Search

This study introduces a unified approach to tackle challenges in both low-level and high-level vision tasks for image processing. The framework integrates faster nonconvex low-rank matrix computations and continuity techniques to yield efficient and high-quality results. In addressing real-world image complexities like noise, variations, and missing data, the framework exploits the intrinsic low-rank structure of the data and incorporates specific residual measurements. The optimization problem for low-rank matrix learning is effectively solved using the nonconvex Proximal Block Coordinate Descent (PBCD) algorithm, resulting in nearly unbiased estimators. Rigorous theoretical analysis ensures both local and global convergence. The PBCD algorithm updates blocks of variables iteratively with closed-form solutions, adeptly handling nonconvexity and promoting faster convergence. Notably, the framework incorporates the randomized singular value decomposition (RSVD) technique and introduces a continuous strategy for adaptive model parameter updates. These strategic choices reduce computational complexity while maintaining result quality. They offer fine-tuned control over the desired rank of the learned matrix and enhance robustness in a straightforward manner. Furthermore, the versatility of the proposed nonconvex PBCD algorithm extends to handling problems with multiple variables, as supported by theoretical analysis. Experimental evaluations, spanning various image low-level and high-level vision tasks such as inpainting, classification, and clustering, validate the effectiveness and efficiency of our framework across diverse databases. The source code is available at https://github.com/ZhangHengMin/FNPBCD%5fLR. In a nutshell, our framework provides a unified solution to tackle both low-level and high-level vision tasks in images. By combining fast nonconvex low-rank matrix learning with adaptive parameter updates, we achieve efficient computation, yielding high-quality results that demonstrate robustness against various types of noise. The evaluations further endorse the reliability and applicability of our proposed framework. • Integrating nonconvex estimators serves to enhance learning capabilities; • Introducing a unified framework generalizes multiple rank-relaxed problems; • The combination of RSVD and continuity techniques yields an efficient solver; • The superiority is established and reinforced through experimental validations. [ABSTRACT FROM AUTHOR]

The low-rank (LR) property is widely applied to capture the global as well as intrinsic structure of the given data in different visual information processing tasks. Actually, there are three key information to determine the performance and generalization low-rank property based methods: (1) visual intrinsic structural information, (2) visual representation structural information, (3) visual robust information. To achieve these jointly in a unified framework, in this paper, we propose D ual L ow-rank S tructure E mbedding (DLSE) that embeds structural and robust information. We additionally proposed the J oint M atrix-based L inear R epresentation (JMLR) and theoretically proved it can realize DLSE. The proposed method was validated on 6 datasets (from 1,440 samples to 70,000 samples in size) and showed a promising performance in visual recognition (14.32% improvement compared with the deep features). In addition, we performed multiple analysis on robustness, representation, and its parameters to show the effectiveness of DLSE from different aspects. [ABSTRACT FROM AUTHOR]

In recent years, low-rank matrix recovery problems have attracted much attention in computer vision and machine learning. The corresponding rank minimization problems are both combinational and NP-hard in general, which are mainly solved by both nuclear norm and Schatten-p ($0 < {p} < 1$) norm based optimization algorithms. However, inspired by weighted nuclear norm and Schatten-p norm as the relaxations of rank function, the main merits of this work firstly provide a modified Schatten-p norm in the affine matrix rank minimization problem, denoted as the modified Schatten-p norm minimization (MSpNM). Secondly, its surrogate function is constructed and the equivalence relationship with the MSpNM is further achieved. Thirdly, the iterative singular value thresholding algorithm (ISVTA) is devised to optimize it, and its accelerated version, i.e., AISVTA, is also obtained to reduce the number of iterations through the well-known Nesterov’s acceleration strategy. Most importantly, the convergence guarantees and their relationship with objective function, stationary point and variable sequence generated by the proposed algorithms are established under some specific assumptions, e.g., Kurdyka-Łojasiewicz (K) property. Finally, numerical experiments demonstrate the effectiveness of the proposed algorithms in the matrix completion problem for image inpainting and recommender systems. It should be noted that the accelerated algorithm has a much faster convergence speed and a very close recovery precision when comparing with the proposed non-accelerated one. [ABSTRACT FROM AUTHOR]

For face recognition, sparse coding based classification methods have demonstrated the inspiring attraction in dealing with the pixel-level based sparse or gaussian noise, and nuclear norm based matrix regression (NMR) methods have shown the robustness in handling with the image-level based structural noise (e.g., occlusions, illuminations). Such regression methods have two limitations: one is that both ignore the label information of training samples and the similarity relationship between the training samples and the testing ones, the other is that nuclear norm as the rank relaxation can make the obtained solution deviate from the original matrix since its over-relaxations to the larger singular values. To overcome both limitations, this paper presents nonconvex relaxation based matrix regression (NRMR) methods: one is called locality-constrained group sparsity regularized nonconvex matrix gamma norm regression model for the s tructural noise (NRMRS), and the other extends it to the locality-constrained group sparsity regularized matrix gamma and minimax concave plus (MCP) regression model for the m ixed noise (NRMRM), i.e., structural noise plus sparse noise. Two variants of inexact augmented Lagrange multiplier (IALM) algorithms including nonconvex IALM (NC-IALM) and majorization–minization IALM (MM-IALM) are devised to solve the proposed models, respectively. Finally, experiments on Extended Yale B, AR and CUHKFS databases can show the superiority of our methods to face recognition with structural noise and mixed noise. [ABSTRACT FROM AUTHOR]

• Proposed a novel generalized intra- and inter-class kernel constraint (IIKC). • IIKC focused on improving the separability and margin between nearby data points. • IIKC can be directly embedded into LDA algorithms, with no increase of dimension. • Extensive experiments showed the effectiveness of the proposed IIKC. Linear discriminant analysis (LDA) as a classical supervised dimensionality reduction method has shown powerful capability in various image classification tasks. The purpose of LDA seeks an optimal linear transformation that maps the original data to a low-dimensional space. Inspired by the fact that the kernel trick can capture the nonlinear similarity of features, we propose a novel generalized distance constraint dubbed intra-class and inter-class kernel constraint (IIKC). The proposed IIKC explicitly models the category kernel distance and focuses on helping the original LDA capture more discriminant features in order to further improve the separability and magnitude difference between nearby data points. Our proposed method with IIKC aims to achieve maximum category separability by minimizing the intra-class kernel distances as well as maximizing the inter-class kernel distance, simultaneously. Extensive experimental results on six publicly available benchmark databases illustrate that the LDA-based methods embedded with the proposed IIKC significantly improve the discrimination ability and achieve a better classification performance than the original and state-of-the-art LDA algorithms. [ABSTRACT FROM AUTHOR]

Although arbitrary style transfer has been a hot topic in computer vision, most existing methods that directly align style and content features frequently result in unnatural effects in the generated images, such as over-stylization and style leakage. In this paper, we introduce a novel progressive Intrinsic-style Distribution Matching (ISDM) approach which initially aligns the intrinsic style distribution of both style and content images and then integrates it with the image's content component. This novel approach can effectively alleviate the issue of over-stylization while preserving the content structure, particularly in the case of high contrast and vivid colors. To further enhance the performance of our method, we propose a learnable multi-level style modulation module to assist the network in aligning the intrinsic style distributions. Moreover, two contrastive objectives are proposed to improve the ability of the encoder to extract more distinct and representative intrinsic content and intrinsic style features. Extensive experimental results showcase that our approach can preserve more content details than state-of-the-art methods. It can also generate more natural images, especially when the style image has high contrast and vivid colors. [ABSTRACT FROM AUTHOR]

• A new HSI classification model is proposed based on a bidirectional GRU network guided by a three-dimensional Softmax mechanism. • The proposed model leverages the fact that hyperspectral images can be treated as a type of sequence data by introducing bidirectional GRU to process sequences. • The model is evaluated on four widely used hyperspectral datasets, and extensive experiments demonstrate that it is robust. Hyperspectral data is a valuable source of both spectral and spatial information. However, to enhance the classification accuracy of hyperspectral image features, it is crucial to capture the spatial spectral features of image elements. The recent years have witnessed the potentials of deep learning methods have shown great promise in the hyperspectral image classification due to their ability to model complex structures and extract multiple features in an end-to-end fashion. Since hyperspectral images can be viewed as sequential data, we propose a novel three-dimensional Softmax mechanism-guided bidirectional GRU network (TDS-BiGRU) for HSI classification. By utilizing a bidirectional GRU to process the sequence data, our method can significantly reduce the processing time. Furthermore, the proposed three-dimensional Softmax mechanism leverages three branches to capture cross-latitude interactions and calculate Softmax weights, which enables us to obtain deeper features with greater discriminative power. The experimental results demonstrate that the proposed method outperforms several prevalent algorithms on four hyperspectral remote sensing datasets. Additionally, we conduct thorough comparisons and ablation tests, which further confirm the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Face recognition (FR) via regression analysis-based classification has been widely studied in the past several years. Most existing regression analysis methods characterize the pixelwise representation error via l1 -norm or l2 -norm, which overlook the 2D structure of the error image. Recently, the nuclear norm-based matrix regression model is proposed to characterize low-rank structure of the error image. However, the nuclear norm cannot accurately describe the low-rank structural noise when the incoherence assumptions on the singular values does not hold, since it overpenalizes several much larger singular values. To address this problem, this paper presents the robust nuclear norm to characterize the structural error image and then extends it to deal with the mixed noise. The majorization–minimization (MM) method is applied to derive a iterative scheme for minimization of the robust nuclear norm optimization problem. Then, an efficiently alternating direction method of multipliers (ADMM) method is used to solve the proposed models. We use weighted nuclear norm as classification criterion to obtain the final recognition results. Experiments on several public face databases demonstrate the effectiveness of our models in handling with variations of structural noise (occlusion, illumination, and so on) and mixed noise. [ABSTRACT FROM PUBLISHER]

Recently, regression analysis has become a popular method for face recognition. Various robust regression methods have been proposed to handle with different recognition tasks. In this paper, we attempt to achieve this goal by the strategy of adding an adaptive noise dictionary (AND) to the training samples. In contrast to the previous methods, the noise dictionary (ND) is adaptive to different kinds of noise and extracted automatically. To get an effective noise dictionary, the Iteratively Reweighted Robust Principal Component Analysis (IRRPCA) is proposed. A corresponding classifier based on linear regression is presented for recognition. As this adaptive noise dictionary can describe the noise distribution of testing samples, it is robust to various kinds of noise and applicable for recognition tasks with occluded or corrupted images. This method is also extended to deal with misaligned images. Experiments are conducted on AR, Yale B, CMU PIE, CMU Multi-Pie, LFW and Pubfig databases to verify the robustness of our method to variations in occlusion, corruption, illumination, misalignment, etc. [ABSTRACT FROM AUTHOR]

Objectives: Angiopoietin-like protein 2 (ANGPTL2), a recently identified pro-inflammatory cytokine, is mainly secreted from the adipose tissue. This study aimed to explore the role of ANGPTL2 in adipose tissue inflammation and macrophage activation in a mouse model of diabetes. Methodology/Principal Findings: Adenovirus mediated lacZ (Ad-LacZ) or human ANGPTL2 (Ad-ANGPTL2) was delivered via tail vein in diabetic db/db mice. Ad-ANGPTL2 treatment for 2 weeks impaired both glucose tolerance and insulin sensitivity as compared to Ad-LacZ treatment. Ad-ANGPTL2 treatment significantly induced pro-inflammatory gene expression in white adipose tissue. We also isolated stromal vascular fraction from epididymal fat pad and analyzed adipose tissue macrophage and T lymphocyte populations by flow cytometry. Ad-ANGPTL2 treated mice had more adipose tissue macrophages (F4/80+CD11b+) and a larger M1 macrophage subpopulation (F4/80+CD11b+CD11c+). Moreover, Ad-ANGPTL2 treatment increased a CD8-positive T cell population in adipose tissue, which preceded increased macrophage accumulation. Consistent with our in vivo results, recombinant human ANGPTL2 protein treatment increased mRNA levels of pro-inflammatory gene products and production of TNF-α protein in the human macrophage-like cell line THP-1. Furthermore, Ad-ANGPTL2 treatment induced lipid accumulation and increased fatty acid synthesis, lipid metabolism related gene expression in mouse liver. Conclusion: ANGPTL2 treatment promotes macrophage accumulation and activation. These results suggest potential mechanisms for insulin resistance. [ABSTRACT FROM AUTHOR]

Dentin matrix protein 1 (DMP1) is an acidic non-collagenous protein that is necessary for the proper biomineralization of bone, cartilage, cementum, dentin, and enamel. Dentin matrix protein 1 is highly phosphorylated and potentially glycosylated, but there is no experimental data identifying which specific amino acids are modified. For the purpose of facilitating the characterization of DMP1 from pig, which has the advantage of large developing teeth for obtaining protein in quantity and extensive structural information concerning other tooth matrix proteins, we characterized the porcine DMP1 cDNA and gene structure, raised anti-peptide immunoglobulins that are specific for porcine DMP1, and detected DMP1 protein in porcine tooth extracts and histological sections. Porcine DMP1 has 510 amino acids, including a 16-amino acid signal peptide. The deduced molecular weight of the secreted, unmodified protein is 53.5 kDa. The protein has 93 serines and 12 threonines in the appropriate context for phosphorylation, and four asparagines in a context suitable for glycosylation. Dentin matrix protein 1 protein bands with apparent molecular weights between 30 and 45 kDa were observed in partially purified dentin extracts. In developing teeth, immunohistochemistry localized DMP1 in odontoblasts and the dentinal tubules of mineralized dentin and in ameloblasts, but not in the enamel matrix. [ABSTRACT FROM AUTHOR]

Background: Vein graft failure is a major clinical problem with no effective medical therapies; however, its underlying mechanisms remain incompletely understood. PCSK9 increases LDL-cholesterol levels by degrading LDL receptor (LDLR) and may promote vascular inflammation. We explored a new mechanism of macrophage activation and vein graft disease induced by circulating PCSK9 in an LDLR-independent fashion. Methods and Results: Endotoxin-free recombinant PCSK9 increased the expression of pro-inflammatory molecules (e.g., IL-1β, TNFα, MCP-1) in human primary macrophages and peritoneal macrophages of LDLR-/- mice (Fig. A, n=5), suggesting its LDLR-independent pro-inflammatory effects. We examined in vivo the LDLR-independent role of circulating PCSK9 in experimental vein graft lesions. We transferred the inferior vena cava to the carotid artery of fat-fed LDLR-/- mice and analyzed the grafts 4 weeks after implantation. Hepatic overproduction of PCSK9 involved a single injection of adenoassociated virus (AAV) vector encoding a gain-of-function mutant of PCSK9 (rAAV8/D377Y-mPCSK9) or control LacZ (1x1011 vg, i.v.). In LDLR-/- mice, AAV-PCSK9 increased circulating PCSK9, but caused no changes in the serum lipid profile, as expected. By ultrasonography, AAV-PCSK9-treated mice showed statistically significant increases in the vessel wall area and 3D-volume of vein graft lesions than did control mice. These results were consistent with increased intimal area and thickness by AAV-PCSK9 as assessed by histological analysis (Fig. B, n=11-12). Intravital molecular imaging revealed that AAV-PCSK9 promoted macrophage phagocytic and MMP activity associated with decreased collagen. Conclusions: Circulating PCSK9 may induce macrophage activation and contribute to the vein graft lesion development via mechanisms independent of LDLR degradation and blood cholesterol levels. PCSK9 may be a promising therapeutic target for vein graft failure. [ABSTRACT FROM AUTHOR]