检索结果-内蒙古大学图书馆

MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Fenghe Nian, Bingkun Li, Yingtai Jiang, Zihang Yang, Jie Liu, Wei Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Suzhou Institute for Advanced Research USTC Suzhou China Department of Automation Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China State Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China Anhui Hefei230026 China

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning methods have not yet fully unleashed Mamba’s potential for handling long-range dependencies because they overlook the inherent causal properties of state space sequences in masked modeling. To address this challenge, we propose a general-purpose pre-training framework called MambaMIM, a masked image modeling method based on a novel TOKen-Interpolation strategy (TOKI) for the selective structure state space sequence, which learns causal relationships of state space within the masked sequence. Further, MambaMIM introduces a bottom-up 3D hybrid masking strategy to maintain a masking consistency across different architectures and can be used on any single or hybrid Mamba architecture to enhance its multi-scale and long-range representation capability. We pre-train MambaMIM on a large-scale dataset of 6.8K CT scans and evaluate its performance across eight public medical segmentation benchmarks. Extensive downstream experiments reveal the feasibility and advancement of using Mamba for medical image pre-training. In particular, when we apply the MambaMIM to a customized architecture that hybridizes MedNeXt and Vision Mamba, we consistently obtain the state-of-the-art segmentation performance. The code is available at: https://***/FengheTan9/MambaMIM. Copyright © 2024, The Authors. All rights reserved.

关键词： image segmentation

A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Chulun Liang, Yunlong Meng, Fandong Zhou, Jie Xu, Jinan Wang, Hongji Zhang, Min Su, Jinsong School of Informatics Xiamen University Xiamen361005 China Beijing Jiaotong University Beijing100044 China Pattern Recognition Center WeChat AI Tencent Inc China Soochow University Suzhou215031 China School of Informatics Institute of Artificial Intelligence Xiamen University Xiamen361005 China Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage Fujian Taiwan Xiamen University Ministry of Culture and Tourism China Pengcheng Laboratory China

Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited resources of annotated bilingual dialogues;2) the neglect of modelling conversational properties;3) training discrepancy between different stages. To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues. We elaborately design two auxiliary tasks, namely utterance discrimination and speaker discrimination, to introduce the modelling of dialogue coherence and speaker characteristic into the NCT model. The training process consists of three stages: 1) sentence-level pre-training on large-scale parallel corpus;2) intermediate training with auxiliary tasks using additional monolingual dialogues;3) context-aware fine-tuning with gradual transition. Particularly, the second stage serves as an intermediate phase that alleviates the training discrepancy between the pre-training and fine-tuning stages. Moreover, to make the stage transition smoother, we train the NCT model using a gradual transition strategy, i.e., gradually transiting from using monolingual to bilingual dialogues. Extensive experiments on two language pairs demonstrate the effectiveness and superiority of our proposed training framework. © 2023, CC BY-NC-SA.

关键词：

Multi-granulation variable precision rough set based on limited tolerance relation

学校读者我要写书评

暂无评论

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第3期83卷 63-74页

作者： Wan, Renxia Yao, Yonghong Kumar, Hussain School of Mathematics and Information Science North Minzu University Ningxia750021 China HongYang Institute for Big Data in Health Fuzhou Fujian350028 China School of Mathematical Sciences Tiangong University Tianjin300387 China The Key Laboratory of Intelligent Information and Data Processing of NingXia Province North Minzu University and Health Big Data Research Institute of North Minzu University Yinchuan750021 China Machine vision and pattern recognition lab University of Regina ReginaSKS4S0A2 Canada

In this paper, the combination of the variable precision rough set and the limited tolerance relation under multi-granularity is explored. As an extension of rough set model, Multi-granularity variable precision limited tolerance rough set model is con-structed. Properties of upper and lower approximation operator and detailed structure of object class through threshold are discussed. Theoretical proofs are given to show the rationality and superiority of the proposed model. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Granulation

Research on the identification of obstacle image based on convolutional neural network

学校读者我要写书评

暂无评论

Research on the identification of obstacle image based on co...

2021 International Conference on Signal image processing and Communication, ICSIPC 2021

作者： Zhongyu, Li Huajun, Wang Yuhang, Cao Yuting, Dai College of Geophysics Chengdu University of Technology Chengdu610059 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China College of Computer Science Chengdu Normal University Chengdu611130 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China Key Laboratory of Interior Layout Optimization and Security Institutions of Higher Education of Sichuan Province Chengdu Normal University Chengdu Sichuan611130 China

ISBN: (数字)9781510645417

ISBN: (纸本)9781510645400

To effectively realize the reasonable obstacle avoidance of the detection robot, VGG based obstacle discrimination method is proposed. Above all, the image captured by the robot is input into the multi-layer convolutional neural network to obtain the high-level image features, which are used to construct the more accurate neural network model parameters and to train the softmax classifier with these parameters. Then the distance between the imported images and the data images is calculated by using the softmax classifier, and the similarity between the obstacles and non-obstacles is estimated. The experimental results show that the discrimination accuracy increase to above 94%. And the proposed method is more effectively compared with traditional ultrasonic and radar methods. © 2021 SPIE.

关键词： Convolution

A Fall Detection System Based on a Thermopile Imaging Array and a Back Projection Algorithm

学校读者我要写书评

暂无评论

A Fall Detection System Based on a Thermopile Imaging Array ...

IEEE International Conference on Electro-Information Technology

作者： Lei Yu Han Chen Hantao He Hong Nie Xuping Zhai Bangshu Xiong Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China University of Northern Iowa Iowa USA Shanghai University Shanghai China

ISBN: (数字)9781728153179

ISBN: (纸本)9781728153186

In this paper, a fall detection system consisting of a thermopile imaging array with 80*64 pixels and a Raspberry Pi 3 has been developed. First, the thermal images captured by the hardware system are processed to eliminate fixed interferences and identify the human body. Then, the real height of the human body is estimated from the original height in the thermal images. Finally, after smoothing the fluctuation of the real height, fall events are detected according to the relative variations of the smoothed height. Our experiments show that the newly developed system and image processing algorithm can achieve much better performance on fall detection than other systems based on infrared sensors or sensor arrays.

关键词： Imaging Sensor arrays Senior citizens Projection algorithms Infrared sensors image resolution

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

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM image processing

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hu, Rui Cai, Jiaming Zheng, Wangjie Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai200240 China

ISBN: (纸本)9781728162157

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools. © 2020 IEEE.

关键词： image reconstruction

Analysis Model of Terrorist Attacks Based on Big Data 32

学校读者我要写书评

暂无评论

Analysis Model of Terrorist Attacks Based on Big Data

第32届中国控制与决策会议

作者： LIN Zhenkai DOU Yimin LI Jinping School of Information Science and Engineering University of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing(University of Jinan) Shandong College and University Key Laboratory of Information Processing and Cognitive Computing in 13th Five-year Institute of Pattern Recognition and Intelligent Systems University of Jinan

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

With the continuous deepening of international anti-terrorism movement,the anti-terrorism has entered a new stage,and it is facing new *** of the new challenges is to extract useful and valuable information from massive data *** anti-terrorism system model based on local shallow information is imperfect,which is not conducive to obtaining accurate prediction *** shortcomings of existing research are the lack of comprehensive analysis and deeper mining of *** order to improve the efficiency and accuracy of the present anti-terrorism system,we propose an effective method for risk assessment and prediction based on machine learning by using Global Terrorism Database(GTD).There are four basic steps:first,we reduce the data dimension through correlation calculation and Singular Value Decomposition(SVD),then,the function is established to rank the harmfulness of terrorist attacks;second,the cascaded network with attention mechanism is used to predict suspects;third,k-means is used to cluster the regions of terrorist attacks,and then we establish a generalized linear regression model to predict the situation of terrorist *** verify the feasibility of the model by comparing with the real *** experimental results show that the proposed method can analyze and predict the information related to terrorist attacks comprehensively and accurately.

关键词： anti-terrorism warning data modeling SVD cascade network with attention mechanism K-means

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