arXiv subjects

Xin Wei

Publications and source records attributed to Xin Wei.

At least 73 records · Page 4Linked to original sources

arXiv2023

Chrono DEM-Engine: A Discrete Element Method dual-GPU simulator with customizable contact forces and element shape

This paper introduces DEM-Engine, a new submodule of Project Chrono, that is designed to carry out Discrete Element Method (DEM) simulations. Based on spherical primitive shapes, DEM-Engine can simulate polydisperse granular materials and handle complex shapes generated as assemblies of primitives, referred to as clumps. DEM-Engine has a multi-tier parallelized structure that is optimized to operate simultaneously on two GPUs. The code uses custom-defined data types to reduce memory footprint and increase bandwidth. A novel "delayed contact detection" algorithm allows the decoupling of the contact detection and force computation, thus splitting the workload into two asynchronous GPU streams. DEM-Engine uses just-in-time compilation to support user-defined contact force models. This paper discusses its C++ and Python interfaces and presents a variety of numerical tests, in which impact forces, complex-shaped particle flows, and a custom force model are validated considering well-known benchmark cases. Additionally, the full potential of the simulator is demonstrated for the investigation of extraterrestrial rover mobility on granular terrain. The chosen case study demonstrates that large-scale co-simulations (comprising 11 million elements) spanning 15 seconds, in conjunction with an external multi-body dynamics system, can be efficiently executed within a day. Lastly, a performance test suggests that DEM-Engine displays linear scaling up to 150 million elements on two NVIDIA A100 GPUs.

cs.CE↗

arXiv2023

DeepPatent2: A Large-Scale Benchmarking Corpus for Technical Drawing Understanding

Recent advances in computer vision (CV) and natural language processing have been driven by exploiting big data on practical applications. However, these research fields are still limited by the sheer volume, versatility, and diversity of the available datasets. CV tasks, such as image captioning, which has primarily been carried out on natural images, still struggle to produce accurate and meaningful captions on sketched images often included in scientific and technical documents. The advancement of other tasks such as 3D reconstruction from 2D images requires larger datasets with multiple viewpoints. We introduce DeepPatent2, a large-scale dataset, providing more than 2.7 million technical drawings with 132,890 object names and 22,394 viewpoints extracted from 14 years of US design patent documents. We demonstrate the usefulness of DeepPatent2 with conceptual captioning. We further provide the potential usefulness of our dataset to facilitate other research areas such as 3D image reconstruction and image retrieval.

cs.CV↗

arXiv2023

Swap-Robust and Almost Supermagic Complete Graphs for Dynamical Distributed Storage

To prevent service time bottlenecks in distributed storage systems, the access balancing problem has been studied by designing almost supermagic edge labelings of certain graphs to balance the access requests to different servers. In this paper, we introduce the concept of robustness of edge labelings under limited-magnitude swaps, which is important for studying the dynamical access balancing problem with respect to changes in data popularity. We provide upper and lower bounds on the robustness ratio for complete graphs with $n$ vertices, and construct $O(n)$-almost supermagic labelings that are asymptotically optimal in terms of the robustness ratio.

math.CO↗

arXiv2023

Separating hash families with large universe

Separating hash families are useful combinatorial structures which generalize several well-studied objects in cryptography and coding theory. Let $p_t(N, q)$ denote the maximum size of universe for a $t$-perfect hash family of length $N$ over an alphabet of size $q$. In this paper, we show that $q^{2-o(1)}<p_t(t, q)=o(q^2)$ for all $t\geq 3$, which answers an open problem about separating hash families raised by Blackburn et al. in 2008 for certain parameters. Previously, this result was known only for $t=3, 4$. Our proof is obtained by establishing the existence of a large set of integers avoiding nontrivial solutions to a set of correlated linear equations.

math.CO↗

arXiv2023

On supersaturation for oddtown and eventown

We study the supersaturation problems of oddtown and eventown. Given a family $\mathcal A$ of subsets of an $n$ element set, let $op(\mathcal A)$ denote the number of distinct pairs $A,B\in \mathcal A$ for which $|A \cap B|$ is odd. We show that if $\mathcal A$ consists of $n+s$ odd-sized subsets, then $op(\mathcal A)\geq s+2$, which is tight when $s\le n-4$. This disproves a conjecture by O'Neill on the supersaturation problem of oddtown. For the supersaturation problem of eventown, we show that for large enough $n$, if $\mathcal A$ consists of $2^{\lfloor \frac n 2\rfloor}+s$ even-sized subsets, then $op(\mathcal A)\ge s\cdot2^{\lfloor \frac n 2\rfloor-1} $ for any positive integer $s\le \frac{2^{\lfloor\frac n 8\rfloor}} n$. This partially proves a conjecture by O'Neill on the supersaturation problem of eventown. Previously, the correctness of this conjecture was only verified for $s=1$ and $2$. We further provide a twice weaker lower bound in this conjecture for eventown, that is $op(\mathcal{A})\ge s\cdot 2^{\lfloor n/2\rfloor-2}$ for general $n$ and $s$ by using discrete Fourier analysis. Finally, some asymptotic results for the lower bounds of $op(\mathcal A)$ are given when $s$ is large for both problems.

math.CO↗

arXiv2023

Towards Accurate Acne Detection via Decoupled Sequential Detection Head

Accurate acne detection plays a crucial role in acquiring precise diagnosis and conducting proper therapy. However, the ambiguous boundaries and arbitrary dimensions of acne lesions severely limit the performance of existing methods. In this paper, we address these challenges via a novel Decoupled Sequential Detection Head (DSDH), which can be easily adopted by mainstream two-stage detectors. DSDH brings two simple but effective improvements to acne detection. Firstly, the offset and scaling tasks are explicitly introduced, and their incompatibility is settled by our task-decouple mechanism, which improves the capability of predicting the location and size of acne lesions. Second, we propose the task-sequence mechanism, and execute offset and scaling sequentially to gain a more comprehensive insight into the dimensions of acne lesions. In addition, we build a high-quality acne detection dataset named ACNE-DET to verify the effectiveness of DSDH. Experiments on ACNE-DET and the public benchmark ACNE04 show that our method outperforms the state-of-the-art methods by significant margins. Our code and dataset are publicly available at (temporarily anonymous).

cs.CV↗

arXiv2022

Decreased serum vitamin D level as a prognostic marker in patients with COVID-19

Background: The corona virus disease 2019 (COVID-19) pandemic, which is caused by severe acute respiratory syndrome coronavirus 2, is still localized outbreak and has resulted in a high rate of infection and severe disease in older patients with comorbidities. The vitamin D status of the population has been found to be an important factor that could influence outcome of COVID-19. However, whether vitamin D can lessen the symptoms or severity of COVID-19 still remains controversial. Methods: A total of 719 patients with confirmed COVID-19 were enrolled retrospectively in this study from April 13 to June 6, 2022 at Shanghai Forth People's Hospital. The circulating levels of 25(OH)D3, inflammatory factors, and clinical parameters were assayed. Time to viral RNA clearance (TVRC), classification and prognosis of COVID-19 were used to evaluate the severity of COVID-19 infection. Results: The median age was 76 years (interquartile range, IQR, 64.5-84.6), 44.1% of patients were male, and the TVRC was 11 days (IQR, 7-16) in this population. The median level of 25(OH)D3 was 27.15 (IQR, 19.31-38.89) nmol/L. Patients with lower serum 25(OH)D3 had prolonged time to viral clearance, more obvious inflammatory response, more severe respiratory symptoms and higher risks of impaired hepatic and renal function. Multiple regression analyses revealed that serum 25(OH)D3 level was negatively associated with TVRC independently. ROC curve showed the serum vitamin D level could predict the severity classification and prognosis of COVID-19 significantly.Conclusions: Serum 25(OH)D3 level is independently associated with the severity of COVID-19 in elderly, and it could be used as a predictor of the severity of COVID-19. In addition, supplementation with vitamin D might provide beneficial effects in old patients with COVID-19.

q-bio.TO↗

arXiv2022

Faint Features Tell: Automatic Vertebrae Fracture Screening Assisted by Contrastive Learning

Long-term vertebral fractures severely affect the life quality of patients, causing kyphotic, lumbar deformity and even paralysis. Computed tomography (CT) is a common clinical examination to screen for this disease at early stages. However, the faint radiological appearances and unspecific symptoms lead to a high risk of missed diagnosis, especially for the mild vertebral fractures. In this paper, we argue that reinforcing the faint fracture features to encourage the inter-class separability is the key to improving the accuracy. Motivated by this, we propose a supervised contrastive learning based model to estimate Genent's Grade of vertebral fracture with CT scans. The supervised contrastive learning, as an auxiliary task, narrows the distance of features within the same class while pushing others away, enhancing the model's capability of capturing subtle features of vertebral fractures. Our method has a specificity of 99% and a sensitivity of 85% in binary classification, and a macro-F1 of 77% in multi-class classification, indicating that contrastive learning significantly improves the accuracy of vertebrae fracture screening. Considering the lack of datasets in this field, we construct a database including 208 samples annotated by experienced radiologists. Our desensitized data and codes will be made publicly available for the community.

cs.CV↗

arXiv2022

Spiral Contrastive Learning: An Efficient 3D Representation Learning Method for Unannotated CT Lesions

Computed tomography (CT) samples with pathological annotations are difficult to obtain. As a result, the computer-aided diagnosis (CAD) algorithms are trained on small datasets (e.g., LIDC-IDRI with 1,018 samples), limiting their accuracies and reliability. In the past five years, several works have tailored for unsupervised representations of CT lesions via two-dimensional (2D) and three-dimensional (3D) self-supervised learning (SSL) algorithms. The 2D algorithms have difficulty capturing 3D information, and existing 3D algorithms are computationally heavy. Light-weight 3D SSL remains the boundary to explore. In this paper, we propose the spiral contrastive learning (SCL), which yields 3D representations in a computationally efficient manner. SCL first transforms 3D lesions to the 2D plane using an information-preserving spiral transformation, and then learn transformation-invariant features using 2D contrastive learning. For the augmentation, we consider natural image augmentations and medical image augmentations. We evaluate SCL by training a classification head upon the embedding layer. Experimental results show that SCL achieves state-of-the-art accuracy on LIDC-IDRI (89.72%), LNDb (82.09%) and TianChi (90.16%) for unsupervised representation learning. With 10% annotated data for fine-tune, the performance of SCL is comparable to that of supervised learning algorithms (85.75% vs. 85.03% on LIDC-IDRI, 78.20% vs. 73.44% on LNDb and 87.85% vs. 83.34% on TianChi, respectively). Meanwhile, SCL reduces the computational effort by 66.98% compared to other 3D SSL algorithms, demonstrating the efficiency of the proposed method in unsupervised pre-training.

cs.CV↗

arXiv2022

GREN: Graph-Regularized Embedding Network for Weakly-Supervised Disease Localization in X-ray Images

Locating diseases in chest X-ray images with few careful annotations saves large human effort. Recent works approached this task with innovative weakly-supervised algorithms such as multi-instance learning (MIL) and class activation maps (CAM), however, these methods often yield inaccurate or incomplete regions. One of the reasons is the neglection of the pathological implications hidden in the relationship across anatomical regions within each image and the relationship across images. In this paper, we argue that the cross-region and cross-image relationship, as contextual and compensating information, is vital to obtain more consistent and integral regions. To model the relationship, we propose the Graph Regularized Embedding Network (GREN), which leverages the intra-image and inter-image information to locate diseases on chest X-ray images. GREN uses a pre-trained U-Net to segment the lung lobes, and then models the intra-image relationship between the lung lobes using an intra-image graph to compare different regions. Meanwhile, the relationship between in-batch images is modeled by an inter-image graph to compare multiple images. This process mimics the training and decision-making process of a radiologist: comparing multiple regions and images for diagnosis. In order for the deep embedding layers of the neural network to retain structural information (important in the localization task), we use the Hash coding and Hamming distance to compute the graphs, which are used as regularizers to facilitate training. By means of this, our approach achieves the state-of-the-art result on NIH chest X-ray dataset for weakly-supervised disease localization. Our codes are accessible online (https://github.com/qibaolian/GREN).

cs.CV↗

arXiv2022

Learning High-quality Proposals for Acne Detection

Acne detection is crucial for interpretative diagnosis and precise treatment of skin disease. The arbitrary boundary and small size of acne lesions lead to a significant number of poor-quality proposals in two-stage detection. In this paper, we propose a novel head structure for Region Proposal Network to improve the proposals' quality in two ways. At first, a Spatial Aware Double Head(SADH) structure is proposed to disentangle the representation learning for classification and localization from two different spatial perspectives. The proposed SADH ensures a steeper classification confidence gradient and suppresses the proposals having low intersection-over-union(IoU) with the matched ground truth. Then, we propose a Normalized Wasserstein Distance prediction branch to improve the correlation between the proposals' classification scores and IoUs. In addition, to facilitate further research on acne detection, we construct a new dataset named AcneSCU, with high-resolution imageries, precise annotations, and fine-grained lesion categories. Extensive experiments are conducted on both AcneSCU and the public dataset ACNE04, and the results demonstrate the proposed method could improve the proposals' quality, consistently outperforming state-of-the-art approaches. Code and the collected dataset are available in https://github.com/pingguokiller/acnedetection.

cs.CV↗

arXiv2022

Nature of novel moiré exciton states in WSe$_2$/WS$_2$ heterobilayers

Moiré patterns of transition metal dichalcogenide (TMD) heterobilayers have proven to be an ideal platform to host unusual correlated electronic phases, emerging magnetism, and correlated exciton physics. While the existence of novel moiré excitonic states is established through optical measurements, the microscopic nature of these states is still poorly understood, often relying on empirically fit models. Here, combining large-scale first-principles GW-BSE calculations and micro-reflection spectroscopy, we identify the nature of the exciton resonances in WSe$_2$/WS$_2$ moiré superlattices, discovering a surprisingly rich set of moiré excitons that cannot be even qualitatively captured by prevailing continuum models. Our calculations reveal moiré excitons with distinct characters, including modulated Wannier excitons and previously unindentified intralayer charge-transfer excitons. Signatures of these distinct excitonic characters are confirmed experimentally via the unique carrier-density and magnetic-field dependences of different moiré exciton resonances. Our study highlights the highly non-trivial exciton states that can emerge in TMD moiré superlattices, and suggests novel ways of tuning many-body physics in moiré systems by engineering excited-states with specific spatial characters.

cond-mat.mes-hall↗

arXiv2021

A Synthetic Prediction Market for Estimating Confidence in Published Work

Explainably estimating confidence in published scholarly work offers opportunity for faster and more robust scientific progress. We develop a synthetic prediction market to assess the credibility of published claims in the social and behavioral sciences literature. We demonstrate our system and detail our findings using a collection of known replication projects. We suggest that this work lays the foundation for a research agenda that creatively uses AI for peer review.

cs.CY↗

arXiv2021

Predicting the Reproducibility of Social and Behavioral Science Papers Using Supervised Learning Models

In recent years, significant effort has been invested verifying the reproducibility and robustness of research claims in social and behavioral sciences (SBS), much of which has involved resource-intensive replication projects. In this paper, we investigate prediction of the reproducibility of SBS papers using machine learning methods based on a set of features. We propose a framework that extracts five types of features from scholarly work that can be used to support assessments of reproducibility of published research claims. Bibliometric features, venue features, and author features are collected from public APIs or extracted using open source machine learning libraries with customized parsers. Statistical features, such as p-values, are extracted by recognizing patterns in the body text. Semantic features, such as funding information, are obtained from public APIs or are extracted using natural language processing models. We analyze pairwise correlations between individual features and their importance for predicting a set of human-assessed ground truth labels. In doing so, we identify a subset of 9 top features that play relatively more important roles in predicting the reproducibility of SBS papers in our corpus. Results are verified by comparing performances of 10 supervised predictive classifiers trained on different sets of features.

cs.DL↗

arXiv2021

GMH: A General Multi-hop Reasoning Model for KG Completion

Knowledge graphs are essential for numerous downstream natural language processing applications, but are typically incomplete with many facts missing. This results in research efforts on multi-hop reasoning task, which can be formulated as a search process and current models typically perform short distance reasoning. However, the long-distance reasoning is also vital with the ability to connect the superficially unrelated entities. To the best of our knowledge, there lacks a general framework that approaches multi-hop reasoning in mixed long-short distance reasoning scenarios. We argue that there are two key issues for a general multi-hop reasoning model: i) where to go, and ii) when to stop. Therefore, we propose a general model which resolves the issues with three modules: 1) the local-global knowledge module to estimate the possible paths, 2) the differentiated action dropout module to explore a diverse set of paths, and 3) the adaptive stopping search module to avoid over searching. The comprehensive results on three datasets demonstrate the superiority of our model with significant improvements against baselines in both short and long distance reasoning scenarios.

cs.AI↗

arXiv2021

Energy absorbency and phase stability during NaCl solution icing

NaCl solvation turns the fS portion molecules into the hydrating supersolid phase by ionic polarization and leaves the rest fO portion ordinary. Polarization shortens and stiffens the HO bond and does the O:H nonbond contrastingly in the supersolid. Water absorbs energy by HO cooling contraction in the quasisolid phase during the transition from Liquid to Quasisolid and then Ice The solution R drops with the fO loss till zero corresponding to 10 water molecules that saturates the solvation per solute at least. The polarization-weakening of the O H nonbonds lowers the TN to 253 K or below of the supersolid phase.

physics.chem-ph↗

arXiv2021

Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views

In this paper, we focus on recognizing 3D shapes from arbitrary views, i.e., arbitrary numbers and positions of viewpoints. It is a challenging and realistic setting for view-based 3D shape recognition. We propose a canonical view representation to tackle this challenge. We first transform the original features of arbitrary views to a fixed number of view features, dubbed canonical view representation, by aligning the arbitrary view features to a set of learnable reference view features using optimal transport. In this way, each 3D shape with arbitrary views is represented by a fixed number of canonical view features, which are further aggregated to generate a rich and robust 3D shape representation for shape recognition. We also propose a canonical view feature separation constraint to enforce that the view features in canonical view representation can be embedded into scattered points in a Euclidean space. Experiments on the ModelNet40, ScanObjectNN, and RGBD datasets show that our method achieves competitive results under the fixed viewpoint settings, and significantly outperforms the applicable methods under the arbitrary view setting.

cs.CV↗

arXiv2021

Entropy-based Optimization via A* Algorithm for Parking Space Recommendation

This paper addresses the path planning problems for recommending parking spaces, given the difficulties of identifying the most optimal route to vacant parking spaces and the shortest time to leave the parking space. Our optimization approach is based on the entropy method and realized by the A* algorithm. Experiments have shown that the combination of A* and the entropy value induces the optimal parking solution with the shortest route while being robust to environmental factors.

cs.CV↗