检索结果-内蒙古大学图书馆

Anomaly Detection for Medical Images Using Heterogeneous auto-encoder

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 2770-2782页

作者： Lu, Shuai Zhang, Weihang Zhao, He Liu, Hanruo Wang, Ningli Li, Huiqi Beijing Inst Technol Beijing 100081 Peoples R China Univ Liverpool Dept Eye & Vis Sci Liverpool L7 8TX England Capital Med Univ Beijing Tongren Hosp Beijing Inst Ophthalmol Beijing 100054 Peoples R China Henan Prov Acad Med Sci Zhengzhou 450046 Peoples R China

Anomaly detection is an important task for medical image analysis, which can alleviate the reliance of supervised methods on large labelled datasets. Most existing methods use a pixel-wise self-reconstruction framework for anomaly detection. However, there are two challenges of these studies: 1) they tend to overfit learning an identity mapping between the input and output, which leads to failure in detecting abnormal samples;2) the reconstruction considers the pixel-wise differences which may lead to an undesirable result. To mitigate the above problems, we propose a novel heterogeneous auto-encoder (Hetero-AE) for medical anomaly detection. Our model utilizes a convolutional neural network (CNN) as the encoder and a hybrid CNN-Transformer network as the decoder. The heterogeneous structure enables the model to learn the intrinsic information of normal data and enlarge the difference on abnormal samples. To fully exploit the effectiveness of Transformer in the hybrid network, a multi-scale sparse Transformer block is proposed to trade off modelling long-range feature dependencies and high computational costs. Moreover, the multi-stage feature comparison is introduced to reduce the noise of pixel-wise comparison. Extensive experiments on four public datasets (i.e., retinal OCT, chest X-ray, brain MRI, and COVID-19) verify the effectiveness of our method on different imaging modalities for anomaly detection. Additionally, our method can accurately detect tumors in brain MRI and lesions in retinal OCT with interpretable heatmaps to locate lesion areas, assisting clinicians in diagnosing abnormalities efficiently.

关键词： Anomaly detection Magnetic resonance imaging auto-encoder heterogeneous network

来源：评论

学校读者我要写书评

暂无评论

auto-encoder Based automated Epilepsy Diagnosis 7

Auto-encoder Based Automated Epilepsy Diagnosis

引用

7th International Conference on Computing, Communications and Informatics (ICACCI)

作者： Sharathappriyaa, V Gautham, S. Lavanya, R. Amrita Vishwa Vidyapeetham Amrita Sch Engn Dept Elect & Commun Engn Coimbatore Tamil Nadu India

ISBN: (纸本)9781538653142

This work proposes the design of an automated system based on auto-encoders to detect epilepsy using Electroencephalogram (EEG) signal. HarmonicWavelet Packet Transform (HWPT) and Fractal Analysis are employed to extract the initial feature vector. HWPT is used to capture spectral information using non-overlapping octave bands, thereby avoiding recursive calculations. Fractal dimension (FD) based on Katz technique is performed on windowed segments of the signal to capture spatial information of the EEG signal. Features comprising HWPT and FD are fed to an auto-encoder, which is used to compress the high dimensional feature vector to a more discriminative and lower dimensional feature vector, for efficient classification. Finally, a Softmax classifier is used for the binary classification problem of discriminating epilepsy signals from normal cases.

关键词： EEG Fractal dimension Harmonic wavelet packet transform auto-encoder Softmax

来源：评论

学校读者我要写书评

暂无评论

An auto-encoder-based summarization algorithm for unstructured videos

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2017年第23期76卷 25039-25056页

作者： Han, Meng-Xiong Hu, Hai-Miao Liu, Yang Zhang, Chi Tian, Rong-Peng Zheng, Jin Beihang Univ Sch Comp Sci & Engn Beijing Key Lab Digital Media Beijing 100083 Peoples R China Beijing Inst Graph Beijing 100029 Peoples R China Beihang Univ Digital Media Lab Beijing Peoples R China

Video summarization is an effective way to quick view videos and relieve the pressure of videos storage. However the traditional algorithms are hardly adapted to unstructured videos, due to the unobvious for scenes changing and ignoring the structure of the videos. Therefore, an auto-encoder-based summarization algorithm is proposed in this paper for unstructured videos. Each video structure is detected by an auto-encoder and both of the interestingness and representativeness of each video segment are predicted by the reconstruction errors of the segment. Meanwhile, most interesting and representative summarization is generated with the limited summary length. The experimental results show that the proposed algorithm obtained a better performance by comparing with the state-of-the-art.

关键词： Video summarization auto-encoder Video analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Modality Adversarial auto-encoder for Zero-Shot Learning

引用

IEEE ACCESS 2020年 8卷 9287-9295页

作者： Ji, Zhong Dai, Guangwen Yu, Yunlong Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China

The existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well. In this paper, we propose to generate visual features based on an auto-encoder framework paired with multi-modality adversarial networks respectively for visual and semantic modalities to reinforce the visual-semantic interactions with a bidirectional alignment, which ensures the generated visual features to fit the real visual distribution and to be highly related to the semantics. The encoder aims at generating real-like visual features while the decoder forces both the real and the generated visual features to be more related to the class semantics. To further capture the discriminative information of the generated visual features, both the real and generated visual features are forced to be classified into the correct classes via a classification network. Experimental results on four benchmark datasets show that the proposed approach is particularly competitive on both the traditional ZSL and the generalized ZSL tasks.

关键词： Zero-shot learning adversarial network auto-encoder image recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised domain adaptation techniques based on auto-encoder for non-stationary EEG-based emotion recognition

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2016年 79卷 205-214页

作者： Chai, Xin Wang, Qisong Zhao, Yongping Liu, Xin Bai, Ou Li, Yongqiang Harbin Inst Technol Sch Elect Engn & Automat Harbin Peoples R China Harbin Inst Technol Sch Transportat Sci & Engn Dept Traff Informat & Control Engn Harbin Peoples R China Florida Int Univ Dept Elect & Comp Engn Miami FL 33199 USA

In electroencephalography (EEG)-based emotion recognition systems, the distribution between the training samples and the testing samples may be mismatched if they are sampled from different experimental sessions or subjects because of user fatigue, different electrode placements, varying impedances, etc. Therefore, it is difficult to directly classify the EEG patterns with a conventional classifier. The domain adaptation method, which is aimed at obtaining a common representation across training and test domains, is an effective method for reducing the distribution discrepancy. However, the existing domain adaptation strategies either employ a linear transformation or learn the nonlinearity mapping without a consistency constraint;they are not sufficiently powerful to obtain a similar distribution from highly non-stationary EEG signals. To address this problem, in this paper, a novel component, called the subspace alignment auto-encoder (SAAE), is proposed. Taking advantage of both nonlinear transformation and a consistency constraint, we combine an auto-encoder network and a subspace alignment solution in a unified framework. As a result, the source domain can be aligned with the target domain together with its class label, and any supervised method can be applied to the new source domain to train a classifier for classification in the target domain, as the aligned source domain follows a distribution similar to that of the target domain. We compared our SAAE method with six typical approaches using a public EEG dataset containing three affective states: positive, neutral, and negative. Subject to-subject and session-to-session evaluations were performed. The subject-to-subject experimental results demonstrate that our component achieves a mean accuracy of 77.88% in comparison with a state-of-the-art method, TCA, which achieves 73.82% on average. In addition, the average classification accuracy of SAAE in the session-to-session evaluation for all the 15 subjects in

关键词： Emotion recognition EEG Domain adaptation auto-encoder MMD

来源：评论

学校读者我要写书评

暂无评论

Cramer-Wold auto-encoder

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2020年 21卷

作者： Knop, Szymon Spurek, Przemyslaw Tabor, Jacek Podolak, Igor Mazur, Marcin Jastrzebski, Stanislaw Jagiellonian Univ Fac Math & Comp Sci Krakow Poland NYU Dept Radiol Ctr Data Sci 560 1St Ave New York NY 10016 USA

The computation of the distance to the true distribution is a key component of most state-of-the-art generative models. Inspired by prior works on the Sliced-Wasserstein auto-encoders (SWAE) and the Wasserstein auto-encoders with MMD-based penalty (WAE-MMD), we propose a new generative model - a Cramer-Wold auto-encoder (CWAE). A fundamental component of CWAE is the characteristic kernel, the construction of which is one of the goals of this paper, from here on referred to as the Cramer-Wold kernel. Its main distinguishing feature is that it has a closed-form of the kernel product of radial Gaussians. Consequently, CWAE model has a closed-form for the distance between the posterior and the normal prior, which simplifies the optimization procedure by removing the need to sample in order to compute the loss function. At the same time, CWAE performance often improves upon WAE-MMD and SWAE on standard benchmarks.

关键词： auto-encoder Generative model Wasserstein auto-encoder Cramer-Wold Theorem Deep neural network

来源：评论

学校读者我要写书评

暂无评论

Wavelet Loss Function for auto-encoder

引用

IEEE ACCESS 2021年 9卷 27101-27108页

作者： Zhu, Qiuyu Wang, Hu Zhang, Ruixin Shanghai Univ Sch Commun & Informat Engn Shanghai 201900 Peoples R China

In the field of image generation, especially for auto-encoder models, how to extract better features and obtain better quality reconstruction samples by modifying network structure and training algorithms has always been the focus of attention. For example, Variational auto-encoder (VAE), which is a very popular auto-encoder model, is a theoretically rigorously derived image generation model. For commonly used auto-encoders, such as VAE, Regularized auto-encoder (RAE), and Wasserstein auto-encoder (WAE), the mean square error (MSE) is all used as the loss function of the reconstructed process, which makes the blur problem of the reconstruction samples unavoidable. Especially for larger-sized images, the blur phenomenon is more obvious. To solve this problem, Perceptual Loss Function is used in some cases. Although it can improve the image quality to a certain extent, the amount of calculation is large and the image quality improvement in auto-encoder is also relatively limited. For this reason, we try to propose a new loss function, Wavelet loss function, to better generate and reconstruct images. Wavelet transform is applied to the reconstructed image loss function of the auto-encoder, and the frequency characteristics of the decomposed image are used to constrain it. We conducted comparative experiments on two larger-size image datasets (FaceSrub, COIL20) and a small-size image dataset (Fashion_MNIST), and proved the effectiveness of the wavelet loss function. At the same time, we propose a new image quality index: wavelet high-frequency signal-to-noise ratio (WHF-SNR), which can better measure the quality of the reconstructed image of the auto-encoder.

关键词： Wavelet transforms Image reconstruction Training Image quality Indexes Image synthesis Feature extraction auto-encoder reconstruct generate wavelet loss function

来源：评论

学校读者我要写书评

暂无评论

Exemplar-based Cascaded Stacked auto-encoder Networks for robust face alignment

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2018年 171卷 95-103页

作者： Zhang Junfeng Hu Haifeng Sun Yat Sen Univ Sch Elect & Informat Engn Guangzhou Guangdong Peoples R China

In this paper, we present a novel Exemplar-based Cascaded Stacked auto-encoder Network (ECSAN) for facial landmarks detection. The proposed framework consists of a Global Exemplar Constraint Stacked auto-encoder Network (GECSAN) and a set of Local Information Preserve Stacked auto-encoder Networks (LIPSANs). In our work, GECSAN utilizes successive stacked auto-encoder network and some well-designed exemplars to obtain an initial shape estimation from a holistic facial image. Then LIPSANs are presented which take the local features extracted around current landmarks as input and generate a facial landmark refinement. Different from existing deep models, a prior exemplar-based shape is utilized to handle the partial occlusion in the image so that our model can achieve robustness against local occlusions. Experimental results on several datasets demonstrate that our model acquires better performance over the state-of-the-art methods with respect to occlusion handling and attain higher alignment accuracy.

关键词： auto-encoder Deep learning Exemplar-based Cascaded architecture Face alignment

来源：评论

学校读者我要写书评

暂无评论

Cross -modal guidance based auto -encoder for multi -video summarization

引用

PATTERN RECOGNITION LETTERS 2020年 135卷 131-137页

作者： Ji, Zhong Zhao, Yuxiao Pang, Yanwei Li, Xuelong Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Northwestern Polytech Univ Ctr OPT IMagery Anal & Learning Xian 710072 Shaanxi Peoples R China

Multi-Video Summarization (MVS) aims at condensing a great number of videos with the same search query to obtain a compact storyboard, which improves user’s browsing experience . Recently, a line of research resorts to a mass of extra web images to specify the search intent for a query. However, these web images are indirect and noisy. In contrast, the tag information for queried videos is more accurate and concise than those web images, which can also be directly employed as side information. To this end, we proposed to employ tag information, i.e., titles and descriptions, as the side information for the generation of summarization. Specifically, we employed sparse auto-encoder as the main model to generate the final summarization, where the input was the multiple videos, the output was the keyframes set. Meanwhile, we fused the visual and tag information to guide visual features, which constrained the sparse auto-encoder to select the important candidate keyframes. The proposed approach is called Cross-modal guidance based auto-encoder for MVS approach (CAE-MVS). Extensive experimental results demonstrate that the CAE-MVS clearly outperforms the state-of-the-art methods.

关键词： auto-encoder Cross-modal Multi-video summarization

来源：评论

学校读者我要写书评

暂无评论

An Image Clustering auto-encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

引用

NEURAL PROCESSING LETTERS 2020年第2期51卷 1973-1988页

作者： Zhu, Qiuyu Wang, Zhengyong Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China

In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses predefined evenly-distributed class centroids (PEDCC) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance. Specifically, we perform one-to-one data augmentation to learn the more effective features. The data and the augmented data are simultaneously input into the autoencoder to obtain latent features and the augmented latent features whose similarity are constrained by an augmentation loss. Then, making use of the maximum mean discrepancy distance, we combine the latent features and augmented latent features to make their distribution close to the PEDCC distribution (uniform distribution between classes, Dirac distribution within the class) to further learn clustering-oriented features. At the same time, the MSE of the original input image and reconstructed image is used as reconstruction constraint, and the Sobel smooth loss to build generalization constraint to improve the generalization ability. Finally, extensive experiments on three common datasets MNIST, Fashion-MNIST, COIL20 are conducted. The experimental results show that the algorithm has achieved the best clustering results so far. In addition, we can use the predefined PEDCC class centers, and the decoder to clearly generate the samples of each class. The code can be downloaded at

关键词： auto-encoder Clustering Predefined evenly-distributed class centroids (PEDCC) Data augmentation Maximum mean discrepancy (MMD)

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：