检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Juan Jing Tao Wan Jiajia Cao Zengchang Qin School of Biological Science and Medical Engineering Beihang University China Intelligent Computing & Machine Learning Lab Beihang University China

ISBN: (纸本)9781479923519

Segmentation of nuclei on breast cancer histopathological images is considered a basic and essential step for diagnosis in a computer-aided diagnosis framework. Nuclear segmentation remains a challenging problem due to the inherent diversity of cancer biology and the variability of the tissue appearance. We present an automatic nuclear segmentation method using an improved hybrid active contour (AC) model driven by both boundary and region information. The initialization of segmentation based on morphological operations and watershed allows for generation of initial closed curves and reduction in computational load of curve evolution for the AC model. Color gradients are computed to capture image gradients along the margin of nucleus. The AC segmentation scheme is performed in a coarse-to-fine fashion which can help to solve the problem of multiple object overlap in an image scene. Segmentation performance was evaluated on various breast cancer histopathological images with different grades and was compared with the existing popular AC models, suggesting that our improved hybrid active contour model can be used to build an accurate and robust nuclear segmentation tool.

关键词： Image segmentation Computational modeling Breast cancer Mathematical model Active contours Solid modeling Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Marginalized denoising autoencoder via graph regularization for domain adaptation

Marginalized denoising autoencoder via graph regularization ...

引用

20th International Conference on Neural Information Processing, ICONIP 2013

作者： Peng, Yong Wang, Shen Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong Unviersity Shanghai 200240 China Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI 48109 United States MoE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong Unviersity Shanghai 200240 China

ISBN: (纸本)9783642420412

Domain adaptation, which aims to learn domain-invariant features for sentiment classification, has received increasing attention. The underlying rationality of domain adaptation is that the involved domains share some common latent factors. Recently neural network based on Stacked Denoising Auto-Encoders (SDA) and its marginalized version (mSDA) have shown promising results on learning domain-invariant features. To explicitly preserve the intrinsic structure of data, this paper proposes a marginalized Denoising Autoencoders via graph Regularization (GmSDA) in which the autoencoder based framework can learn more robust features with the help of newly incorporated graph regularization. The learned representations are fed into the sentiment classifiers and experiments show that the GmSDA can effectively improve the classification accuracy when comparing with some state-of-the-art models on the cropped Amazon benchmark data set. © Springer-Verlag 2013.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Structure preserving low-rank representation for semi-supervised face recognition

Structure preserving low-rank representation for semi-superv...

引用

20th International Conference on Neural Information Processing, ICONIP 2013

作者： Peng, Yong Wang, Suhang Wang, Shen Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong Unviersity Shanghai 200240 China Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI 48109 United States MOE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong Unviersity Shanghai 200240 China

ISBN: (纸本)9783642420412

Constructing an informative and discriminative graph plays an important role in the graph based semi-supervised learning methods. Among these graph construction methods, low-rank representation based graph, which calculates the edge weights of both lab.led and unlab.led samples as the low-rank representation (LRR) coefficients, has shown excellent performance in semi-supervised learning. In this paper, we additionally impose twofold constraints (local affinity and distant repulsion) on the LRR graph. The improved model, termed structure preserving LRR (SPLRR), can preserve the local geometrical structure but without distorting the distant repulsion property. Experiments are taken on three widely used face data sets to investigate the performance of SPLRR and the results show that it is superior to some state-of-the-art semi-supervised graphs. © Springer-Verlag 2013.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Topic Model of Observing Chinese Characters

A Topic Model of Observing Chinese Characters

引用

2010 Second International Conference on intelligent Human-machine Systems and Cybernetics(第二届智能人机系统与控制论国际学术会议 IHMSC 2010)

作者： Yunkai Zhang Zengchang Qin College of Software Beihang University Beijing China100191 Intelligent Computing and Machine Learning Lab School of Automation Science and Electrical Engineeri

The Topic Models are a class of hierarchical statistical models for analyzing document collections and it has become one of the most used techniques in Natural Language Processing in the recent years. It assumes that each document could be expressed as a mixture of topics and each topic could be characterized by a distribution over words. In previous research [6], like in English language, Topic Models for Chinese Language use the words as observing data. In this research, we demonstrated the effectiveness of using Chinese characters as the basic units of observing data. The comparisons with those models based on Chinese words and English words are presented.

关键词： Biological system modeling Training Semantics Analytical models Computational modeling Accuracy Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Multi-level network for high-speed multi-person pose estimation

arXiv

引用

arXiv 2019年

作者： Huang, Ying Zhuang, Jiankai Qin, Zengchang Alibaba Business School Hangzhou Normal University Hangzhou Intelligent Computing and Machine Learning Lab School of Asee Beihang University Beijing

In multi-person pose estimation, the left/right joint type discrimination is always a hard problem because of the similar appearance. Traditionally, we solve this problem by stacking multiple refinement modules to increase network's receptive fields and capture more global context, which can also increase a great amount of computation. In this paper, we propose a Multi-level Network (MLN) that learns to aggregate features from lower-level (left/right information), upper-level (localization information), joint-limb level (complementary information) and global-level (context) information for discrimination of joint type. Through feature reuse and its intrarelation, MLN can attain comparable performance to other conventional methods while runtime speed retains at 42 FPS. Copyright © 2019, The Authors. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

DAM: Deliberation, abandon and memory networks for generating detailed and non-repetitive responses in visual dialogue 29

DAM: Deliberation, abandon and memory networks for generatin...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Jiang, Xiaoze Yu, Jing Sun, Yajing Qin, Zengchang Zhu, Zihao Hu, Yue Wu, Qi Institute of Information Engineering Chinese Academy of Sciences Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China AI Research Codemao Inc University of Adelaide Australia

ISBN: (纸本)9780999241165

Visual Dialogue task requires an agent to be engaged in a conversation with human about an image. The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation. In this paper, we propose a novel generative decoding architecture to generate high-quality responses, which moves away from decoding the whole encoded semantics towards the design that advocates both transparency and flexibility. In this architecture, word generation is decomposed into a series of attention-based information selection steps, performed by the novel recurrent Deliberation, Abandon and Memory (DAM) module. Each DAM module performs an adaptive combination of the response-level semantics captured from the encoder and the word-level semantics specifically selected for generating each word. Therefore, the responses contain more detailed and non-repetitive descriptions while maintaining the semantic accuracy. Furthermore, DAM is flexible to cooperate with existing visual dialogue encoders and adaptive to the encoder structures by constraining the information selection mode in DAM. We apply DAM to three typical encoders and verify the performance on the VisDial v1.0 dataset. Experimental results show that the proposed models achieve new state-of-the-art performance with high-quality responses. The code is availab.e at https://***/JXZe/DAM. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-View Document Representation learning for Open-Domain Dense Retrieval

arXiv

引用

arXiv 2022年

作者： Zhang, Shunyu Liang, Yaobo Gong, Ming Jiang, Daxin Duan, Nan Intelligent Computing and Machine Learning Lab School of ASEE Beihang University China Microsoft Research Asia China Microsoft STC Asia

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document can usually answer multiple potential queries from different views. So the single vector representation of a document is hard to match with multi-view queries, and faces a semantic mismatch problem. This paper proposes a multi-view document representation learning framework, aiming to produce multi-view embeddings to represent documents and enforce them to align with different queries. First, we propose a simple yet effective method of generating multiple embeddings through viewers. Second, to prevent multi-view embeddings from collapsing to the same one, we further propose a global-local loss with annealed temperature to encourage the multiple viewers to better align with different potential queries. Experiments show our method outperforms recent works and achieves state-of-the-art results. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Personalizing EEG-based affective models with transfer learning 25

Personalizing EEG-based affective models with transfer learn...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Zheng, Wei-Long Lu, Bao-Liang Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering China Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

Individual differences across subjects and nonstationary characteristic of electroencephalography (EEG) limit the generalization of affective braincomputer interfaces in real-world applications. On the other hand, it is very time consuming and expensive to acquire a large number of subjectspecific lab.led data for learning subject-specific models. In this paper, we propose to build personalized EEG-based affective models without lab.led target data using transfer learning techniques. We mainly explore two types of subject-to-subject transfer approaches. One is to exploit shared structure underlying source domain (source subject) and target domain (target subject). The other is to train multiple individual classifiers on source subjects and transfer knowledge about classifier parameters to target subjects, and its aim is to learn a regression function that maps the relationship between feature distribution and classifier parameters. We compare the performance of five different approaches on an EEG dataset for constructing an affective model with three affective states: positive, neutral, and negative. The experimental results demonstrate that our proposed subject transfer framework achieves the mean accuracy of 76.31% in comparison with a conventional generic classifier with 56.73% in average.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient 41

Double Variance Reduction: A Smoothing Trick for Composite O...

引用

41st International Conference on machine learning, ICML 2024

作者： Di, Hao Ye, Haishan Zhang, Yueling Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China International Business School Beijing Foreign Studies University Beijing China Singapore College of Computing and Data Science NTU Singapore

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random gradient estimation. To reduce this variance, prior works require estimating all partial derivatives, essentially approximating FO information. This approach demands O(d) function evaluations (d is the dimension size), which incurs substantial computational costs and is prohibitive in high-dimensional scenarios. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances. Compared to prior methods, ZPDVR relies solely on random gradient estimates, calls the stochastic zeroth-order oracle (SZO) in expectation O(1) times per iteration, and achieves the optimal O(d(n+κ) log(1/ϵ)) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ϵ is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

English to Chinese translation: How Chinese character matters? 29

English to Chinese translation: How Chinese character matter...

引用

29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015

作者： Wang, Rui Zhao, Hai Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China

Word segmentation is helpful in Chinese natural language processing in many aspects. However it is showed that different word segmentation strategies do not affect the performance of Statistical machine Translation (SMT) from English to Chinese significantly. In addition, it will cause some confusions in the evaluation of English to Chinese SMT. So we make an empirical attempt to translation English to Chinese in the character level, in both the alignment model and language model. A series of empirical comparison experiments have been conducted to show how different factors affect the performance of character-level English to Chinese SMT. We also apply the recent popular continuous s- pace language model into English to Chinese SMT. The best performance is obtained with the BLEU score 41.56, which improve base- line system (40.31) by around 1.2 BLEU s- core.

关键词： Computer aided language translation

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：