arXiv subjects

Qian Wang

Publications and source records attributed to Qian Wang.

At least 523 records · Page 29Linked to original sources

arXiv2019

Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition

Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain. One limitation of the problem setting is that testing data, despite having no labels, from the target domain is needed during training, which prevents the trained model being directly applied to classify unseen test instances. We formulate a new cross-domain classification problem arising from real-world scenarios where labelled data is available for a subset of classes (known classes) in the target domain, and we expect to recognize new samples belonging to any class (known and unseen classes) once the model is learned. This is a generalized zero-shot learning problem where the side information comes from the source domain in the form of labelled samples instead of class-level semantic representations commonly used in traditional zero-shot learning. We present a unified domain adaptation framework for both unsupervised and zero-shot learning conditions. Our approach learns a joint subspace from source and target domains so that the projections of both data in the subspace can be domain invariant and easily separable. We use the supervised locality preserving projection (SLPP) as the enabling technique and conduct experiments under both unsupervised and zero-shot learning conditions, achieving state-of-the-art results on three domain adaptation benchmark datasets: Office-Caltech, Office31 and Office-Home.

cs.CV↗

arXiv2019

Excited-state quantum phase transition and the quantum speed limit

We investigate the influence of an excited-state quantum phase transition (ESQPT) on the quantum speed limit (QSL) time of an open quantum system. The system consists of a central qubit coupled to a spin environment modeled by a Lipkin-Meshkov-Glick (LMG) Hamiltonian. We show that when the coupling between qubit and environment is such that the latter is located at the ESQPT critical energy the qubit evolution shows a remarkable slowdown, marked by an abrupt peak in the QSL time. Interestingly, this slowdown at the ESQPT critical point is induced by the singular behavior of the qubit decoherence rate, being independent of the Markovian nature of the environment.

quant-ph↗

arXiv2019

Tri-meson bound state $BBB^{\ast}$ via delocalized $π$~Bond

During the last decades, numerous exotic states which cannot be explained by the conventional quark model have been observed in experiment. Some of them can be understood as two-body hadronic molecules, such as the famous $X(3872)$, analogous to deuteron in nuclear physics. Along the same line, the existence of the triton leaves an open question whether there is a bound state formed by three hadrons. Since, for a given potential, a system with large reduced masses is more easier to form a bound state, we study the $BBB^{\ast}$ system with the one-pion exchange potential as an exploratory step by solving the three-body Schrödinger Equation. We predict that a tri-meson molecular state for the $BBB^{\ast}$ system is probably existent as long as the molecular states of its two-body subsystem $BB^*$ exist.

hep-ph↗

arXiv2019

Synthesis and Inpainting-Based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors

Thermal ablation is a minimally invasive procedure for treat-ing small or unresectable tumors. Although CT is widely used for guiding ablation procedures, the contrast of tumors against surrounding normal tissues in CT images is often poor, aggravating the difficulty in accurate thermal ablation. In this paper, we propose a fast MR-CT image registration method to overlay a pre-procedural MR (pMR) image onto an intra-procedural CT (iCT) image for guiding the thermal ablation of liver tumors. By first using a Cycle-GAN model with mutual information constraint to generate synthesized CT (sCT) image from the cor-responding pMR, pre-procedural MR-CT image registration is carried out through traditional mono-modality CT-CT image registration. At the intra-procedural stage, a partial-convolution-based network is first used to inpaint the probe and its artifacts in the iCT image. Then, an unsupervised registration network is used to efficiently align the pre-procedural CT (pCT) with the inpainted iCT (inpCT) image. The final transformation from pMR to iCT is obtained by combining the two estimated transformations,i.e., (1) from the pMR image space to the pCT image space (through sCT) and (2) from the pCT image space to the iCT image space (through inpCT). Experimental results confirm that the proposed method achieves high registration accuracy with a very fast computational speed.

eess.IV↗

arXiv2019

Dual Adversarial Learning with Attention Mechanism for Fine-grained Medical Image Synthesis

Medical imaging plays a critical role in various clinical applications. However, due to multiple considerations such as cost and risk, the acquisition of certain image modalities could be limited. To address this issue, many cross-modality medical image synthesis methods have been proposed. However, the current methods cannot well model the hard-to-synthesis regions (e.g., tumor or lesion regions). To address this issue, we propose a simple but effective strategy, that is, we propose a dual-discriminator (dual-D) adversarial learning system, in which, a global-D is used to make an overall evaluation for the synthetic image, and a local-D is proposed to densely evaluate the local regions of the synthetic image. More importantly, we build an adversarial attention mechanism which targets at better modeling hard-to-synthesize regions (e.g., tumor or lesion regions) based on the local-D. Experimental results show the robustness and accuracy of our method in synthesizing fine-grained target images from the corresponding source images. In particular, we evaluate our method on two datasets, i.e., to address the tasks of generating T2 MRI from T1 MRI for the brain tumor images and generating MRI from CT. Our method outperforms the state-of-the-art methods under comparison in all datasets and tasks. And the proposed difficult-region-aware attention mechanism is also proved to be able to help generate more realistic images, especially for the hard-to-synthesize regions.

eess.IV↗

arXiv2019

Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization

Medical image segmentation is challenging especially in dealing with small dataset of 3D MR images. Encoding the variation of brain anatomical struc-tures from individual subjects cannot be easily achieved, which is further chal-lenged by only a limited number of well labeled subjects for training. In this study, we aim to address the issue of brain MR image segmentation in small da-taset. First, concerning the limited number of training images, we adopt adver-sarial defense to augment the training data and therefore increase the robustness of the network. Second, inspired by the prior knowledge of neural anatomies, we reorganize the segmentation tasks of different regions into several groups in a hierarchical way. Third, the task reorganization extends to the semantic level, as we incorporate an additional object-level classification task to contribute high-order visual features toward the pixel-level segmentation task. In experiments we validate our method by segmenting gray matter, white matter, and several major regions on a challenge dataset. The proposed method with only seven subjects for training can achieve 84.46% of Dice score in the onsite test set.

eess.IV↗

arXiv2019

Scalable Online Survey Framework: from Sampling to Analysis

With the advancement in technology, raw event data generated by the digital world have grown tremendously. However, such data tend to be insufficient and noisy when it comes to measuring user intention or satisfaction. One effective way to measure user experience directly is through surveys. In particular, with the popularity of online surveys, extensive work has been put in to study this field. Surveys at LinkedIn play a major role in influencing product and marketing decisions and supporting our sales efforts. We run an increasing number of surveys that help us understand shifts in awareness and perceptions with regards to our own products and also to peer companies. As the need to survey grows, both sampling and analysis of surveys have become more challenging. Instead of simply multiplying the number of surveys each user takes, we need a scalable approach to collect enough and representative samples for each survey analysis while maintaining good user experience. In this paper, we start with discussions on how we handle multiple email surveys under such constraints. We then shift our discussions to challenges of in-product surveys and how we address them at LinkedIn through a survey study conducted across two mobile apps. Finally, we share how in-product surveys can be utilized as monitoring tools and connect surveys with A/B testing.

stat.AP↗

arXiv2019

Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation

Semantic segmentation is essentially important to biomedical image analysis. Many recent works mainly focus on integrating the Fully Convolutional Network (FCN) architecture with sophisticated convolution implementation and deep supervision. In this paper, we propose to decompose the single segmentation task into three subsequent sub-tasks, including (1) pixel-wise image segmentation, (2) prediction of the class labels of the objects within the image, and (3) classification of the scene the image belonging to. While these three sub-tasks are trained to optimize their individual loss functions of different perceptual levels, we propose to let them interact by the task-task context ensemble. Moreover, we propose a novel sync-regularization to penalize the deviation between the outputs of the pixel-wise segmentation and the class prediction tasks. These effective regularizations help FCN utilize context information comprehensively and attain accurate semantic segmentation, even though the number of the images for training may be limited in many biomedical applications. We have successfully applied our framework to three diverse 2D/3D medical image datasets, including Robotic Scene Segmentation Challenge 18 (ROBOT18), Brain Tumor Segmentation Challenge 18 (BRATS18), and Retinal Fundus Glaucoma Challenge (REFUGE18). We have achieved top-tier performance in all three challenges.

cs.CV↗

arXiv2019

Bias Scheme Reducing Transient Currents and Speeding up Read Operations for 3-D Cross Point PCM

3-D cross point phase change memory (PCM) is a promising emerging memory. However, dynamic performances of 3-D cross point PCM are limited and the role of bias scheme is unknown. Previous studies on bias schemes for planar memories use static analyses to assess static array performances. Here, a high peak transient read current is found to result in a long read access time. Three factors which contribute to the high peak read current are analyzed. The proposed 2V/3 bias scheme and a single-reference parasitic-matching sensing circuit are utilized in a 64Mbit 3-D cross point PCM. The sensing time is reduced by 22.5%. Designing bias schemes through dynamic analyses paves the way for the development of high-performance 3-D PCM technology to boost the working efficiency of computing systems. The following contents are the listed errors as mentioned in the comments for reasons of withdrawal: missing labels of Fig.1, lack of the explanation of the peak current on the sensing speed, lack of the reason of the chosen of 2V/3 scheme, lack of influence of the parasitic capacitors, unclear explanation of the factor that contributes to a high peak read current, lack of comparisons, lack of the explanation of the sneak current, lack of the explanations of the SRPM sensing circuit, lack of the define valuables like NM_{A1}, unclear explanation of comparisons of the power consumption, wrong writing of the two conventional circuits, writing of 3D-IC, wrong writing of number of memory layers, etc. These errors may confuse a good understanding of our work. Therefore, we decide to withdraw this manuscript from arXiv. We will significantly rewrite it and publish the correct and complete paper in the future.

cs.ET↗

arXiv2019

DLIMD: Dictionary Learning based Image-domain Material Decomposition for spectral CT

The potential huge advantage of spectral computed tomography (CT) is its capability to provide accuracy material identification and quantitative tissue information. This can benefit clinical applications, such as brain angiography, early tumor recognition, etc. To achieve more accurate material components with higher material image quality, we develop a dictionary learning based image-domain material decomposition (DLIMD) for spectral CT in this paper. First, we reconstruct spectral CT image from projections and calculate material coefficients matrix by selecting uniform regions of basis materials from image reconstruction results. Second, we employ the direct inversion (DI) method to obtain initial material decomposition results, and a set of image patches are extracted from the mode-1 unfolding of normalized material image tensor to train a united dictionary by the K-SVD technique. Third, the trained dictionary is employed to explore the similarities from decomposed material images by constructing the DLIMD model. Fourth, more constraints (i.e., volume conservation and the bounds of each pixel within material maps) are further integrated into the model to improve the accuracy of material decomposition. Finally, both physical phantom and preclinical experiments are employed to evaluate the performance of the proposed DLIMD in material decomposition accuracy, material image edge preservation and feature recovery.

eess.IV↗

arXiv2019

A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks

Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks. Although performance gains have been reported, the backbone deep models of the proposed approaches and the evaluation metrics employed in different works vary, making it difficult to compare each fairly. Moreover, due to the lack of properly investigated baselines, the advantage introduced by the proposed techniques are often ambiguous. To address these issues, we make a thorough investigation of the mainstream deep convolutional neural network architectures for multi-label image classification and present a strong baseline. With the use of proper data augmentation techniques and model ensembles, the basic deep architectures can achieve better performance than many existing more complex ones on three benchmark datasets, providing great insight for the future studies on multi-label image classification.

cs.CV↗

arXiv2019

Global solution for Massive Maxwell-Klein-Gordon equations with large Maxwell field

We derive the global dynamic properties of the mMKG system (Maxwell coupled with a massive Klein-Gordon scalar field) with a general, unrestrictive class of data, in particular, for Maxwell field of arbitrary size, and by a gauge independent method. Due to the critical slow decay expected for the Maxwell field, the scalar field exhibits a loss of decay at the causal infinities within an outgoing null cone. To overcome the difficulty caused by such loss in the energy propagation, we uncover a hidden cancellation contributed by the Maxwell equation, which enables us to obtain the sharp control of the Maxwell field under a rather low regularity assumption on data. Our method can be applied to other physical field equations, such as the Einstein equations for which a similar cancellation structure can be observed.

math.AP↗

arXiv2019

Automated Segmentation of the Optic Disk and Cup using Dual-Stage Fully Convolutional Networks

Automated segmentation of the optic cup and disk on retinal fundus images is fundamental for the automated detection / analysis of glaucoma. Traditional segmentation approaches depend heavily upon hand-crafted features and a priori knowledge of the user. As such, these methods are difficult to be adapt to the clinical environment. Recently, deep learning methods based on fully convolutional networks (FCNs) have been successful in resolving segmentation problems. However, the reliance on large annotated training data is problematic when dealing with medical images. If a sufficient amount of annotated training data to cover all possible variations is not available, FCNs do not provide accurate segmentation. In addition, FCNs have a large receptive field in the convolutional layers, and hence produce coarse outputs of boundaries. Hence, we propose a new fully automated method that we refer to as a dual-stage fully convolutional networks (DSFCN). Our approach leverages deep residual architectures and FCNs and learns and infers the location of the optic cup and disk in a step-wise manner with fine-grained details. During training, our approach learns from the training data and the estimated results derived from the previous iteration. The ability to learn from the previous iteration optimizes the learning of the optic cup and the disk boundaries. During testing (prediction), DSFCN uses test (input) images and the estimated probability map derived from previous iterations to gradually improve the segmentation accuracy. Our method achieved an average Dice co-efficient of 0.8488 and 0.9441 for optic cup and disk segmentation and an area under curve (AUC) of 0.9513 for glaucoma detection.

cs.CV↗

arXiv2019

Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding

Human action recognition refers to automatic recognizing human actions from a video clip. In reality, there often exist multiple human actions in a video stream. Such a video stream is often weakly-annotated with a set of relevant human action labels at a global level rather than assigning each label to a specific video episode corresponding to a single action, which leads to a multi-label learning problem. Furthermore, there are many meaningful human actions in reality but it would be extremely difficult to collect/annotate video clips regarding all of various human actions, which leads to a zero-shot learning scenario. To the best of our knowledge, there is no work that has addressed all the above issues together in human action recognition. In this paper, we formulate a real-world human action recognition task as a multi-label zero-shot learning problem and propose a framework to tackle this problem in a holistic way. Our framework holistically tackles the issue of unknown temporal boundaries between different actions for multi-label learning and exploits the side information regarding the semantic relationship between different human actions for knowledge transfer. Consequently, our framework leads to a joint latent ranking embedding for multi-label zero-shot human action recognition. A novel neural architecture of two component models and an alternate learning algorithm are proposed to carry out the joint latent ranking embedding learning. Thus, multi-label zero-shot recognition is done by measuring relatedness scores of action labels to a test video clip in the joint latent visual and semantic embedding spaces. We evaluate our framework with different settings, including a novel data split scheme designed especially for evaluating multi-label zero-shot learning, on two datasets: Breakfast and Charades. The experimental results demonstrate the effectiveness of our framework.

cs.CV↗

arXiv2019

Deep Morphological Simplification Network (MS-Net) for Guided Registration of Brain Magnetic Resonance Images

Objective: Deformable brain MR image registration is challenging due to large inter-subject anatomical variation. For example, the highly complex cortical folding pattern makes it hard to accurately align corresponding cortical structures of individual images. In this paper, we propose a novel deep learning way to simplify the difficult registration problem of brain MR images. Methods: We train a morphological simplification network (MS-Net), which can generate a "simple" image with less anatomical details based on the "complex" input. With MS-Net, the complexity of the fixed image or the moving image under registration can be reduced gradually, thus building an individual (simplification) trajectory represented by MS-Net outputs. Since the generated images at the ends of the two trajectories (of the fixed and moving images) are so simple and very similar in appearance, they are easy to register. Thus, the two trajectories can act as a bridge to link the fixed and the moving images, and guide their registration. Results: Our experiments show that the proposed method can achieve highly accurate registration performance on different datasets (i.e., NIREP, LPBA, IBSR, CUMC, and MGH). Moreover, the method can be also easily transferred across diverse image datasets and obtain superior accuracy on surface alignment. Conclusion and Significance: We propose MS-Net as a powerful and flexible tool to simplify brain MR images and their registration. To our knowledge, this is the first work to simplify brain MR image registration by deep learning, instead of estimating deformation field directly.

cs.CV↗

arXiv2018

Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning

Federated learning, i.e., a mobile edge computing framework for deep learning, is a recent advance in privacy-preserving machine learning, where the model is trained in a decentralized manner by the clients, i.e., data curators, preventing the server from directly accessing those private data from the clients. This learning mechanism significantly challenges the attack from the server side. Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i.e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client. This paper gives the first attempt to explore user-level privacy leakage against the federated learning by the attack from a malicious server. We propose a framework incorporating GAN with a multi-task discriminator, which simultaneously discriminates category, reality, and client identity of input samples. The novel discrimination on client identity enables the generator to recover user specified private data. Unlike existing works that tend to interfere the training process of the federated learning, the proposed method works "invisibly" on the server side. The experimental results demonstrate the effectiveness of the proposed attacking approach and the superior to the state-of-the-art.

cs.LG↗

arXiv2018

Interactions between vector mesons and dynamically generated resonances

The $ρρ$ interaction and the corresponding dynamically generated bound states are revisited. We demonstrate that an improved unitarization method is necessary to study the pole structures of amplitudes outside the near-threshold region. In this work, we extend the study of the covariant $ρρ$ scattering in a unitarized chiral theory to the $S$-wave interactions for the whole vector-meson nonet. We demonstrate that there are unphysical left-hand cuts in the on-shell factorization approach of the Bethe-Salpeter equation. This is in conflict with the correct analytic behavior and makes the so-obtained poles, corresponding to possible bound states or resonances, unreliable. To avoid this difficulty, we employ the first iterated solution of the $N/D$ method and investigate the possible dynamically generated resonances from vector-vector interactions. A comparison with the results from the nonrelativistic calculation is provided as well.

hep-ph↗

arXiv2018

Watermark Retrieval from 3D Printed Objects via Convolutional Neural Networks

We present a method for reading digital data embedded in planar 3D printed surfaces. The data are organised in binary arrays and embedded as surface textures in a way inspired by QR codes. At the core of the retrieval method lies a Convolutional Neural Network, outputting a confidence map of the location of the surface textures encoding value 1 bits. Subsequently, the bit array is retrieved through a series of simple image processing and statistical operations applied on the confidence map. Extensive experimentation with images captured from various camera views, under various illumination conditions and from objects printed with various material colours, shows that the proposed method generalizes well and achieves the level of accuracy required in practical applications.

cs.CV↗