检索结果-内蒙古大学图书馆

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：

CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene

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 Cai, Xinyu 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

Sensor-based environmental perception is a crucial part of the autonomous driving system. In order to get an excellent perception of the surrounding environment, an intelligent system would configure multiple LiDARs (3D Light Detection and Ranging) to cover the distant and near space of the car. The precision of perception relies on the quality of sensor calibration. This research aims at developing an accurate, automatic, and robust calibration strategy for multiple LiDAR systems in the general road scene. We thus propose CROON (automatic multi-LiDAR Calibration and Refinement methOd in rOad sceNe), a two-stage method including rough and refinement calibration. The first stage can calibrate the sensor from an arbitrary initial pose, and the second stage is able to precisely calibrate the sensor iteratively. Specifically, CROON utilize the nature characteristics of road scene so that it is independent and easy to apply in large-scale conditions. Experimental results on real-world and simulated data sets demonstrate the reliability and accuracy of our method. All the related data sets and codes are open-sourced on the Github website https://***/OpenCalib/LiDAR2LiDAR. Copyright © 2022, The Authors. All rights reserved.

关键词： Intelligent systems

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

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

ENHANCING KERNEL FLEXIBILITY VIA LEARNING ASYMMETRIC LOCALLY-ADAPTIVE KERNELS

学校读者我要写书评

暂无评论

arXiv 2023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 Belgium Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University China

The lack of sufficient flexibility is the key bottleneck of kernel-based learning that relies on manually designed, pre-given, and non-trainable kernels. To enhance kernel flexibility, this paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel, giving rise to the LAB RBF kernel. The parameters in LAB RBF kernels are data-dependent, and its number can increase with the dataset, allowing for better adaptation to diverse data patterns and enhancing the flexibility of the learned function. This newfound flexibility also brings challenges, particularly with regards to asymmetry and the need for an efficient learning algorithm. To address these challenges, this paper for the first time establishes an asymmetric kernel ridge regression framework and introduces an iterative kernel learning algorithm. This novel approach not only reduces the demand for extensive support data but also significantly improves generalization by training bandwidths on the available training data. Experimental results on real datasets underscore the remarkable performance of the proposed algorithm, showcasing its superior capability in handling large-scale datasets compared to Nyström approximation-based algorithms. Moreover, it demonstrates a significant improvement in regression accuracy over existing kernel-based learning methods and even surpasses residual neural networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Bandwidth

Supervised Classification of Plant image Based on Attention Mechanism

学校读者我要写书评

暂无评论

Supervised Classification of Plant Image Based on Attention ...

International Conference on Systems and Informatics (ICSAI)

作者： Jie Li Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665426251

In view of the wide variety of plants on the earth, the plant species identification is particularly necessary to protect and preserve biodiversity. In this work, we propose a plant image classification method based on the encoder-decoder model with additive attention mechanism to extract plant image features and convert them into text descriptions related to plant features. In a well-trained network, it can successfully classify on the species of the generated plant texts. We show that, the proposed method not only equalizes the results of deep convolutional neural network on classification task, but also uses of the prior information of botanists in classification, and thus provide a significant prediction result.

关键词： Earth image recognition Text recognition Biological system modeling Feature extraction Convolutional neural networks Biodiversity

Mushroom Classification Based on Deep Residual Network

学校读者我要写书评

暂无评论

Mushroom Classification Based on Deep Residual Network

pattern recognition and Machine Learning (PRML), IEEE International Conference on

作者： Ju Feng Xufeng Ling Yubo Wang Jie Yang School of Artificial Intelligence Shanghai Normal University Tianhua College Shanghai China Shanghai Acoustics Laboratory Chinese Academy of Sciences Shanghai China Institute of Image Processing and Pattern Recognition and Institute of Medical Robotics Shanghai Jiaotong University Shanghai China

Due to the similarity in mushroom features and the difficulty in distinguishing between poisonous and nonpoisonous varieties, mushrooms pose a threat to human health. To address the challenge of mushroom classification and identification, this paper proposes a mushroom classification method based on residual networks. Firstly, a network architecture with multiple residual blocks is designed, and it is trained using an image dataset. Then, a transfer learning strategy is employed to initialize the network parameters from a pre-trained model, followed by fine-tuning to adapt to the mushroom classification task. Finally, multiple testing experiments are conducted to evaluate the effectiveness of the proposed method. The experimental results demonstrate excellent performance of the proposed method in mushroom classification tasks. Compared to traditional feature extraction methods, it can better capture the details and texture features of mushrooms, thereby improving classification accuracy. In conclusion, the mushroom classification method based on residual networks exhibits high accuracy and generalization capability. This method has potential applications in the field of mushroom classification, aiding in the better identification and differentiation of poisonous mushrooms, thereby protecting human health.

关键词：

Indoor Elderly Fall recognition System Based on Target Detection and Self-attention Model 2

学校读者我要写书评

暂无评论

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

2nd International Conference on Electronics, Communications and Information Technology, CECIT 2021

作者： Liu, Min Ling, Xufeng Yang, Jie 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)9781665437578

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. © 2021 IEEE.

关键词： Deep learning