检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Haofeng Gou, Shuiping Zhou, Yanyan Jiao, Changzhe Liu, Wenbo Shi, Mei Luo, Zhonghua Key Laboratory of Intelligent Perception and Image Understanding Education Ministry of China School of Artificial Intelligence Xidian University Xi’an710071 China Department of Interventional Radiology Tangdu Hospital Air Force Medical University Xi’an710038 China Central Laboratory of the First Affiliated Hospital Weifang Medical University Weifang261044 China Department of Radiation Oncology Xijing Hospital Air Force Medical University Xi’an710000 China Fourth Military Medical University China

The segmentation of small tumors with irregular shapes and ill-defined boundaries is a crucial step in needle biopsy and radiotherapy. However, manual segmentation is costly and error prone. And acquiring large-scale high-quality annotations for automatic tumor segmentation methods based fully supervised learning is therefore difficult. To address these problem, shape-background joint-aware multiple instance learning (SBJMIL) method is proposed in this paper for small tumor segmentation. In SBJMIL, an instance classification network based on tumor background-aware is designed to deal with the precise annotation scarcity, which can generate tight bounding box annotations via remove background pixels inside loose bounding boxes. Furthermore, a tumor shape-aware module is explored to deal with the class imbalance related to small tumors with irregular shapes, which can learn the morphology information of the tumor via estimating the proportion of positive instances in the prediction results. Quantitative and validation experiments are conducted on the liver tumor segmentation (LiTS-ISBI2017) dataset and nasopharyngeal neoplasm segmentation (NpNS) dataset. For tumor segmentation, the performance of SBJMIL which trained with only loose bounding box annotations is approach to that of fully supervised segmentation methods. And the the segmentation performance of tiny and small liver tumors was improved by 14% and 13% compared to state-of-the-art weakly supervised segmentation methods, respectively. © 2024, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Behavior mimics distribution: Combining individual and group behaviors for federated learning

arXiv

引用

arXiv 2021年

作者： Huang, Hua Shang, Fanhua Liu, Yuanyuan Liu, Hongying Key Lab of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China Peng Cheng Lab Shenzhen China

Federated Learning (FL) has become an active and promising distributed machine learning paradigm. As a result of statistical heterogeneity, recent studies clearly show that the performance of popular FL methods (e.g., FedAvg) deteriorates dramatically due to the client drift caused by local updates. This paper proposes a novel Federated Learning algorithm (called IGFL), which leverages both Individual and Group behaviors to mimic distribution, thereby improving the ability to deal with heterogeneity. Unlike existing FL methods, our IGFL can be applied to both client and server optimization. As a by-product, we propose a new attention-based federated learning in the server optimization of IGFL. To the best of our knowledge, this is the first time to incorporate attention mechanisms into federated optimization. We conduct extensive experiments and show that IGFL can significantly improve the performance of existing federated learning methods. Especially when the distributions of data among individuals are diverse, IGFL can improve the classification accuracy by about 13% compared with prior baselines. © 2021, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Learning a Dynamic High-Resolution Network for Multi-Scale Pedestrian Detection

Learning a Dynamic High-Resolution Network for Multi-Scale P...

引用

International Conference on Pattern Recognition

作者： Mengyuan Ding Shanshan Zhang Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security China

ISBN: (纸本)9781728188089;9781728188096

Pedestrian detection is a canonical instance of object detection in computer vision. In practice, scale variation is one of the key challenges, resulting in unbalanced performance across different scales. Recently, the High-Resolution Network (HRNet) has become popular because high-resolution feature representations are more friendly to small objects. However, when we apply HRNet to pedestrian detection, we observe that it improves for small pedestrians on one hand, but hurts the performance for larger ones on the other hand. To overcome this problem, we propose a learnable Dynamic HRNet (DHRNet) aiming to generate different network paths adaptive to different scales. Specifically, we construct a parallel multi-branch architecture and add a soft conditional gate module allowing for dynamic feature fusion. Both branches share all the same parameters except the soft gate module. Experimental results on CityPersons and Caltech benchmarks indicate that our proposed dynamic HRNet is more capable of dealing with pedestrians of various scales, and thus improves the performance across different scales consistently.

关键词： Computer vision Adaptive systems Object detection Computer architecture Logic gates Benchmark testing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Boosting gradient for white-box adversarial attacks

arXiv

引用

arXiv 2020年

作者： Liu, Hongying Zhou, Zhenyu Shang, Fanhua Qi, Xiaoyu Liu, Yuanyuan Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University China

Deep neural networks (DNNs) are playing key roles in various artificial intelligence applications such as image classification and object recognition. However, a growing number of studies have shown that there exist adversarial examples in DNNs, which are almost imperceptibly different from original samples, but can greatly change the network output. Existing white-box attack algorithms can generate powerful adversarial examples. Nevertheless, most of the algorithms concentrate on how to iteratively make the best use of gradients to improve adversarial performance. In contrast, in this paper, we focus on the properties of the widely-used ReLU activation function, and discover that there exist two phenomena (i.e., wrong blocking and over transmission) misleading the calculation of gradients in ReLU during the backpropagation. Both issues enlarge the difference between the predicted changes of the loss function from gradient and corresponding actual changes, and mislead the gradients which results in larger perturbations. Therefore, we propose a universal adversarial example generation method, called ADV-ReLU, to enhance the performance of gradient based white-box attack algorithms. During the backpropagation of the network, our approach calculates the gradient of the loss function versus network input, maps the values to scores, and selects a part of them to update the misleading gradients. Comprehensive experimental results on imageNet demonstrate that our ADV-ReLU can be easily integrated into many state-of-the-art gradient-based white-box attack algorithms, as well as transferred to black-box attack attackers, to further decrease perturbations in the `2-norm. Copyright © 2020, 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

Unsupervised Detailed Human Shape Estimation from Multi-view Color images 11th

Unsupervised Detailed Human Shape Estimation from Multi-view...

引用

11th International Conference on image and Graphics, ICIG 2021

作者： Zheng, Huayu Wang, Kangkan Li, Wei Yang, Jian Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Lab for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9783030873578

This paper presents a novel framework to estimate detailed human body shape from color images in an unsupervised manner. It is a challenging task due to factors such as variations in human shapes, occlusion, and cloth details. The existing methods are mainly supervised and require a large number of ground truth real training data which is usually hard to obtain. To solve this problem, we propose an unsupervised detailed human shape estimation method from multi-view color images. Specifically, we first predict the depth map for the source view through robust photometric consistency with different views. Then, we predict the initial SMPL model from the color image and refine it by an iterative error feedback regressor based on point clouds of the predicted depth map. Finally, the refined SMPL model is deformed to fit the details (i.e., clothes and faces) on the point clouds to recover the detailed human shapes which are represented by adding a set of offsets to the SMPL model. The experimental results on different dataset demonstrate that our method outperforms the state-of-the-art methods and achieves higher reconstruction accuracy. © 2021, Springer Nature Switzerland AG.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Early stage of radiological expertise modulates resting-state local coherence in the inferior temporal lobe

引用

Psychoradiology 2022年第4期2卷 199-206页

作者： Minghao Dong Peiming Zhang Weilu Chai Xiaoyan Zhang Bihong TChen Hongmei Wang Jia Wu Chao Chen Yi Niu Jimin Liang Guangming Shi Chenwang Jin Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and TechnologyXidian UniversityXi’an CityShaanxi 710071China Xian Key Laboratory of Intelligent Sensing and Regulation of tran-Scale Life Information Xi’an CityShaanxi 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial IntelligenceXidian UniversityXi’an CityShaanxi 710071China City of Hope Medical Center Duarte CityCalifornia 91010USA Department of Medical Imaging First Affiliated Hospital of Medical CollegeXi’an Jiaotong UniversityXi’an CityShaanxi 710000China School of Foreign Languages Northwestern Polytechnical UniversityXi’an CityShaanxi 710071China PLA Funding Payment Center Beijing 100000China School of Electronics and Engineering Xidian UniversityXi’an CityShaanxi 710071China

Background The visual system and its inherent functions undergo experience-dependent changes through the lifespan,enabling acquisition of new *** fMRI studies using tasks reported increased specialization in a number of cortical regions subserving visual *** ample studies focused on representation of long-term visual expertise in the brain,*** terms of year,monthly-based early-stage representation of visual expertise remains *** that spontaneous neuronal oscillations actively encode previous experience,we propose brain representations in the resting state is fundamentally *** The current study aimed to investigate how monthly-based early-stage visual expertise are represented in the resting state using the expertise model of *** In particular,we investigated the altered local clustering pattern of spontaneous brain activity using regional homogeneity(ReHo).A cohort group of radiology interns(n=22)after one-month training in X-ray department and matched laypersons(n=22)were recruited after rigorous behavioral *** The results showed higher ReHo in the right hippocampus(HIP)and the right ventral anterior temporal lobe(vATL)(corrected by Alphasim correction,P<0.05).Moreover,ReHo in the right HIP correlated with the number of cases reviewed during intern radiologists’training(corrected by Alphasim correction,P<0.05).Conclusions In sum,our results demonstrated that the early stage of visual expertise is more concerned with stabilizing visual feature and domain-specific knowledge into long-term *** results provided novel evidence regarding how early-stage visual expertise is represented in the resting brain,which help further elaborate how human visual expertise is *** propose that our current study may provide novel ideas for developing new training protocols in medical schools.

关键词： visual expertise resting state fMRI radiologists inferior temporal cortex

来源：评论

学校读者我要写书评

暂无评论

Nighttime Pedestrian Detection Based on Feature Attention and Transformation

Nighttime Pedestrian Detection Based on Feature Attention an...

引用

International Conference on Pattern Recognition

作者： Gang Li Shanshan Zhang Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security China

Pedestrian detection at nighttime is an important yet challenging task, which is fundamental for many practical applications, e.g. autonomous driving, video surveillance. To address this problem, in this work we start with some analysis, from which we find that the nighttime features have much more noise than that of daytime, resulting in low discrimination ability. Besides, we also observe some pedestrian examples are under adverse illumination conditions, and they can hardly provide sufficient information for accurate detection. Based on these findings, we propose the Feature Attention Module (FAM) and Feature Transformation Module (FTM) to enhance nighttime features. In FAM, guided by progressive segmentation supervision, hierarchical feature attention is produced to enhance multilevel features. On the other hand, FTM is introduced to enforce features from adverse illumination to approach that from better illumination. Based on feature attention and transformation (FAT) mechanism, a two-stage detector called FATNet is constructed for nighttime pedestrian detection. We conduct extensive experiments on nighttime datasets of EuroCity Persons (Night) and NightOwls to demonstrate the effectiveness of our method. On both datasets, our method achieves significant improvements to the baseline and also outperforms state-of-the-art detectors.

关键词： Lighting Detectors Feature extraction Video surveillance Pattern recognition Fats Noise measurement

来源：评论

学校读者我要写书评

暂无评论

ConsistencyDet: A Robust Object Detector with a Denoising Paradigm of Consistency Model

arXiv

引用

arXiv 2024年

作者： Jiang, Lifan Wang, Zhihui Wang, Changmiao Li, Ming Leng, Jiaxu Wu, Xindong the College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266510 China Shenzhen Research Institute of Big Data Shenzhen518172 China Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua321004 China the Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China the Key Laboratory of Knowledge Engineering with Big Data the Ministry of Education of China China School of Computer Science and Information Technology Hefei University of Technology Hefei230009 China

Object detection, a quintessential task in the realm of perceptual computing, can be tackled using a generative methodology. In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities. This framework, termed ConsistencyDet, leverages an innovative denoising concept known as the Consistency Model. The hallmark of this model is its self-consistency feature, which empowers the model to map distorted information from any temporal stage back to its pristine state, thereby realizing a "one-step denoising" mechanism. Such an attribute markedly elevates the operational efficiency of the model, setting it apart from the conventional Diffusion Model. Throughout the training phase, ConsistencyDet initiates the diffusion sequence with noise-infused boxes derived from the ground-truth annotations and conditions the model to perform the denoising task. Subsequently, in the inference stage, the model employs a denoising sampling strategy that commences with bounding boxes randomly sampled from a normal distribution. Through iterative refinement, the model transforms an assortment of arbitrarily generated boxes into definitive detections. Comprehensive evaluations employing standard benchmarks, such as MS-COCO and LVIS, corroborate that ConsistencyDet surpasses other leading-edge detectors in performance metrics. Our code is available at https://***/Tankowa/ConsistencyDet. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Panchromatic image Land Cover Classification Via DCNN with Updating Iteration Strategy

Panchromatic Image Land Cover Classification Via DCNN with U...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Biao Hou Yangfei Liu Tuotuo Rong Bo Ren Zijuan Xiang Xiangrong Zhang Shuang Wang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Land cover classification is a critical research task in many significant remote sensing applications. There are emerging many powerful pixel-level classification methods based on deep convolutional neural network (DCNN) in the universal computer vision community. However, due to the complication of satellite image senses and the lack of high-quality labeled datasets, these computer vision techniques can not be applied to remote sensing applications directly. In this paper, we propose a novel DCNN method to extract abstract feature from the complicated remote scene. The proposed method fuses three level features from the encoder while the segmentation result is obtained by decoder. Furthermore, we propose an updating iteration strategy (UIS) with label smoothing on training set to reduce the impact of the incorrect labels. The proposed strategy employs the output of the network to update the low-confidence labels on training set, and utilizes the updated labels to continue training the network. In order to acquire a better segmentation result on a very high resolution (VHR) panchromatic image, we transfer the features trained on GID dataset to our dataset for training. Our experiments has demonstrated the oustanding performance of the proposed method in land cover classification compared to DeepLabv3 on the GID and our dataset.

关键词： Training Remote sensing Feature extraction image segmentation image resolution Forestry Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Differentially private ADMM algorithms for machine learning

arXiv

引用

arXiv 2020年

作者： Xu, Tao Shang, Fanhua Liu, Yuanyuan Liu, Hongying Shen, Longjie Gong, Maoguo Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xidian University China

In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smooth convex loss functions with (non)-smooth regularization, we propose the first differentially private ADMM (DP-ADMM) algorithm with performance guarantee of (∊, δ)-differential privacy ((∊, δ)-DP). From the viewpoint of theoretical analysis, we use the Gaussian mechanism and the conversion relationship between Rényi Differential Privacy (RDP) and DP to perform a comprehensive privacy analysis for our algorithm. Then we establish a new criterion to prove the convergence of the proposed algorithms including DP-ADMM. We also give the utility analysis of our DP-ADMM. Moreover, we propose an accelerated DP-ADMM (DP-AccADMM) with the Nesterov’s acceleration technique. Finally, we conduct numerical experiments on many real-world datasets to show the privacy-utility tradeoff of the two proposed algorithms, and all the comparative analysis shows that DP-AccADMM converges faster and has a better utility than DP-ADMM, when the privacy budget ∊ is larger than a threshold. Copyright © 2020, The Authors. All rights reserved.

关键词： Budget control

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：