Searcharxiv⌕ Search

arXiv subjects

Hong Wang

Publications and source records attributed to Hong Wang.

At least 235 records · Page 13Linked to original sources

InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction

For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT imaging geometry constraint is not fully embedded into the network during training, leaving room for further performance improvement; 2) the model interpretability is lack of sufficient consideration. Against these issues, we propose a novel interpretable dual domain network, termed as InDuDoNet, which combines the advantages of model-driven and data-driven methodologies. Specifically, we build a joint spatial and Radon domain reconstruction model and utilize the proximal gradient technique to design an iterative algorithm for solving it. The optimization algorithm only consists of simple computational operators, which facilitate us to correspondingly unfold iterative steps into network modules and thus improve the interpretablility of the framework. Extensive experiments on synthesized and clinical data show the superiority of our InDuDoNet. Code is available in \url{https://github.com/hongwang01/InDuDoNet}.%method on the tasks of MAR and downstream multi-class pelvic fracture segmentation.

eess.IV↗

The collision frequency of electron-neutral-particle in the weakly ionized plasmas with Non-Maxwellian velocity distributions

The collision frequencies of electron-neutral-particle in the weakly ionized complex plasmas with the non-Maxwellian velocity distributions are studied. The average collision frequencies of electron-neutral-particle in the plasmas are derived accurately. We find that these collision frequencies are significantly dependent on the power-law spectral indices of non-Maxwellian distribution functions and so they are generally different from the collision frequencies in the plasmas with a Maxwellian velocity distribution, which will affect the transport properties of the charged particles in the plasmas. Numerically analyses are made to show the roles of the spectral indices in the average collision frequencies respectively.

physics.plasm-ph↗

AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learning

While deep neural networks have shown impressive performance in many tasks, they are fragile to carefully designed adversarial attacks. We propose a novel adversarial training-based model by Attention Guided Knowledge Distillation and Bi-directional Metric Learning (AGKD-BML). The attention knowledge is obtained from a weight-fixed model trained on a clean dataset, referred to as a teacher model, and transferred to a model that is under training on adversarial examples (AEs), referred to as a student model. In this way, the student model is able to focus on the correct region, as well as correcting the intermediate features corrupted by AEs to eventually improve the model accuracy. Moreover, to efficiently regularize the representation in feature space, we propose a bidirectional metric learning. Specifically, given a clean image, it is first attacked to its most confusing class to get the forward AE. A clean image in the most confusing class is then randomly picked and attacked back to the original class to get the backward AE. A triplet loss is then used to shorten the representation distance between original image and its AE, while enlarge that between the forward and backward AEs. We conduct extensive adversarial robustness experiments on two widely used datasets with different attacks. Our proposed AGKD-BML model consistently outperforms the state-of-the-art approaches. The code of AGKD-BML will be available at: https://github.com/hongw579/AGKD-BML.

cs.CV↗

The facet ideals of matching complexes of line graphs

Let $L_n$ be a line graph with $n$ edges and $\F(L_n)$ the facet ideal of its matching complex. In this paper, we provide the irreducible decomposition of $\F(L_n)$ and some exact formulas for the projective dimension and the regularity of $\F(L_n)$.

math.AC↗

Hamilton-Jacobi Equations for Nonholonomic Reducible Hamiltonian Systems on a Cotangent Bundle

In this paper, for a variety of nonholonomic (reducible) Hamiltonian systems, we first give to various distributional Hamiltonian systems, by analyzing carefully the dynamics and structures of the nonholonomic Hamiltonian systems. Secondly, we derive precisely the geometric constraint conditions of the induced distributional two-form for the nonholonomic dynamical vector field, which are called the Type I and Type II of Hamilton-Jacobi equations. Thirdly, we generalize the above results for the nonholonomic reducible Hamiltonian systems with symmetries, as well as with momentum maps, and prove two types of Hamilton-Jacobi theorems for various nonholonomic reduced distributional Hamiltonian systems. Finally, as an application, we give two examples to illustrate the theoretical results. These researches reveal the deeply internal relationships of the nonholonomic constraints, the induced (resp. reduced) distributional two-forms and the dynamical vector fields of the nonholonomic Hamiltonian system and its various distributional Hamiltonian systems.

math.SG↗

Lifelong Learning of Hate Speech Classification on Social Media

Existing work on automated hate speech classification assumes that the dataset is fixed and the classes are pre-defined. However, the amount of data in social media increases every day, and the hot topics changes rapidly, requiring the classifiers to be able to continuously adapt to new data without forgetting the previously learned knowledge. This ability, referred to as lifelong learning, is crucial for the real-word application of hate speech classifiers in social media. In this work, we propose lifelong learning of hate speech classification on social media. To alleviate catastrophic forgetting, we propose to use Variational Representation Learning (VRL) along with a memory module based on LB-SOINN (Load-Balancing Self-Organizing Incremental Neural Network). Experimentally, we show that combining variational representation learning and the LB-SOINN memory module achieves better performance than the commonly-used lifelong learning techniques.

cs.CL↗

HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data

Existing question answering datasets focus on dealing with homogeneous information, based either only on text or KB/Table information alone. However, as human knowledge is distributed over heterogeneous forms, using homogeneous information alone might lead to severe coverage problems. To fill in the gap, we present HybridQA https://github.com/wenhuchen/HybridQA, a new large-scale question-answering dataset that requires reasoning on heterogeneous information. Each question is aligned with a Wikipedia table and multiple free-form corpora linked with the entities in the table. The questions are designed to aggregate both tabular information and text information, i.e., lack of either form would render the question unanswerable. We test with three different models: 1) a table-only model. 2) text-only model. 3) a hybrid model that combines heterogeneous information to find the answer. The experimental results show that the EM scores obtained by two baselines are below 20\%, while the hybrid model can achieve an EM over 40\%. This gap suggests the necessity to aggregate heterogeneous information in HybridQA. However, the hybrid model's score is still far behind human performance. Hence, HybridQA can serve as a challenging benchmark to study question answering with heterogeneous information.

cs.CL↗

Unusual normal and superconducting state properties observed in hydrothermal Fe1-xSe flakes

The electronic and superconducting properties of Fe1-xSe single-crystal flakes grown hydrothermally are studied by the transport measurements under zero and high magnetic fields up to 38.5 T. The results contrast sharply with those previously reported for nematically ordered FeSe by chemical-vapor-transport (CVT) growth. No signature of the electronic nematicity, but an evident metal-to-nonmetal crossover with increasing temperature, is detected in the normal state of the present hydrothermal samples. Interestingly, a higher superconducting critical temperature Tc of 13.2 K is observed compared to a suppressed Tc of 9 K in the presence of the nematicity in the CVT FeSe. Moreover, the upper critical field in the zero-temperature limit is found to be isotropic with respect to the field direction and to reach a higher value of ~42 T, which breaks the Pauli limit by a factor of 1.8.

cond-mat.supr-con↗

The Bochner-Riesz problem: an old approach revisited

We show that the recent techniques developed to study the Fourier restriction problem apply equally well to the Bochner-Riesz problem. This is achieved via applying a pseudo-conformal transformation and a two-parameter induction-on-scales argument. As a consequence, we improve the Bochner-Riesz problem to the best known range of the Fourier restriction problem in all high dimensions.

math.CA↗

An improved result for Falconer's distance set problem in even dimensions

We show that if compact set $E\subset \mathbb{R}^d$ has Hausdorff dimension larger than $\frac{d}{2}+\frac{1}{4}$, where $d\geq 4$ is an even integer, then the distance set of $E$ has positive Lebesgue measure. This improves the previously best known result towards Falconer's distance set conjecture in even dimensions.

math.CA↗

Symmetric Reduction of Regular Controlled Lagrangian System with Momentum Map

In this paper, following the ideas in Marsden et al.[18], we set up the regular reduction theory of a regular controlled Lagrangian (RCL) system with symmetry and momentum map, by using Legendre transformation and Euler-Lagrange vector field, and this reduction is an extension of symmetric reduction theory of a regular Lagrangian system under regular controlled Lagrangian equivalence conditions. Considering the completeness of reduction, in order to describe uniformly the RCL systems defined on a tangent bundle and on its regular reduced spaces, we first define a kind of RCL systems on a symplectic fiber bundle. Then we give a good expression of the dynamical vector field of the RCL system, such that we can describe the RCL-equivalence for the RCL systems. Moreover, we introduce regular point and regular orbit reducible RCL systems with symmetries and momentum maps, by using the reduced Lagrange symplectic forms and the reduced Euler-Lagrange vector fields, and prove the regular point and regular orbit reduction theorems for the RCL systems and regular Lagrangian systems, which explain the relationships between RpCL-equivalence, RoCL-equivalence for the reducible RCL systems with symmetries and RCL-equivalence for the associated reduced RCL systems, as well as the relationship of equivalences of the regular reducible Lagrangian systems, $R_p$-reduced Lagrangian systems and $R_o$-reduced Lagrangian systems.

math.SG↗

Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering

To extract answers from a large corpus, open-domain question answering (QA) systems usually rely on information retrieval (IR) techniques to narrow the search space. Standard inverted index methods such as TF-IDF are commonly used as thanks to their efficiency. However, their retrieval performance is limited as they simply use shallow and sparse lexical features. To break the IR bottleneck, recent studies show that stronger retrieval performance can be achieved by pretraining a effective paragraph encoder that index paragraphs into dense vectors. Once trained, the corpus can be pre-encoded into low-dimensional vectors and stored within an index structure where the retrieval can be efficiently implemented as maximum inner product search. Despite the promising results, pretraining such a dense index is expensive and often requires a very large batch size. In this work, we propose a simple and resource-efficient method to pretrain the paragraph encoder. First, instead of using heuristically created pseudo question-paragraph pairs for pretraining, we utilize an existing pretrained sequence-to-sequence model to build a strong question generator that creates high-quality pretraining data. Second, we propose a progressive pretraining algorithm to ensure the existence of effective negative samples in each batch. Across three datasets, our method outperforms an existing dense retrieval method that uses 7 times more computational resources for pretraining.

cs.CL↗

NBSearch: Semantic Search and Visual Exploration of Computational Notebooks

Code search is an important and frequent activity for developers using computational notebooks (e.g., Jupyter). The flexibility of notebooks brings challenges for effective code search, where classic search interfaces for traditional software code may be limited. In this paper, we propose, NBSearch, a novel system that supports semantic code search in notebook collections and interactive visual exploration of search results. NBSearch leverages advanced machine learning models to enable natural language search queries and intuitive visualizations to present complicated intra- and inter-notebook relationships in the returned results. We developed NBSearch through an iterative participatory design process with two experts from a large software company. We evaluated the models with a series of experiments and the whole system with a controlled user study. The results indicate the feasibility of our analytical pipeline and the effectiveness of NBSearch to support code search in large notebook collections.

cs.HC↗

A cone restriction estimate using polynomial partitioning

We obtain improved Fourier restriction estimate for the truncated cone using the method of polynomial partitioning in dimension $n\geq 3$, which in particular solves the cone restriction conjecture for $n=5$, and recovers the sharp range for $3\leq n\leq 4$. The main ingredient of the proof is a $k$-broad estimate for the cone extension operator, which is a weak version of the $k$-linear cone restriction estimate for $2\leq k\leq n$.

math.CA↗

From Rain Generation to Rain Removal

For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets. Most of current state-of-the-art focus on constructing powerful deep models to obtain better deraining results. In this paper, to further improve the deraining performance, we novelly attempt to handle the SIRR task from the perspective of training datasets by exploring a more efficient way to synthesize rainy images. Specifically, we build a full Bayesian generative model for rainy image where the rain layer is parameterized as a generator with the input as some latent variables representing the physical structural rain factors, e.g., direction, scale, and thickness. To solve this model, we employ the variational inference framework to approximate the expected statistical distribution of rainy image in a data-driven manner. With the learned generator, we can automatically and sufficiently generate diverse and non-repetitive training pairs so as to efficiently enrich and augment the existing benchmark datasets. User study qualitatively and quantitatively evaluates the realism of generated rainy images. Comprehensive experiments substantiate that the proposed model can faithfully extract the complex rain distribution that not only helps significantly improve the deraining performance of current deep single image derainers, but also largely loosens the requirement of large training sample pre-collection for the SIRR task.

cs.CV↗

Quantifying the potential and flux landscapes for nonequilibrium multiverse, a new scenario for time arrow

We propose a new scenario of nonequilibirum multiverse. We quantified the potential landscape and the flux landscape for the Bousso-Polchinski type of multiverse. The potential landscape quantifies the weight of each universe. When the terminal vacuum with zero (flat) or negative cosmological constant (AdS) have a chance to tunnel back to the normal universes with positive cosmological constant (dS) through the bounce suggested by the recent studies, the detailed balance of the populations of the multiverse can be broken. We found that the degree of the detailed balance breaking can be quantified by the underlying average flux and associated flux landscape, which gives arise to the dynamical origin of irreversibility and the arrow of time. We also showed that the steady state of the multiverse is maintained by the thermodynamic cost quantified by the entropy production rate which is associated to the flux. This gives arise to thermodynamic origin of time irreversibility. We show that terminal vacuum universes can have dominant weights or lowest potentials giving arise to a funnel shaped potential landscape, while terminal vacuum universes together with other normal universes including ours can form dominant cycles giving arise to a funnel shaped cycle flux landscape. This indicates that even our universe may not be distinct from others based on the probability measure, it may lie in the dominant cycle(s), leading to higher chance of being found. This may provide an additional way beyond the anthropological principle for identifying our universe.

hep-th↗

The Geometrical Structure of Phase Space of the Controlled Hamiltonian System with Symmetry

In this paper, from the viewpoint of completeness of Marsden-Weinstein reduction, we illustrate how to give the definitions of a controlled Hamiltonian (CH) system and a reducible controlled Hamiltonian system with symmetry; and how to describe the dynamics of a CH system and the controlled Hamiltonian equivalence; as well as how to give the regular point reduction and the regular orbit reduction for a CH system with symmetry, by analyzing carefully the geometrical and topological structures of the phase space and the reduced phase space of the corresponding Hamiltonian system. We also introduce briefly some recent developments in the study of reduction theory for the CH systems with symmetries and applications. These research work reveal the deeply internal relationships of the geometrical structures of phase spaces, the dynamical vector fields and controls of the CH systems.

math.SG↗

Improved decoupling for the parabola

We prove an $(l^2, l^6)$ decoupling inequality for the parabola with constant $(\log R)^c$. In the appendix, we present an application to the six-order correlation of the integer solutions to $x^2+y^2=m$.

math.CA↗