Low-rank matrix completion aims to recover matrices with missing entries and has attracted considerable attention from machine learning researchers. Most of the existing methods, such as weighted nuclear-norm-minimization-based methods and Qatar Riyal (QR)-decomposition-based methods, cannot provide both convergence accuracy and convergence speed. To investigate a fast and accurate completion method, an iterative QR-decomposition-based method is proposed for computing an approximate singular value decomposition. This method can compute the largest r (r>0) singular values of a matrix by iterative QR decomposition. Then, under the framework of matrix trifactorization, a method for computing an approximate SVD based on QR decomposition (CSVD-QR)-based L2,1-norm minimization method (LNM-QR) is proposed for fast matrix completion. Theoretical analysis shows that this QR-decomposition-based method can obtain the same optimal solution as a nuclear norm minimization method, i.e., the L2,1-norm of a submatrix can converge to its nuclear norm. Consequently, an LNM-QR-based iteratively reweighted L2,1-norm minimization method (IRLNM-QR) is proposed to improve the accuracy of LNM-QR. Theoretical analysis shows that IRLNM-QR is as accurate as an iteratively reweighted nuclear norm minimization method, which is much more accurate than the traditional QR-decomposition-based matrix completion methods. Experimental results obtained on both synthetic and real-world visual data sets show that our methods are much faster and more accurate than the state-of-the-art methods.
9 August 2021 in IEEE Transactions on Image Processing
Facial action units (AUs) analysis plays an important role in facial expression recognition (FER). Existing deep spectral convolutional networks (DSCNs) have made encouraging performance for FER based on a set of facial local regions and a predefined graph structure. However, these regions do not have close relationships to AUs, and DSCNs cannot model the dynamic spatial dependencies of these regions for estimating different facial expressions. To tackle these issues, we propose a novel double dynamic relationships graph convolutional network (DDRGCN) to learn the strength of the edges in the facial graph by a trainable weighted adjacency matrix. We construct facial graph data by 20 regions of interest (ROIs) guided by different facial AUs. Furthermore, we devise an efficient graph convolutional network in which the inherent dependencies of vertices in the facial graph can be learned automatically during network training. Notably, the proposed model only has 110K parameters and 0.48MB model size, which is significantly less than most existing methods. Experiments on four widely-used FER datasets demonstrate that the proposed dynamic relationships graph network achieves superior results compared to existing light-weight networks, not just in terms of accuracy but also model size and speed.
In this paper, a face spoofing detection method called the Fully Convolutional Network with Domain Adaptation and Lossless Size Adaptation (FCN-DA-LSA) is proposed. As its name suggests, the FCN-DA-LSA includes a lossless size adaptation preprocessor followed by an FCN based pixel-level classifier embedded with a domain adaptation layer. The FCN local classifier makes full use of the basic properties of face spoof distortion namely ubiquitous and repetitive. The domain adaptation (DA) layer improves generalization across different domains. The lossless size adaptation (LSA) preserves the highfrequent spoof clues caused by the face recapture process. The ablation study shows that both DA and the LSA are necessary for high-accuracy face spoofing detection. The FCN-LSA obtains competitive performance among the state-of-the-art methods. With the help of small-sample external data in the target domain (2/50, 2/50, and 1/20 subjects for CASIA-FASD, Replay-Attack, and OULU-NPU respectively), the FCN-DA-LSA further improves the performance and outperforms the existing methods.