arXiv subjects

Hang Zhang

Publications and source records attributed to Hang Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2021

Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network

An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed. We use an affine motion model with randomly created motion profiles to simulate motion-corrupted QSM images. The simulated QSM image is paired with its motion-free reference to train a neural network using supervised learning. The trained network is tested on unseen simulated motion-corrupted QSM images, in healthy volunteers and in Parkinson's disease patients. The results show that motion artifacts, such as ringing and ghosting, were successfully suppressed.

physics.med-ph↗

arXiv2021

Marangoni Convection-Driven Laser Fountains and Waves on Free Surfaces of Liquids

It is well accepted that an outward Marangoni convection from a low surface tension region will make the surface depressed. Here, we report that this established perception is only valid for thin liquid films. Using surface laser heating, we show that in deep liquids a laser beam actually pulls up the fluid above the free surface generating fountains with different shapes. Whereas with decreasing liquid depth a transition from fountain to indentation with fountain in-indentation is observed. Further, high-speed imaging reveals a transient surface process before steady elevation is formed, and this dynamic deformation is subsequently utilized to resonantly excite giant surface waves by a modulated laser beam. Computational fluid dynamics models reveal the underlying flow patterns and quantify the depth-dependent and time-resolved surface deformations. Our discoveries and techniques have upended the century-old perception and opened up a new regime of interdisciplinary research and applications of Marangoni-induced interface phenomena and optocapillary fluidic surfaces-the control of fluids with light.

physics.flu-dyn↗

arXiv2021

Ultra-Low Noise L-Band Cryogenic Astronomical Receiver for FAST Telescope

This paper presents an ultra-low noise L-band radio astronomical cryogenic receiver for FAST telescope. The development of key low noise microwave parts of Coupling-LNA and conical quad-ridge OMT and reasonable system integration achieve outstanding performance of receiver.It covers the frequency range of 1.2 GHz to 1.8 GHz. Novel cryogenic Coupling-LNAs with low noise, large return loss, high dynamic range and the function of coupling calibration signals are developed for the proposed receiver.Amplification and coupling function circuits are integrated as a single Coupling-LNA with full noise temperature of 4 K at the physical temperature of 15 K. And its return loss is more than 18 dB, and output 1 dB compression power is +5 dBm. A cryogenic dewar is fabricated to provide 55 K and 15 K cryogenic environment for OMT and Coupling-LNAs, respectively. The receiver's system noise temperature is below 9 K referred to feed aperture plane. Benefiting from optimal design and precise mechanical treatment, good scattering performance of OMT and equalized radiation patterns of horn are achieved with an antenna efficiency above 75%.

astro-ph.IM↗

arXiv2021

Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping

A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation. In PDI, a deep convolutional neural network (CNN) is used to represent the multivariate Gaussian distribution as the approximate posterior distribution of susceptibility given the input measured field. Such CNN is first trained on healthy subjects via posterior density estimation, where the training dataset contains samples from the true posterior distribution. Domain adaptations are then deployed on patient datasets with new pathologies not included in pre-training, where PDI updates the pre-trained CNN's weights in an unsupervised fashion by minimizing the Kullback-Leibler divergence between the approximate posterior distribution represented by CNN and the true posterior distribution from the likelihood distribution of a known physical model and pre-defined prior distribution. Based on our experiments, PDI provides additional uncertainty estimation compared to the conventional MAP approach, while addressing the potential issue of the pre-trained CNN when test data deviates from training.

eess.IV↗

arXiv2021

Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction

Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging. In this work, we focus on optimizing the acquisition and reconstruction process of multi-echo gradient echo pulse sequence for quantitative susceptibility mapping as one important quantitative imaging method in MRI. A multi-echo sampling pattern optimization block extended from LOUPE-ST is proposed to optimize the k-space sampling patterns along echoes. Besides, a recurrent temporal feature fusion block is proposed and inserted into a backbone deep ADMM network to capture the signal evolution along echo time during reconstruction. Experiments show that both blocks help improve multi-echo image reconstruction performance.

eess.SP↗

arXiv2021

NeRD: Neural Representation of Distribution for Medical Image Segmentation

We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution. Using NeRD, we propose an end-to-end deep learning model for medical image segmentation that can compensate the negative impact of feature distribution shifting issue caused by commonly used network operations such as padding and pooling. An implicit function is used to represent the parameter space of the feature distribution by querying the image coordinate. With NeRD, the impact of issues such as over-segmenting and missing have been reduced, and experimental results on the challenging white matter lesion segmentation and left atrial segmentation verify the effectiveness of the proposed method. The code is available via https://github.com/tinymilky/NeRD.

eess.IV↗

arXiv2020

ResNeSt: Split-Attention Networks

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

cs.CV↗

arXiv2020

Ensembling Low Precision Models for Binary Biomedical Image Segmentation

Segmentation of anatomical regions of interest such as vessels or small lesions in medical images is still a difficult problem that is often tackled with manual input by an expert. One of the major challenges for this task is that the appearance of foreground (positive) regions can be similar to background (negative) regions. As a result, many automatic segmentation algorithms tend to exhibit asymmetric errors, typically producing more false positives than false negatives. In this paper, we aim to leverage this asymmetry and train a diverse ensemble of models with very high recall, while sacrificing their precision. Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent. Thus, in aggregate the false positive errors will cancel out, yielding high performance for the ensemble. Our strategy is general and can be applied with any segmentation model. In three different applications (carotid artery segmentation in a neck CT angiography, myocardium segmentation in a cardiovascular MRI and multiple sclerosis lesion segmentation in a brain MRI), we show how the proposed approach can significantly boost the performance of a baseline segmentation method.

eess.IV↗

arXiv2020

Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

Multiple sclerosis (MS) lesions occupy a small fraction of the brain volume, and are heterogeneous with regards to shape, size and locations, which poses a great challenge for training deep learning based segmentation models. We proposed a new geometric loss formula to address the data imbalance and exploit the geometric property of MS lesions. We showed that traditional region-based and boundary-aware loss functions can be associated with the formula. We further develop and instantiate two loss functions containing first- and second-order geometric information of lesion regions to enforce regularization on optimizing deep segmentation models. Experimental results on two MS lesion datasets with different scales, acquisition protocols and resolutions demonstrated the superiority of our proposed methods compared to other state-of-the-art methods.

cs.CV↗

arXiv2020

Differential Viewpoints for Ground Terrain Material Recognition

Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined single-view images captured in the scene. We take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture. A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition. We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, to support ground terrain recognition for applications such as autonomous driving and robot navigation. The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions. We develop a novel approach for material recognition called texture-encoded angular network (TEAN) that combines deep encoding pooling of RGB information and differential angular images for angular-gradient features to fully leverage this large dataset. With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance. Our results show that TEAN achieves recognition performance that surpasses single view performance and standard (non-differential/large-angle sampling) multiview performance.

cs.CV↗

arXiv2020

Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation

Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed to capture global contextual information for performance enhancement. However, the large size of 3D volume images poses a great computational challenge to traditional attention methods. In this paper, we propose a folded attention (FA) approach to improve the computational efficiency of traditional attention methods on 3D medical images. The main idea is that we apply tensor folding and unfolding operations with four permutations to build four small sub-affinity matrices to approximate the original affinity matrix. Through four consecutive sub-attention modules of FA, each element in the feature tensor can aggregate spatial-channel information from all other elements. Compared to traditional attention methods, with moderate improvement of accuracy, FA can substantially reduce the computational complexity and GPU memory consumption. We demonstrate the superiority of our method on two challenging tasks for 3D MIR and MIS, which are quantitative susceptibility mapping and multiple sclerosis lesion segmentation.

eess.IV↗

arXiv2020

Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI

The previously established LOUPE (Learning-based Optimization of the Under-sampling Pattern) framework for optimizing the k-space sampling pattern in MRI was extended in three folds: firstly, fully sampled multi-coil k-space data from the scanner, rather than simulated k-space data from magnitude MR images in LOUPE, was retrospectively under-sampled to optimize the under-sampling pattern of in-vivo k-space data; secondly, binary stochastic k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator to estimate the gradient of the threshold operation in a neural network; thirdly, modified unrolled optimization network, rather than modified U-Net in LOUPE, was used as the reconstruction network in order to reconstruct multi-coil data properly and reduce the dependency on training data. Experimental results show that when dealing with the in-vivo k-space data, unrolled optimization network with binary under-sampling block and ST estimator had better reconstruction performance compared to the ones with either U-Net reconstruction network or approximate sampling pattern optimization network, and once trained, the learned optimal sampling pattern worked better than the hand-crafted variable density sampling pattern when deployed with other conventional reconstruction methods.

eess.IV↗

arXiv2020

Unveiling the Finite Temperature Physics of Hydrogen Chains via Auxiliary Field Quantum Monte Carlo

The ability to accurately predict the finite temperature properties of realistic quantum solids is central to uncovering new phases and engineering materials with novel properties. Nonetheless, there remain comparatively few many-body techniques capable of elucidating the finite temperature physics of solids from first principles. In this work, we take a significant step towards developing such a technique by generalizing our previous, fully ab initio finite temperature Auxiliary Field Quantum Monte Carlo (FT-AFQMC) method to model periodic solids and employing it to uncover the finite temperature physics of periodic hydrogen chains. Based upon our calculations of these chains' many-body thermodynamic quantities and correlation functions, we outline their metal-insulator and magnetic ordering as a function of both H-H bond distance and temperature. At low temperatures approaching the ground state, we observe both metal-insulator and ferromagnetic-antiferromagnetic crossovers at bond lengths between 0.5 and 0.75 Å. We then demonstrate how this low-temperature ordering evolves into a metallic phase with decreasing magnetic order at higher temperatures. By comparing the features we observe to those previously seen in one-dimensional, half-filled Hubbard models at finite temperature and in ground state hydrogen chains, interestingly, we identify signatures of the Pomeranchuk effect in hydrogen chains for the first time and show that spin and charge excitations that typically arise at distinct temperatures in the Hubbard model are indistinguishably coupled in these systems. Beyond qualitatively revealing the many-body phase behavior of hydrogen chains, our efforts shed light on the further theoretical developments that will be required to construct the phase diagrams of the more complex transition metal, lanthanide, and actinide solids of longstanding interest to physicists.

cond-mat.str-el↗

arXiv2020

Vertical CVD Growth of Highly Uniform Transition Metal Dichalcogenides

Two-dimensional (2D) transition metal dichalcogenides (TMDCs) have attracted great attention due to their physical and chemical properties that make them promising in electronics and optoelectronics. Because of the difficulties in controlling concentrations of solid precursors and spatially non-uniform growth dynamics, it is challenging to grow wafer-scale 2D TMDCs with good uniformity and reproducibility so far, which significantly hinders their practical use. Here we report a vertical chemical vapor deposition (VCVD) design to grow monolayer TMDCs with a uniform density and high quality over the whole wafer, and with excellent reproducibility. The use of such VCVD design can easily control the three key growth parameters of precursor concentration, gas flow and temperature, which cannot be done in currently widely-used horizontal CVD system. Statistical results show that VCVD-grown monolayer TMDCs including MoS2 and WS2 are of high uniformity and quality on substrates over centimeter size. We also fabricated multiple van der Waals heterostructures by the one-step transfer of VCVD-grown TMDC samples, owning to its good uniformity. This work opens a way to grow 2D materials with high uniformity and reproducibility on the wafer scale, which can be used for the scalable fabrication of 2D materials and their heterostructures.

physics.app-ph↗

arXiv2020

The Benefits of Diversity: Permutation Recovery in Unlabeled Sensing from Multiple Measurement Vectors

In "Unlabeled Sensing", one observes a set of linear measurements of an underlying signal with incomplete or missing information about their ordering, which can be modeled in terms of an unknown permutation. Previous work on the case of a single noisy measurement vector has exposed two main challenges: 1) a high requirement concerning the \emph{signal-to-noise ratio} ($\snr$), i.e., approximately of the order of $n^{5}$, and 2) a massive computational burden in light of NP-hardness in general. In this paper, we study the case of \emph{multiple} noisy measurement vectors (MMVs) resulting from a \emph{common} permutation and investigate to what extent the number of MMVs $m$ facilitates permutation recovery by "borrowing strength". The above two challenges have at least partially been resolved within our work. First, we show that a large stable rank of the signal significantly reduces the required snr which can drop from a polynomial in $n$ for $m = 1$ to a constant for $m = Ω(\log n)$, where $m$ denotes the number of MMVs and $n$ denotes the number of measurements per MV. This bound is shown to be sharp and is associated with a phase transition phenomenon. Second, we propose a computational scheme for recovering the unknown permutation in practice. For the "oracle case" with the known signal, the maximum likelihood (ML) estimator reduces to a linear assignment problem whose global optimum can be obtained efficiently. For the case in which both the signal and permutation are unknown, the problem is reformulated as a bi-convex optimization problem with an auxiliary variable, which can be solved by the Alternating Direction Method of Multipliers (ADMM). Numerical experiments based on the proposed computational scheme confirm the tightness of our theoretical analysis.

cs.IT↗

arXiv2020

Let's be Humorous: Knowledge Enhanced Humor Generation

The generation of humor is an under-explored and challenging problem. Previous works mainly utilize templates or replace phrases to generate humor. However, few works focus on freer forms and the background knowledge of humor. The linguistic theory of humor defines the structure of a humor sentence as set-up and punchline. In this paper, we explore how to generate a punchline given the set-up with the relevant knowledge. We propose a framework that can fuse the knowledge to end-to-end models. To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model. Furthermore, we create the first humor-knowledge dataset. The experimental results demonstrate that our method can make use of knowledge to generate fluent, funny punchlines, which outperforms several baselines.

cs.CL↗

arXiv2020

Character Matters: Video Story Understanding with Character-Aware Relations

Different from short videos and GIFs, video stories contain clear plots and lists of principal characters. Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots. Video Story Question Answering (VSQA) offers an effective way to benchmark higher-level comprehension abilities of a model. However, current VSQA methods merely extract generic visual features from a scene. With such an approach, they remain prone to learning just superficial correlations. In order to attain a genuine understanding of who did what to whom, we propose a novel model that continuously refines character-aware relations. This model specifically considers the characters in a video story, as well as the relations connecting different characters and objects. Based on these signals, our framework enables weakly-supervised face naming through multi-instance co-occurrence matching and supports high-level reasoning utilizing Transformer structures. We train and test our model on the six diverse TV shows in the TVQA dataset, which is by far the largest and only publicly available dataset for VSQA. We validate our proposed approach over TVQA dataset through extensive ablation study.

cs.CV↗

arXiv2020

Improving Semantic Segmentation via Self-Training

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets while requiring significantly less supervision. We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin. Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.

cs.CV↗