检索结果-内蒙古大学图书馆

9th International Conference on Image and Graphics (ICIG)

作者： Li, Xingyue Wan, Shouhong Zou, Chang Yin, Bangjie Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Peoples R China Chinese Acad Sci Key Lab Electromagnet Space Informat Hefei 230027 Peoples R China

ISBN: (纸本)9783319716077;9783319716060

In image categorization, one image is usually reshaped as a bag of instances affiliated with multiple labels, which naturally induces a paradigm of multi-instance and multi-label learning (MIMLL). Previous researches proved that the significant improvements on image categorization accuracy resulted from applying connections between labels and regions or correlations among labels, but most proposed approaches could not make full use of contextual cues. Thus we propose a brand-new MIMLL method with integrating three distinct types of contexts into a conditional random fields (CRFs) framework, which can simultaneously capture latent probability distribution of instances, spatial context among adjacent instances and correlations between instances and labels. We perform image categorization on MSRC and Corel 1000 data sets to verify our proposal. Compared with traditional and state-of-the-art MIMLL algorithms, our approach obtains the superior performance.

关键词： multi-instance multi-label learning Image categorization Conditional random fields Contextual information

来源：评论

学校读者我要写书评

暂无评论

HMIML: Hierarchical multi-instance multi-label learning of Drosophila Embryogenesis Images Using Convolutional Neural Networks

HMIML: Hierarchical Multi-Instance Multi-Label Learning of <...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Human Genomics

作者： Li, Tiange Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China Key Lab Shanghai Educ Commiss Intelligent Interac Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China Minist Educ China Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China

ISBN: (纸本)9781538654880

The Drosophila embryonic gene expression images provide important spatio-temporal expression information for understanding the mechanisms of Drosophila embryogenesis. Automatic annotation of these images is an imperative but challenging task. Unlike the auto-annotation for nature images, the labels (terms from a controlled vocabulary) are assigned to genes rather than images. Each gene corresponds to a set of images, and different genes are associated with different numbers of images and labels, thus conventional machine learning methods are not applicable in such a scenario. In this study, we treat this task as a multi-instance multi-label (MIML) problem, and propose a hierarchical MIML learning framework, called HMIML. We implement HMIML at image-level and gene-level, respectively, both using convolutional neural networks. Especially, an image stitching strategy is employed to get a combined image representation at gene-level. Experimental results on the FlyExpress database show that HMIML enhances annotation accuracy on all developmental stages compared with the existing methods.

关键词： gene expression Drosophila embryonic image multi-instance multi-label learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Deep multi-instance multi-label learning for Image Annotation

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2018年第3期32卷 1859005-1859005页

作者： Guo, Hai-Feng Han, Lixin Su, Shoubao Sun, Zhou-Bao Hohai Univ Coll Comp & Informat Nanjing 210024 Jiangsu Peoples R China Jinling Inst Technol Sch Comp Engn Nanjing 211169 Jiangsu Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210093 Jiangsu Peoples R China Nanjing Audit Univ Nanjing 211815 Jiangsu Peoples R China

multi-instance multi-label learning (MIML) is a popular framework for supervised classification where an example is described by multiple instances and associated with multiple labels. Previous MIML approaches have focused on predicting labels for instances. The idea of tackling the problem is to identify its equivalence in the traditional supervised learning framework. Motivated by the recent advancement in deep learning, in this paper, we still consider the problem of predicting labels and attempt to model deep learning in MIML learning framework. The proposed approach enables us to train deep convolutional neural network with images from social networks where images are well labeled, even labeled with several labels or uncorrelated labels. Experiments on real-world datasets demonstrate the effectiveness of our proposed approach.

关键词： multi-instance multi-label learning deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming for instance Annotation in multi-instance multi-label learning

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2017年第12期39卷 2381-2394页

作者： Pham, Anh T. Raich, Raviv Fern, Xiaoli Z. Oregon State Univ Sch EECS Corvallis OR 97331 USA

labeling data for classification requires significant human effort. To reduce labeling cost, instead of labeling every instance, a group of instances (bag) is labeled by a single bag label. Computer algorithms are then used to infer the label for each instance in a bag, a process referred to as instance annotation. This task is challenging due to the ambiguity regarding the instance labels. We propose a discriminative probabilistic model for the instance annotation problem and introduce an expectation maximization framework for inference, based on the maximum likelihood approach. For many probabilistic approaches, brute-force computation of the instance label posterior probability given its bag label is exponential in the number of instances in the bag. Our contribution is a dynamic programming method for computing the posterior that is linear in the number of instances. We evaluate our method using both benchmark and real world data sets, in the domain of bird song, image annotation, and activity recognition. In many cases, the proposed framework outperforms, sometimes significantly, the current state-of-the-art MIML learning methods, both in instance label prediction and bag label prediction.

关键词： multi-instance multi-label learning instance annotation expectation maximization graphical model dynamic programming

来源：评论

学校读者我要写书评

暂无评论

multi-instance multi-label learning for whole slide breast histopathology 4

Multi-instance multi-label learning for whole slide breast h...

引用

Conference on Medical Imaging - Digital Pathology

作者： Mercan, Caner Mercan, Ezgi Aksoy, Selim Shapiro, Linda G. Weaver, Donald L. Elmore, Joann G. Bilkent Univ Dept Comp Engn TR-06800 Ankara Turkey Univ Washington Dept Comp Sci & Engn Seattle WA 98195 USA Univ Vermont Dept Pathol Burlington VT 05405 USA Univ Washington Dept Med Seattle WA 98195 USA

ISBN: (纸本)9781510600263

Digitization of full biopsy slides using the whole slide imaging technology has provided new opportunities for understanding the diagnostic process of pathologists and developing more accurate computer aided diagnosis systems. However, the whole slide images also provide two new challenges to image analysis algorithms. The first one is the need for simultaneous localization and classification of malignant areas in these large images, as different parts of the image may have different levels of diagnostic relevance. The second challenge is the uncertainty regarding the correspondence between the particular image areas and the diagnostic labels typically provided by the pathologists at the slide level. In this paper, we exploit a data set that consists of recorded actions of pathologists while they were interpreting whole slide images of breast biopsies to find solutions to these challenges. First, we extract candidate regions of interest (ROI) from the logs of pathologists' image screenings based on different actions corresponding to zoom events, panning motions, and fixations. Then, we model these ROIs using color and texture features. Next, we represent each slide as a bag of instances corresponding to the collection of candidate ROIs and a set of slide-level labels extracted from the forms that the pathologists filled out according to what they saw during their screenings. Finally, we build classifiers using five different multi instance multi-label learning algorithms, and evaluate their performances under different learning and validation scenarios involving various combinations of data from three expert pathologists. Experiments that compared the slide-level predictions of the classifiers with the reference data showed average precision values up to 62% when the training and validation data came from the same individual pathologist's viewing logs, and an average precision of 64% was obtained when the candidate ROIs and the labels from all pathologists were comb

关键词： Digital pathology computer aided diagnosis breast histopathology whole slide imaging region of interest analysis image classification multi-instance multi-label learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Protein Functions of Bacteria Genomes via multi-instance multi-label Active learning 3

Predicting Protein Functions of Bacteria Genomes via Multi-i...

引用

3rd IEEE International Conference on Integrated Circuits and Microsystems (ICICM)

作者： Wu, Jiansheng Zhu, Wenyong Jiang, Ye Sun, Guwei Gao, Yusheng Nanjing Univ Posts & Telecommun Sch Geog & Biol Informat Nanjing Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Sch Comp Sci & Technol Nanjing Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Sch Telecommun & Informat Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538683118

Bacteria are workhorses in the fields of molecular biology, genetics, and biochemistry. Understanding the biological functions of proteins is important for bacteria studies in the post-genomic era. There are a large number of proteins with unknown biological functions in newly discovered bacteria species. Active learning can assist biologists in selecting the most valuable proteins as candidates for assays. Previously, we formulated the protein function prediction problem as a multi-instance multi-label (MIML) learning task. Here, we propose a MIML active learning algorithm MIMLAL-R for protein function annotation of bacteria genomes. MIMLAL-R minimizes an approximated surrogate loss by stochastic gradient descent with the most valuable bag-label pairs, which are chosen by a selection criterion that combines label cardinality inconsistency and diversity. We tested MIMLAL-R on four real bacteria, namely Geobacter sulfurreducens, Azotobacter vinelandii, Shewanella loihica PV-4, and Escherichia coli strain K12. The MIMLAL-R approach achieved excellent performances in all cases. The codes and data can be freely downloaded from https://***/njuptml/MIMLAL-R.

关键词： bacteria protein function prediction multi-instance multi-label learning active learning

来源：评论

学校读者我要写书评

暂无评论

A New multi-instance multi-label learning approach for image and text classification

引用

multiMEDIA TOOLS AND APPLICATIONS 2016年第13期75卷 7875-7890页

作者： Yan, Kaobi Li, Zhixin Zhang, Canlong Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China Guangxi Expt Ctr Informat Sci Guilin 541004 Peoples R China

Recently, a reasonable and effectively framework to deal with the classification problem of the polysemy object with complex connotation is multi-instance multi-label (MIML) learning framework in which each example is not only represented by multiple instances but also associated with multiple labels. As we all know, feature expression plays an important role in the classification problems. It determines the accuracy of the classification results from the source. Considering its difficulties for automatically extracting the high-level features which are useful and noiseless for the MIML problem, so in this paper we present a general MIML framework by combining the feature learning technologies with machine learning technologies. Further, based on this framework, a new approach called CPNMIML which combines the probabilistic latent semantic analysis (PLSA) with the neural networks (NN) is proposed. In CPNMIML algorithm, we firstly learn the latent topic allocation of all the training examples by using the PLSA model, it is a feature learning process to get high-level features. Then we utilize the learned latent topic allocation of each training example to train the neural networks. Given a test example, we learn its latent topic distribution. Finally, we send the learned latent topic allocation of the test example to the trained neural networks to get the multiple labels of the test example. Experiments show that the proposed method has superior performance on two real-world MIML tasks.

关键词： Feature learning multi-instance multi-label learning Probabilistic latent semantic analysis Neural networks Scene classification Text categorization

来源：评论

学校读者我要写书评

暂无评论

A multi-instance multi-label learning algorithm based on instance correlations

引用

multiMEDIA TOOLS AND APPLICATIONS 2016年第19期75卷 12263-12284页

作者： Liu, Chanjuan Chen, Tongtong Ding, Xinmiao Zou, Hailin Tong, Yan Ludong Univ Sch Informat & Elect Engn Yantai 264025 Peoples R China Univ South Carolina Dept Comp Sci & Engn Columbia SC 29208 USA Shandong Inst Business & Technol Sch Informat & Elect Engn Yantai 264005 Peoples R China

Existing multi-instance multi-label learning algorithms generally assume that instances in a bag are independent of each other, which is difficult to be guaranteed in practical applications. A novel multi-instance multi-label learning algorithm is proposed by modeling instance correlations in each bag. First, instance correlations are introduced in multi-instance multi-label learning by constructing graphs. Then, different kernel matrices are derived from kernel functions based on graphs at different scales, which are employed to train multiple Kernel Support Vector Machine (MKSVM) classifiers. Experimental results on different datasets show that the proposed method significantly improves the accuracy of the multi-label classification compared with the state-of-the-art methods.

关键词： multi-instance multi-label learning multi-label classification instance correlations multiple-kernel fusion

来源：评论

学校读者我要写书评

暂无评论

Person re-identification based on multi-instance multi-label learning

引用

NEUROCOMPUTING 2016年 217卷 19-26页

作者： Lin, Ying Guo, Feng Cao, Liujuan Wang, Jinlin Xiamen Univ Sch Informat Sci & Engn Dept Cognit Sci Xiamen Peoples R China Xiamen Univ Sch Informat Sci & Engn Dept Comp Sci Xiamen Peoples R China

The person re-identification is an active research branch of the computer vision and attracts many researchers study on it. However, because of the variance in viewpoints, illumination, pedestrians' pose and some of other factors, building a robust person re-identification algorithm in open-world is rather challenging. In this paper, we propose two algorithms, indiscriminative patches trim strategy and multi instance multi-label learning method, to fix the person re-identification in closed short-term surveillance network. There are two main contributions of this paper: first, we define the discriminative region in a person's image. Correspondingly, an adapted canopy-kmeans algorithm is proposed to evaluate the discriminability of image patches which form the discriminative regions. Besides, two strategies, in local image and in global gallery dataset, are proposed to filter out distractions. Finally, the true discriminative patches are employed to compute the similarity between two images, and then used to re-identify pedestrians. Second, we first introduce the multi-instance multi-label learning methods into re-identification, and hence we propose a framework of solving person re-identification by applying MIMLL. We employ two MIMLL methods, the MIMLBOOST and the MIMLSVM, to detect attributes in each image, and those detected attributes contribute to recognize different pedestrians. Experiments on two benchmark datasets show the competitive performance of the two proposed algorithms. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Person re-identification multi-instance multi-label learning Canopy-kmeans

来源：评论

学校读者我要写书评

暂无评论

MIMLTWSVM: Twin Support Vector Machine for multi-instance multi-label learning 11

MIMLTWSVM: Twin Support Vector Machine for Multi-Instance Mu...

引用

11th International Conference on Industrial and Information Systems (ICIIS)

作者： Tomar, Divya Agarwal, Sonali Indian Inst Informat Technol Allahabad Uttar Pradesh India

ISBN: (纸本)9781509038183

Recently, multi instance multi label (MIML) learning has attracted the attention of researchers in which an example not only belongs to multiple instances but also associated with multiple class labels. This study proposes a novel multiinstance multi-label twin support vector machine (MIMLTWSVM) classifier by extending the recently proposed binary twin support vector machine (TWSVM) classifier. MIMLTWSVM classifier involves two steps-(1) the problem of multi-instance multi-label has been converted to single instance multi label learning in the first step and (2) in the second step, the derived problem is solved by using multi-label twin support vector machine classifier. The involved Quadratic Programming Problems (QPPs) of proposed classifier has been solved by Successive Over-Relaxation (SOR) technique to speed up the training procedure. The experiment has been conducted on two MIML benchmark datasets-Scene and Reuters. The experimental results demonstrate the superiority of the proposed classifier over several existing state-of-the-art MIML classifiers such as MIMLSVM, MIMLRBF, MIMLBOOST, MIML-kNN and (MMIML)-M-3.

关键词： multi-instance multi-label learning Twin Support Vector Machine Succesive Over-Relaxtion

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：