Motivated by the advance of deep learning methods, deep unfolding methods such as deep convolutional dictionary learning have achieved great success in image denoising tasks. The main advantages are ...inheriting both the merits of deep learning (strong learning capacity) and traditional machine learning (powerful interpretable capacity). We observe that the update of dictionaries and coefficients is highly correlated with the previous iterative stage information for deep unfolding-based methods. However, most existing deep convolutional dictionary learning methods deal with each iteration step individually, ignoring the inner-memory within the stage and cross-memory across the stages. To alleviate these issues, we propose a dynamic inner-cross memory augmented attentional dictionary learning (M2ADL) network with attention guided residual connection module, which utilizes the previous important stage features such that better uncovering the inner-cross information. Specifically, the proposed inner-cross memory fully utilizes the previous stage's hidden and last-layer information to learn the dictionary. In addition, we develop a dual attention-guided residual connection module to well exploit the deep feature learning ability to capture the spatial-spectral attention across the deep tensor-based features. Considerable experiments on both synthetic and real image datasets demonstrate the superiority of the proposed method over other state-of-the-art methods.
Deep-learning-based methods have been successfully applied to fault diagnosis of rotating machinery. However, the domain mismatch among different operating conditions significantly deteriorates ...diagnostic performance of these methods in industrial applications. To solve this problem, a new fault diagnosis model based on capsule neural network (Cap-net) is constructed, and a novel online domain adaptation learning method based on deep reinforcement learning (DRL) is proposed in this article to improve the adaptivity of the fault diagnosis model. In this method, the Cap-net is first introduced into the DRL as an agent to extract representative features and diagnoses fault. Moreover, the online domain adaptation learning of the agent is conducted based on the Q-learning of the DRL so as to adapt to different operating domains that have never been experienced. Specifically, an online feature dictionary combined with cosine similarity is designed to coarsely label the online data collected from different operating domain, while a reward mechanism is defined to evaluate the obtained label. Subsequently, the online data, the corresponding label, and the reward are used to optimize the agent to obtain the desired diagnostic model. Two experiment studies are implemented to verify the effectiveness of the proposed method. The experimental results show that the proposed method has more excellent diagnostic performance and adaptivity than the existing popular methods.
This paper studies the problem of recovering the authentic samples that lie on a union of multiple subspaces from their corrupted observations. Due to the high-dimensional and massive nature of ...today's data-driven community, it is arguable that the target matrix (i.e., authentic sample matrix) to recover is often low-rank. In this case, the recently established Robust Principal Component Analysis (RPCA) method already provides us a convenient way to solve the problem of recovering mixture data. However, in general, RPCA is not good enough because the incoherent condition assumed by RPCA is not so consistent with the mixture structure of multiple subspaces. Namely, when the subspace number grows, the row-coherence of data keeps heightening and, accordingly, RPCA degrades. To overcome the challenges arising from mixture data, we suggest to consider LRR in this paper. We elucidate that LRR can well handle mixture data, as long as its dictionary is configured appropriately. More precisely, we mathematically prove that LRR can weaken the dependence on the row-coherence, provided that the dictionary is well-conditioned and has a rank of not too high. In particular, if the dictionary itself is sufficiently low-rank, then the dependence on the row-coherence can be completely removed. These provide some elementary principles for dictionary learning and naturally lead to a practical algorithm for recovering mixture data. Our experiments on randomly generated matrices and real motion sequences show promising results.
Unsupervised Video Matting via Sparse and Low-Rank Representation Zou, Dongqing; Chen, Xiaowu; Cao, Guangying ...
IEEE transactions on pattern analysis and machine intelligence,
2020-June-1, 2020-Jun, 2020-6-1, 20200601, Letnik:
42, Številka:
6
Journal Article
Recenzirano
A novel method, unsupervised video matting via sparse and low-rank representation, is proposed which can achieve high quality in a variety of challenging examples featuring illumination changes, ...feature ambiguity, topology changes, transparency variation, dis-occlusion, fast motion and motion blur. Some previous matting methods introduced a nonlocal prior to search samples for estimating the alpha matte, which have achieved impressive results on some data. However, on one hand, searching inadequate or excessive samples may miss good samples or introduce noise; on the other hand, it is difficult to construct consistent nonlocal structures for pixels with similar features, yielding video mattes with spatial and temporal inconsistency. In this paper, we proposed a novel video matting method to achieve spatially and temporally consistent matting result. Toward this end, a sparse and low-rank representation model is introduced to pursue consistent nonlocal structures for pixels with similar features. The sparse representation is used to adaptively select best samples and accurately construct the nonlocal structures for all pixels, while the low-rank representation is used to globally ensure consistent nonlocal structures for pixels with similar features. The two representations are combined to generate spatially and temporally consistent video mattes. We test our method on lots of dataset including the benchmark dataset for image matting and dataset for video matting. Our method has achieved the best performance among all unsupervised matting methods in the public alpha matting evaluation dataset for images.
Offers biographical information about the more than 1900 people mentioned in the correspondence and works of Erasmus who died after 1450 and were thus approximately his contemporaries.
Woordeboeke word veral geraadpleeg ter wille van die funksie dekodering. Hierdie artikel verskaf 'n sistematiese beskrywing van die invloed wat die funksie dekodering op die woordeboekstrukture en ...datatipes in verskillende woordeboektipes het. Tydens hierdie bespreking word veral aandag gegee aan strukture wat in sowel gedrukte as aanlyn woordeboeke voorkom. Alhoewel die belangrikste datatipe vir dekodering betekenisverklarings/vertalings in meertalige woordeboeke is, fokus hierdie artikel veral op die rol van datatipes soos uitspraakleiding, kollokasies, etikette, voorbeelde en etimologiese leiding. In gedrukte woordeboeke is daar 'n groot ooreenkoms ten opsigte van raamstruktuur (minstens sentrale woordelys en gebruikersleiding), dataverspreidingstruktuur en toegangstruktuur, terwyl verskille veral op die vlak van die makrostruktuur (meer of minder lemmas, verskillende ordenings) en mikrostruktuur (aanduidertipes en hoeveelheid data ten opsigte hiervan) voorkom.
Considering that Coupled Dictionary Learning (CDL) method can obtain a reasonable linear mathematical relationship between resource images, we propose a novel CDL-based Synthetic Aperture Radar (SAR) ...and multispectral pseudo-color fusion method. Firstly, the traditional Brovey transform is employed as a pre-processing method on the paired SAR and multispectral images. Then, CDL is used to capture the correlation between the pre-processed image pairs based on the dictionaries generated from the source images via enforced joint sparse coding. Afterward, the joint sparse representation in the pair of dictionaries is utilized to construct an image mask via calculating the reconstruction errors, and therefore generate the final fusion image. The experimental verification results of the SAR images from the Sentinel-1 satellite and the multispectral images from the Landsat-8 satellite show that the proposed method can achieve superior visual effects, and excellent quantitative indicators in terms of spectral distortion, correlation coefficient, MSE, NIQE, BRISQUE, and PIQE.
Continuing globalization has meant the increased development and importance of regional and international trade organizations and trade agreements. This Dictionary provides a background to the ...historical development of such systems, as well as giving a global overview of the current situation.
The introduction, as well as explaining the historical background, discusses the major political and economic ideas and controversies, and analyses the current dynamic between international and regional trade organizations.
Impartial analysis and up-to-date information is given in a concise way, detailing:
major international, regional and bilateral trade agreements and organizations
other national and international organizations involved in trade
core concepts/theories in relation to international economics/development and international co-operation
major trade negotiations and disputes
other topics of importance, such as globalization.
Entries are listed alphabetically, and fully cross-referenced for ease of use.
Entries include: Africa Trade Network, Bretton Woods, China-ASEAN Free Trade Area, Dumping, Globalization, Mercosur, Pan-Arab Free Trade Area, Treaty of Nice, World Bank, WTO Secretariat and WWF
As a branch of dictionary learning (DL), analysis dictionary learning has been widely used for pattern classification, which achieves outstanding performance. However, it is still a challenging to ...learn a more compact and discriminative analysis dictionary to ensure that the coding coefficient matrix of training samples presents a more discriminative block diagonal structure. To address this issue, we propose a self-eliminating discriminant analysis dictionary learning (SeDADL) method to learn a discriminant analysis dictionary that makes the coding coefficient matrix have an approximate block diagonal structure. Specifically, we first design a novel analysis dictionary regularization term to improve the discrimination capability of analysis dictionary by eliminating repeated and linearly dependent atoms in the analysis dictionary while preventing the generation of trivial solutions. Then, we design a self-eliminating coding coefficient constraint term to enhance the discrimination capability of spare codes by forcing the coding coefficient matrix to achieve an approximate block diagonal structure. In order to further improve the classification efficiency of SeDADL model, we introduce a linear classification error term into SeDADL model to learn a linear classifier, which constructs the links between spare codes and class labels. Moreover, an efficient iterative algorithm is designed to solve the optimization problem of SeDADL. Extensive experimental results on six datasets demonstrate that SeDADL can achieve satisfactory classification performance compared with some state-of-the-art methods.