arXiv subjects

Xiang Yu

Publications and source records attributed to Xiang Yu.

At least 163 records · Page 9Linked to original sources

arXiv2019

Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild

Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels. We propose that advantages may be derived by combining them, in the form of different insights that lead to a novel design and complementary properties that result in better performance. At the feature level, inspired by insights from semi-supervised learning, we propose a classification-aware domain adversarial neural network that brings target examples into more classifiable regions of source domain. Next, we posit that computer vision insights are more amenable to injection at the pixel level. In particular, we use 3D geometry and image synthesis based on a generalized appearance flow to preserve identity across pose transformations, while using an attribute-conditioned CycleGAN to translate a single source into multiple target images that differ in lower-level properties such as lighting. Besides standard UDA benchmark, we validate on a novel and apt problem of car recognition in unlabeled surveillance images using labeled images from the web, handling explicitly specified, nameable factors of variation through pixel-level and implicit, unspecified factors through feature-level adaptation.

cs.CV↗

arXiv2019

Synergistic Effects of Nanoparticle Heating and Amoxicillin on H. Pylori Inhibition

We report the design and development of a dual-functional magnetic nanoparticle platform for potential treatment of H. pylori infection. We show that an ultralow concentration of Mn0.3Fe2.7O4@SiO2 nanoparticles subjected to a moderate AC magnetic field, without bulk heating effect, can deposit heat locally and effectively inhibit H. pylori growth and virulence in vitro. When coupled with antibiotic amoxicillin, the dual-functional amoxicillin loaded Mn0.3Fe2.7O4@SiO2 further decreases the bacteria survival rate by a factor of 7 and 5, respectively, compared to amoxicillin treatment and nanoparticle heating alone. The synergistic effect can be partially attributed to the heating induced damage to the cell membrane and protective biofilm, which may increase the permeability of antibiotics to bacteria. Our method provides a viable approach to treat H. pylori infection, with the potential of reducing side effects and enhancing the efficacy for combating drug resistant strains.

physics.app-ph↗

arXiv2019

Classification of stacked central configurations in R^3

We classify the extensions of n-body central configurations to (n + 1)-body central configurations in R3, in both the collinear case and the non-collinear case. We completely solve the two open questions posed by Hampton (Nonlinearity 18: 2299- 2304, 2005). This classification is related with study on co-circular and co-spherical central configurations. We also obtain a general property of co-circular central configurations.

math.DS↗

arXiv2018

IMS at the PolEval 2018: A Bulky Ensemble Depedency Parser meets 12 Simple Rules for Predicting Enhanced Dependencies in Polish

This paper presents the IMS contribution to the PolEval 2018 Shared Task. We submitted systems for both of the Subtasks of Task 1. In Subtask (A), which was about dependency parsing, we used our ensemble system from the CoNLL 2017 UD Shared Task. The system first preprocesses the sentences with a CRF POS/morphological tagger and predicts supertags with a neural tagger. Then, it employs multiple instances of three different parsers and merges their outputs by applying blending. The system achieved the second place out of four participating teams. In this paper we show which components of the system were the most responsible for its final performance. The goal of Subtask (B) was to predict enhanced graphs. Our approach consisted of two steps: parsing the sentences with our ensemble system from Subtask (A), and applying 12 simple rules to obtain the final dependency graphs. The rules introduce additional enhanced arcs only for tokens with "conj" heads (conjuncts). They do not predict semantic relations at all. The system ranked first out of three participating teams. In this paper we show examples of rules we designed and analyze the relation between the quality of automatically parsed trees and the accuracy of the enhanced graphs.

cs.CL↗

arXiv2018

Risk Sensitive Portfolio Optimization with Default Contagion and Regime-Switching

We study an open problem of risk-sensitive portfolio allocation in a regime-switching credit market with default contagion. The state space of the Markovian regime-switching process is assumed to be a countably infinite set. To characterize the value function, we investigate the corresponding recursive infinite-dimensional nonlinear dynamical programming equations (DPEs) based on default states. We propose to work in the following procedure: Applying the theory of monotone dynamical system, we first establish the existence and uniqueness of classical solutions to the recursive DPEs by a truncation argument in the finite state space. The associated optimal feedback strategy is characterized by developing a rigorous verification theorem. Building upon results in the first stage, we construct a sequence of approximating risk sensitive control problems with finite states and prove that the resulting smooth value functions will converge to the classical solution of the original system of DPEs. The construction and approximation of the optimal feedback strategy for the original problem are also thoroughly discussed.

q-fin.PM↗

arXiv2018

Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension

We propose a machine reading comprehension model based on the compare-aggregate framework with two-staged attention that achieves state-of-the-art results on the MovieQA question answering dataset. To investigate the limitations of our model as well as the behavioral difference between convolutional and recurrent neural networks, we generate adversarial examples to confuse the model and compare to human performance. Furthermore, we assess the generalizability of our model by analyzing its differences to human inference,

cs.CL↗

arXiv2018

Optimal Investment with Random Endowments and Transaction Costs: Duality Theory and Shadow Prices

This paper studies the utility maximization on the terminal wealth with random endowments and proportional transaction costs. To deal with unbounded random payoffs from some illiquid claims, we propose to work with the acceptable portfolios defined via the consistent price system (CPS) such that the liquidation value processes stay above some stochastic thresholds. In the market consisting of one riskless bond and one risky asset, we obtain a type of super-hedging result. Based on this characterization of the primal space, the existence and uniqueness of the optimal solution for the utility maximization problem are established using the duality approach. As an important application of the duality theorem, we provide some sufficient conditions for the existence of a shadow price process with random endowments in a generalized form as well as in the usual sense using acceptable portfolios.

q-fin.MF↗

arXiv2018

Deep Supervision with Intermediate Concepts

Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human and machine vision suggests that there are often intermediate representations that are intrinsic to an inference task, and which provide essential structure to improve generalization. In this work, we explore an approach for injecting prior domain structure into neural network training by supervising hidden layers of a CNN with intermediate concepts that normally are not observed in practice. We formulate a probabilistic framework which formalizes these notions and predicts improved generalization via this deep supervision method. One advantage of this approach is that we are able to train only from synthetic CAD renderings of cluttered scenes, where concept values can be extracted, but apply the results to real images. Our implementation achieves the state-of-the-art performance of 2D/3D keypoint localization and image classification on real image benchmarks, including KITTI, PASCAL VOC, PASCAL3D+, IKEA, and CIFAR100. We provide additional evidence that our approach outperforms alternative forms of supervision, such as multi-task networks.

cs.CV↗

arXiv2018

On the Bail-Out Optimal Dividend Problem

This paper studies the optimal dividend problem with capital injection under the constraint that the cumulative dividend strategy is absolutely continuous. We consider an open problem of the general spectrally negative case and derive the optimal solution explicitly using the fluctuation identities of the refracted-reflected Lévy process. The optimal strategy as well as the value function are concisely written in terms of the scale function. Numerical results are also provided to confirm the analytical conclusions.

q-fin.MF↗

arXiv2018

Maximizing Specific Loss Power for Magnetic Hyperthermia by Hard-Soft Mixed Ferrites

We report maximized specific loss power and intrinsic loss power approaching theoretical limits for AC magnetic field heating of nanoparticles. This is achieved by engineering the effective magnetic anisotropy barrier of nanoparticles via alloying of hard and soft ferrites. 22 nm Co0.03Mn0.28Fe2.7O4/SiO2 NPs reached a specific loss power value of 3417 W/gmetal at a field of 33 kA/m and 380 kHz. Biocompatible Zn0.3Fe2.7O4/SiO2 nanoparticles achieved specific loss power of 500 W/gmetal and intrinsic loss power of 26.8 nHm2/kg at field parameters of 7 kA/m and 380 kHz, below the clinical safety limit. Magnetic bone cement achieved heating adequate for bone tumor hyperthermia, incorporating ultralow dosage of just 1 wt% of nanoparticles. In cellular hyperthermia experiments, these nanoparticles demonstrated high cell death rate at low field parameters. Zn0.3Fe2.7O4/SiO2 nanoparticles show cell viabilities above 97% at concentrations up to 0.5 mg/ml within 48 hrs, suggesting toxicity lower than that of magnetite.

cond-mat.mes-hall↗

arXiv2017

Towards Large-Pose Face Frontalization in the Wild

Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments. Learning pose-invariant features is one solution, but needs expensively labeled large-scale data and carefully designed feature learning algorithms. In this work, we focus on frontalizing faces in the wild under various head poses, including extreme profile views. We propose a novel deep 3D Morphable Model (3DMM) conditioned Face Frontalization Generative Adversarial Network (GAN), termed as FF-GAN, to generate neutral head pose face images. Our framework differs from both traditional GANs and 3DMM based modeling. Incorporating 3DMM into the GAN structure provides shape and appearance priors for fast convergence with less training data, while also supporting end-to-end training. The 3DMM-conditioned GAN employs not only the discriminator and generator loss but also a new masked symmetry loss to retain visual quality under occlusions, besides an identity loss to recover high frequency information. Experiments on face recognition, landmark localization and 3D reconstruction consistently show the advantage of our frontalization method on faces in the wild datasets.

cs.CV↗

arXiv2017

Reconstruction-Based Disentanglement for Pose-invariant Face Recognition

Deep neural networks (DNNs) trained on large-scale datasets have recently achieved impressive improvements in face recognition. But a persistent challenge remains to develop methods capable of handling large pose variations that are relatively underrepresented in training data. This paper presents a method for learning a feature representation that is invariant to pose, without requiring extensive pose coverage in training data. We first propose to generate non-frontal views from a single frontal face, in order to increase the diversity of training data while preserving accurate facial details that are critical for identity discrimination. Our next contribution is to seek a rich embedding that encodes identity features, as well as non-identity ones such as pose and landmark locations. Finally, we propose a new feature reconstruction metric learning to explicitly disentangle identity and pose, by demanding alignment between the feature reconstructions through various combinations of identity and pose features, which is obtained from two images of the same subject. Experiments on both controlled and in-the-wild face datasets, such as MultiPIE, 300WLP and the profile view database CFP, show that our method consistently outperforms the state-of-the-art, especially on images with large head pose variations. Detail results and resource are referred to https://sites.google.com/site/xipengcshomepage/iccv2017

cs.CV↗

arXiv2017

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual quality between the domains and the difficulty of curating diverse large-scale video datasets. This paper addresses both of those challenges, through an image to video feature-level domain adaptation approach, to learn discriminative video frame representations. The framework utilizes large-scale unlabeled video data to reduce the gap between different domains while transferring discriminative knowledge from large-scale labeled still images. Given a face recognition network that is pretrained in the image domain, the adaptation is achieved by (i) distilling knowledge from the network to a video adaptation network through feature matching, (ii) performing feature restoration through synthetic data augmentation and (iii) learning a domain-invariant feature through a domain adversarial discriminator. We further improve performance through a discriminator-guided feature fusion that boosts high-quality frames while eliminating those degraded by video domain-specific factors. Experiments on the YouTube Faces and IJB-A datasets demonstrate that each module contributes to our feature-level domain adaptation framework and substantially improves video face recognition performance to achieve state-of-the-art accuracy. We demonstrate qualitatively that the network learns to suppress diverse artifacts in videos such as pose, illumination or occlusion without being explicitly trained for them.

cs.CV↗

arXiv2017

A General-Purpose Tagger with Convolutional Neural Networks

We present a general-purpose tagger based on convolutional neural networks (CNN), used for both composing word vectors and encoding context information. The CNN tagger is robust across different tagging tasks: without task-specific tuning of hyper-parameters, it achieves state-of-the-art results in part-of-speech tagging, morphological tagging and supertagging. The CNN tagger is also robust against the out-of-vocabulary problem, it performs well on artificially unnormalized texts.

cs.CL↗

arXiv2017

Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages

We present a transition-based dependency parser that uses a convolutional neural network to compose word representations from characters. The character composition model shows great improvement over the word-lookup model, especially for parsing agglutinative languages. These improvements are even better than using pre-trained word embeddings from extra data. On the SPMRL data sets, our system outperforms the previous best greedy parser (Ballesteros et al., 2015) by a margin of 3% on average.

cs.CL↗

arXiv2017

Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing

Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image and 3D space while inferring their visibility states, given a single RGB image. Our key insight is to exploit domain knowledge to regularize the network by deeply supervising its hidden layers, in order to sequentially infer intermediate concepts associated with the final task. To acquire training data in desired quantities with ground truth 3D shape and relevant concepts, we render 3D object CAD models to generate large-scale synthetic data and simulate challenging occlusion configurations between objects. We train the network only on synthetic data and demonstrate state-of-the-art performances on real image benchmarks including an extended version of KITTI, PASCAL VOC, PASCAL3D+ and IKEA for 2D and 3D keypoint localization and instance segmentation. The empirical results substantiate the utility of our deep supervision scheme by demonstrating effective transfer of knowledge from synthetic data to real images, resulting in less overfitting compared to standard end-to-end training.

cs.CV↗

arXiv2016

Optimal Consumption under Habit Formation In Markets with Transaction Costs and Random Endowments

This paper studies the optimal consumption under the addictive habit formation preference in markets with transaction costs and unbounded random endowments. To model the proportional transaction costs, we adopt the Kabanov's multi-asset framework with a cash account. At the terminal time T, the investor can receive unbounded random endowments for which we propose a new definition of acceptable portfolios based on the strictly consistent price system (SCPS). We prove a type of super-hedging theorem using the acceptable portfolios which enables us to obtain the consumption budget constraint condition under market frictions. Applying the path dependence reduction and the embedding approach, we obtain the existence and uniqueness of the optimal consumption using some auxiliary processes and the duality analysis. As an application of the duality theory, the market isomorphism with special discounting factors is also discussed in the sense that the original optimal consumption with habit formation is equivalent to the standard optimal consumption problem without the habits impact, however, in a modified isomorphic market model.

q-fin.PM↗

arXiv2016

Deep Deformation Network for Object Landmark Localization

We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects. The hallmarks of DDN are its incorporation of geometric constraints within a convolutional neural network (CNN) framework, ease and efficiency of training, as well as generality of application. A novel shape basis network (SBN) forms the first stage of the cascade, whereby landmarks are initialized by combining the benefits of CNN features and a learned shape basis to reduce the complexity of the highly nonlinear pose manifold. In the second stage, a point transformer network (PTN) estimates local deformation parameterized as thin-plate spline transformation for a finer refinement. Our framework does not incorporate either handcrafted features or part connectivity, which enables an end-to-end shape prediction pipeline during both training and testing. In contrast to prior cascaded networks for landmark localization that learn a mapping from feature space to landmark locations, we demonstrate that the regularization induced through geometric priors in the DDN makes it easier to train, yet produces superior results. The efficacy and generality of the architecture is demonstrated through state-of-the-art performances on several benchmarks for multiple tasks such as facial landmark localization, human body pose estimation and bird part localization.

cs.CV↗