Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Computational single-cell RNA-seq (scRNA-seq) methods have been successfully applied to experiments representing a single condition, technology, or species to discover and define cellular phenotypes. However, identifying subpopulations of cells that are present across multiple data sets remains challenging. Here, we introduce an analytical strategy for integrating scRNA-seq data sets based on common sources of variation, enabling the identification of shared populations across data sets and downstream comparative analysis. We apply this approach, implemented in our R toolkit Seurat (http://satijalab.org/seurat/), to align scRNA-seq data sets of peripheral blood mononuclear cells under resting and stimulated conditions, hematopoietic progenitors sequenced using two profiling technologies, and pancreatic cell 'atlases' generated from human and mouse islets. In each case, we learn distinct or transitional cell states jointly across data sets, while boosting statistical power through integrated analysis. Our approach facilitates general comparisons of scRNA-seq data sets, potentially deepening our understanding of how distinct cell states respond to perturbation, disease, and evolution.

/pdf/integrating-single-cell-transcriptomic-data-across-different-3dtsi5w7ob.pdf

Integrating single-cell transcriptomic data across different conditions, technologies, and species.

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features. The face image is divided into several regions from which the LBP feature distributions are extracted and concatenated into an enhanced feature vector to be used as a face descriptor. The performance of the proposed method is assessed in the face recognition problem under different challenges. Other applications and several extensions are also discussed

Face Description with Local Binary Patterns: Application to Face Recognition

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Human mouth is very flexible such that its status (closed or open) is often used as a judgment in the liveness detection of face recognition. However, due to large head pose and illumination variations, accurate mouth status estimation is still challenging in real-world scenarios. In this paper, we propose a deep convolutional neural networks (CNNs) method for mouth status estimation under unconstrained conditions and different types of attacks. Different from previous methods that extract hand-crafted features and then treat the estimation problem as a binary classification task, our method automatically extracts discriminative features via learned convolutional and the pooling layers. To demonstrate the effectiveness of our method and the challenge of mouth status estimation in real-world, we also propose a mouth status estimation dataset that contains 10,714 images in the wild. Experimental results with two types of liveness attacks show that our proposed method outperforms the other traditional methods, especially in the wild condition.

Accurate mouth state estimation via convolutional neural networks

The invention relates to the technical field of image processing, specifically provides a shielded human face image identification apparatus, and aims to solve the technical problem of how to improvethe accuracy of shielded human face image identification. For the purpose, a generative adversarial network model of the image identification apparatus comprises a decoupling network module, a fusionnetwork module and an optimization training module. The decoupling network module can predict a clear human face image and a shielded image according to the shielded human face image. The fusion network module can reconstruct a new shielded human face image according to the predicted clear human face image and shielded image; and, according to the clear human face image and the shielded image, theshielded human face image is predicted. Based on this, the decoupling network module also can reconstruct new clear human face image and shielded image according to the predicted shielded human faceimage. Through an adversarial network composed of the decoupling network module and the fusion network module, the clear human face image can be obtained, so that the accuracy of the shielded human face image identification is improved.

Shielded human face image identification apparatus

In recent years, dictionary learning (DL) has shown significant potential in various classification tasks. However, most of previous works aim to learn a synthesis dictionary. The other major category of DL-analysis dictionary learning has not been fully exploited yet. This paper proposes a novel DL method, named Topology Preserving Dictionary Learning (TPDL). First, we propose a triplet-constraint-based topology preserving loss function to capture the underlying local topological structures of data in a supervised manner. Second, a sparse-label-matrix-based function is integrated into the basic analysis model to improve discriminative ability. Third, Huber M-estimator is employed as a robust metric to handle the errors (e.g., outliers and noise) that possibly exist in data. Then, an alternating optimization algorithm is developed based on half-quadratic minimization and alternate search strategy. Closed-form solutions in each alternating optimization stage speed up the minimization process. Experiments on four commonly used datasets show that our proposed TPDL achieves competitive performance in contrast to state-of-the-art DL methods.

Topology preserving dictionary learning for pattern classification

Automatic object viewpoint estimation from a single image is an important but challenging problem in machine intelligence community. Although impressive performance has been achieved, current state-of-the-art methods still have difficulty to deal with the visual ambiguity and structure ambiguity in real world images. To tackle these problems, a novel Appearance-and-Structure Fusion network, which we call it ASFnet that estimates viewpoint by fusing both appearance and structure information, is proposed in this paper. The structure information is encoded by precise semantic keypoints and can help address the visual ambiguity. Meanwhile, distinguishable appearance features contribute to overcoming the structure ambiguity. Our ASFnet integrates an appearance path and a structure path to an end-to-end network and allows deep features effectively share supervision from both the two complementary aspects. A convolutional layer is learned to fuse the two path results adaptively. To balance the influence from the two supervision sources, a piecewise loss weight strategy is employed during training. Experimentally, our proposed network outperforms state-of-the-art methods on a public PASCAL 3D+ dataset, which verifies the effectiveness of our method and further corroborates the above proposition.

/pdf/an-appearance-and-structure-fusion-network-for-object-2vx9s0m891.pdf

An Appearance-and-Structure Fusion Network for Object Viewpoint Estimation

The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR). Although recent methods have attempted to fill the gap with deep generative networks, most of them suffer from the inevitable misalignment between different face modalities. Instead of imaging sensors, the misalignment primarily results from facial geometric variations that are independent of the spectrum. Rather than building a monolithic but complex structure, this paper proposes a Pose Aligned Cross-spectral Hallucination (PACH) approach to disentangle the independent factors and deal with them in individual stages. In the first stage, an Unsupervised Face Alignment (UFA) module is designed to align the facial shapes of the near-infrared (NIR) images with those of the visible (VIS) images in a generative way, where UV maps are effectively utilized as the shape guidance. Thus the task of the second stage becomes spectrum translation with aligned paired data. We develop a Texture Prior Synthesis (TPS) module to achieve complexion control and consequently generate more realistic VIS images than existing methods. Experiments on three challenging NIR-VIS datasets verify the effectiveness of our approach in producing visually appealing images and achieving state-of-the-art performance in HFR.

Ran He

Papers

Accurate mouth state estimation via convolutional neural networks

Shielded human face image identification apparatus

Topology preserving dictionary learning for pattern classification

An Appearance-and-Structure Fusion Network for Object Viewpoint Estimation

Cross-Spectral Face Hallucination via Disentangling Independent Factors