多視圖特征學(xué)習(xí)方法研究
發(fā)布時間：2019-06-02 07:44
【摘要】：多視圖數(shù)據(jù)從多個角度刻畫同一物體,包含了比傳統(tǒng)的單視圖數(shù)據(jù)更加豐富的分類識別信息,因此近年來多視圖學(xué)習(xí)技術(shù)成為了一個研究熱點。不同視圖數(shù)據(jù)往往存在一定的信息冗余,如何充分地從多視圖數(shù)據(jù)中提取有用特征并且消除冗余是多視圖學(xué)習(xí)技術(shù)的關(guān)鍵問題。針對該問題,本文對多視圖學(xué)習(xí)技術(shù)進(jìn)行了系統(tǒng)的研究,主要研究成果總結(jié)如下:一、提出了兩個多視圖鑒別分析方法,即組遞歸鑒別子空間學(xué)習(xí)(GRDSL)和不相關(guān)局部敏感多視圖鑒別分析(ULSMDA)。GRDSL在數(shù)據(jù)層融合多視圖數(shù)據(jù),使用遞歸學(xué)習(xí)的方式將樣本集分解成多個近似集和相應(yīng)的差分集,并在每次遞歸的差分集中學(xué)習(xí)一個鑒別變換。GRDSL設(shè)計了遞歸終止準(zhǔn)則以及投影向量選擇規(guī)則,并能在理論上保證多個鑒別變換的正交性。通過自適應(yīng)的遞歸學(xué)習(xí)過程,GRDSL可以從多視圖數(shù)據(jù)中有效地學(xué)得充足的有用特征。ULSMDA聯(lián)合學(xué)習(xí)了多個視圖特定的投影變換,使得在投影空間中,原始近鄰的同類樣本相互聚集,而原始近鄰的異類樣本相互排斥。ULSMDA考慮了跨視圖數(shù)據(jù)的一致性,并設(shè)計了不相關(guān)約束,用于減少變換間的冗余。ULSMDA充分地使用了多視圖數(shù)據(jù)的局部結(jié)構(gòu)信息用于不相關(guān)鑒別特征的學(xué)習(xí)。四個數(shù)據(jù)集上的實驗結(jié)果表明了這兩個方法的有效性。二、提出了三個多視圖字典學(xué)習(xí)方法,即不相關(guān)多視圖鑒別字典學(xué)習(xí)(UMD2L)、多視圖低秩字典學(xué)習(xí)(MLDL)和多視圖低秩共享結(jié)構(gòu)化字典學(xué)習(xí)(MLS2DL)。通過使得字典原子與類別標(biāo)記相對應(yīng),UMD2L從多視圖數(shù)據(jù)中聯(lián)合地學(xué)習(xí)多個結(jié)構(gòu)化字典。UMD2L設(shè)計了不相關(guān)約束用于減少不同視圖字典間的冗余。從增強(qiáng)字典鑒別能力以及消除冗余這兩方面出發(fā),UMD2L提升了多視圖字典學(xué)習(xí)技術(shù)有用特征學(xué)習(xí)的能力。MLDL將低秩學(xué)習(xí)技術(shù)引入到多視圖學(xué)習(xí)技術(shù)中,運用低秩矩陣恢復(fù)理論來解決噪聲存在情況下的多視圖字典學(xué)習(xí)問題。MLDL設(shè)計了結(jié)構(gòu)化不相關(guān)約束,并為多視圖字典學(xué)習(xí)技術(shù)提供了高效的基于聯(lián)合表示的分類機(jī)制。MLDL為多視圖字典學(xué)習(xí)技術(shù)提供了在噪聲影響情況下充分學(xué)習(xí)有用特征的方案。MLS2DL關(guān)注視圖間共享信息的挖掘,提出在學(xué)習(xí)多個視圖特定的低秩結(jié)構(gòu)化字典的同時對視圖共享低秩結(jié)構(gòu)化字典進(jìn)行學(xué)習(xí)。MLS2DL為多視圖字典學(xué)習(xí)技術(shù)提供了在消除視圖間冗余信息的同時有效利用多視圖有利相關(guān)性的方案。實驗證明了相比于代表性的多視圖子空間學(xué)習(xí)方法和多視圖字典學(xué)習(xí)方法以及提出的GRDSL和ULSMDA方法,這三個方法可以獲得更優(yōu)的分類效果。三、提出了一個半監(jiān)督多視圖鑒別分析方法,即不相關(guān)半監(jiān)督視圖內(nèi)和視圖間流形鑒別學(xué)習(xí)(USI2MD)。USI2MD給出了半監(jiān)督視圖內(nèi)和視圖間流形鑒別學(xué)習(xí)機(jī)制,使用無標(biāo)記樣本的局部近鄰結(jié)構(gòu),以及有標(biāo)記樣本視圖內(nèi)和視圖間的鑒別信息來從多視圖數(shù)據(jù)中提取特征。USI2MD設(shè)計了一個半監(jiān)督不相關(guān)約束,用于減少半監(jiān)督場景下不利的多視圖特征相關(guān)性。USI2MD充分使用了視圖內(nèi)和視圖間的有用信息用于半監(jiān)督場景下不相關(guān)鑒別特征的學(xué)習(xí)。實驗證實了該方法相對于代表性的半監(jiān)督多視圖子空間學(xué)習(xí)方法的有效性。
[Abstract]:Multi-view data depict the same object from multiple angles, which contains the classification identification information which is more abundant than the traditional single-view data, so the multi-view learning technology has become a hot topic in recent years. Different view data often have some information redundancy, how to extract useful features from multi-view data sufficiently and to eliminate redundancy is a key issue in multi-view learning technology. In view of this problem, this paper studies the multi-view learning technology, and the main research results are as follows:1. Two multi-view identification and analysis methods are put forward. I.e., group recursive authentication sub-space learning (grDSL) and non-relevant local-sensitive multi-view identification analysis (ULSDA). And a discrimination transformation is learned every time the differential concentration is recursive. GRDSL has designed the recursive termination criteria and the projection vector selection rules and can theoretically ensure the orthogonality of multiple discrimination transforms. Through the self-adaptive recursive learning process, the GRDSL can have sufficient useful features in the multi-view data efficiently. The ULSFDA combines multiple view-specific projection transformations so that in the projection space, the same samples of the original neighbors are aggregated with each other, while the heterogeneous samples of the original neighbors are mutually exclusive. ULSDA takes into account the consistency of cross-view data, and designs non-related constraints to reduce the redundancy between transforms. The ULSDA fully uses the local structure information of the multi-view data for learning of the non-related authentication features. The experimental results on the four data sets show the effectiveness of the two methods. Two, three multi-view dictionary learning methods (UMD2L), multi-view low-rank dictionary learning (MLDL) and multi-view low-rank shared structured dictionary learning (MLS2DL) are proposed. By making the dictionary atoms correspond to the category tags, the UMD2L jointly learns a plurality of structured dictionaries from the multi-view data. The UMD2L is designed with non-related constraints to reduce the redundancy between different view dictionaries. From the two aspects of enhancing the ability of the dictionary and eliminating the redundancy, the UMD2L improves the ability of the multi-view dictionary learning to study the useful features. MLDL introduces the low-rank learning technology into the multi-view learning technology, and uses the low-rank matrix recovery theory to solve the problem of multi-view dictionary learning in the case of noise. MLDL has designed a structured non-related constraint and provides a highly efficient joint-representation-based classification mechanism for multi-view dictionary learning technology. The MLDL is a multi-view dictionary learning technique that provides a scheme that fully learns useful features in the event of noise impact. The MLS2DL focuses on the mining of shared information among the views, and proposes to study the view-sharing low-rank structured dictionary while learning a plurality of view-specific low-rank structured dictionaries. The MLS2DL is a multi-view dictionary learning technique that provides a scheme to effectively utilize multi-view advantageous correlation while eliminating redundant information between views. The experiments prove that the three methods can obtain better classification effect than the representative multi-view subspace learning method and multi-view dictionary learning method and the proposed GRDSL and ULSDA method. in this paper, a semi-supervised multi-view identification and analysis method is proposed, that is, there is no relevant semi-supervised view and inter-view manifold discrimination learning (US2MD). US2MD gives a semi-supervised and inter-view manifold discrimination learning mechanism, And identifying information in the view of the tagged sample and the view to extract features from the multi-view data. US2MD designed a semi-supervised non-related constraint to reduce the negative multi-view feature dependency in a semi-supervised scenario. The US2MD fully uses the useful information in the view and between the views to be used to semi-monitor the learning of the non-relevant authentication features in the scene. The experiment verifies the effectiveness of the method with respect to the representative semi-supervised multi-view subspace learning method.
【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP181
本文編號：2490936
[Abstract]:Multi-view data depict the same object from multiple angles, which contains the classification identification information which is more abundant than the traditional single-view data, so the multi-view learning technology has become a hot topic in recent years. Different view data often have some information redundancy, how to extract useful features from multi-view data sufficiently and to eliminate redundancy is a key issue in multi-view learning technology. In view of this problem, this paper studies the multi-view learning technology, and the main research results are as follows:1. Two multi-view identification and analysis methods are put forward. I.e., group recursive authentication sub-space learning (grDSL) and non-relevant local-sensitive multi-view identification analysis (ULSDA). And a discrimination transformation is learned every time the differential concentration is recursive. GRDSL has designed the recursive termination criteria and the projection vector selection rules and can theoretically ensure the orthogonality of multiple discrimination transforms. Through the self-adaptive recursive learning process, the GRDSL can have sufficient useful features in the multi-view data efficiently. The ULSFDA combines multiple view-specific projection transformations so that in the projection space, the same samples of the original neighbors are aggregated with each other, while the heterogeneous samples of the original neighbors are mutually exclusive. ULSDA takes into account the consistency of cross-view data, and designs non-related constraints to reduce the redundancy between transforms. The ULSDA fully uses the local structure information of the multi-view data for learning of the non-related authentication features. The experimental results on the four data sets show the effectiveness of the two methods. Two, three multi-view dictionary learning methods (UMD2L), multi-view low-rank dictionary learning (MLDL) and multi-view low-rank shared structured dictionary learning (MLS2DL) are proposed. By making the dictionary atoms correspond to the category tags, the UMD2L jointly learns a plurality of structured dictionaries from the multi-view data. The UMD2L is designed with non-related constraints to reduce the redundancy between different view dictionaries. From the two aspects of enhancing the ability of the dictionary and eliminating the redundancy, the UMD2L improves the ability of the multi-view dictionary learning to study the useful features. MLDL introduces the low-rank learning technology into the multi-view learning technology, and uses the low-rank matrix recovery theory to solve the problem of multi-view dictionary learning in the case of noise. MLDL has designed a structured non-related constraint and provides a highly efficient joint-representation-based classification mechanism for multi-view dictionary learning technology. The MLDL is a multi-view dictionary learning technique that provides a scheme that fully learns useful features in the event of noise impact. The MLS2DL focuses on the mining of shared information among the views, and proposes to study the view-sharing low-rank structured dictionary while learning a plurality of view-specific low-rank structured dictionaries. The MLS2DL is a multi-view dictionary learning technique that provides a scheme to effectively utilize multi-view advantageous correlation while eliminating redundant information between views. The experiments prove that the three methods can obtain better classification effect than the representative multi-view subspace learning method and multi-view dictionary learning method and the proposed GRDSL and ULSDA method. in this paper, a semi-supervised multi-view identification and analysis method is proposed, that is, there is no relevant semi-supervised view and inter-view manifold discrimination learning (US2MD). US2MD gives a semi-supervised and inter-view manifold discrimination learning mechanism, And identifying information in the view of the tagged sample and the view to extract features from the multi-view data. US2MD designed a semi-supervised non-related constraint to reduce the negative multi-view feature dependency in a semi-supervised scenario. The US2MD fully uses the useful information in the view and between the views to be used to semi-monitor the learning of the non-relevant authentication features in the scene. The experiment verifies the effectiveness of the method with respect to the representative semi-supervised multi-view subspace learning method.
【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP181
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 程圣軍;劉家鋒;黃慶成;唐降龍;;基于樣本條件價值改進(jìn)的Co-training算法[J];自動化學(xué)報;2013年10期
，本文編號：2490936
本文鏈接：http://sikaile.net/shoufeilunwen/xxkjbs/2490936.html
最近更新
教材專著
