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Yongyi Wang, Ge Mou, Xuanqin Biomedical Imaging Center Rensselaer Polytechnic Institute TroyNY United States Institute of Image Processing and Pattern Recognition Xi’an Jiaotong University Shaanxi Xi’an China

A variety of supervise learning methods have been proposed for low-dose computed tomography (CT) sinogram domain denoising. Traditional measures of image quality have been employed to optimize and evaluate these methods, where mathematical model observers are widely advocated because it’s designed to act as human surrogates in the task of lesion detectability for clinical diagnosis. However, the sinogram domain evaluation for the supervised learning methods remains lacking. Since the lesion in medical images is correspond to a narrow sine strip in sinogram domain, in this paper, we proposed a transformer-based efficient model observer to evaluate the sinogram domain supervise learning methods. The numerical results indicate that, we can well-approximate the Laguerre-Gauss channelized Hotelling observer (LG-CHO) models for a signal-known-exactly (SKE) and background-known-statistically (BKS) task by training a transformer-based model observer in sinogram domain. The proposed transformer-based model observer is then employed to assess three classic CNN-based sinogram domain denoising methods. The evaluation in these denoising methods may suggest future avenues for improving the effectiveness of sinogram domain supervised learning methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

Towards Robust Neural Networks Via Orthogonal Diversity

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Fang, Kun Tao, Qinghua Wu, Yingwen Li, Tao Cai, Jia Cai, Feipeng Huang, Xiaolin Yang, Jie Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai China ESAT-STADIUS KU Leuven LeuvenB-3001 Belgium Central Media Technology Institute Huawei Technologies Ltd. China

Deep Neural Networks (DNNs) are vulnerable to invisible perturbations on the images generated by adversarial attacks, which raises researches on the adversarial robustness of DNNs. A series of methods represented by the adversarial training and its variants have proven as one of the most effective techniques in enhancing the DNN robustness. Generally, adversarial training focuses on enriching the training data by involving perturbed data. Such data augmentation effect of the involved perturbed data in adversarial training does not contribute to the robustness of DNN itself and usually suffers from clean accuracy drop. Towards the robustness of DNN itself, we in this paper propose a novel defense that aims at augmenting the model in order to learn features that are adaptive to diverse inputs, including adversarial examples. More specifically, to augment the model, multiple paths are embedded into the network, and an orthogonality constraint is imposed on these paths to guarantee the diversity among them. A margin-maximization loss is then designed to further boost such DIversity via Orthogonality (DIO). In this way, the proposed DIO augments the model and enhances the robustness of DNN itself as the learned features can be corrected by these mutually-orthogonal paths. Extensive empirical results on various data sets, architectures, and attacks verify the adversarial robustness of the proposed DIO utilizing model augmentation. Besides, DIO can also be flexibly combined with different data augmentation techniques (e.g., TRADES and DDPM), further promoting robustness gains. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks