arXiv subjects

Xin Xiao

Publications and source records attributed to Xin Xiao.

27 records · Page 2Linked to original sources

arXiv2024

Dual Structure-Aware Image Filterings for Semi-supervised Medical Image Segmentation

Semi-supervised image segmentation has attracted great attention recently. The key is how to leverage unlabeled images in the training process. Most methods maintain consistent predictions of the unlabeled images under variations (e.g., adding noise/perturbations, or creating alternative versions) in the image and/or model level. In most image-level variation, medical images often have prior structure information, which has not been well explored. In this paper, we propose novel dual structure-aware image filterings (DSAIF) as the image-level variations for semi-supervised medical image segmentation. Motivated by connected filtering that simplifies image via filtering in structure-aware tree-based image representation, we resort to the dual contrast invariant Max-tree and Min-tree representation. Specifically, we propose a novel connected filtering that removes topologically equivalent nodes (i.e. connected components) having no siblings in the Max/Min-tree. This results in two filtered images preserving topologically critical structure. Applying the proposed DSAIF to mutually supervised networks decreases the consensus of their erroneous predictions on unlabeled images. This helps to alleviate the confirmation bias issue of overfitting to noisy pseudo labels of unlabeled images, and thus effectively improves the segmentation performance. Extensive experimental results on three benchmark datasets demonstrate that the proposed method significantly/consistently outperforms some state-of-the-art methods. The source codes will be publicly available.

cs.CV↗

arXiv2024

Shifted Autoencoders for Point Annotation Restoration in Object Counting

Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing counting model training. Some sophisticated noise-resistance counting methods have been proposed to alleviate this issue. Differently, we aim to directly refine the initial point annotations before training counting models. For that, we propose the Shifted Autoencoders (SAE), which enhances annotation consistency. Specifically, SAE applies random shifts to initial point annotations and employs a UNet to restore them to their original positions. Similar to MAE reconstruction, the trained SAE captures general position knowledge and ignores specific manual offset noise. This allows to restore the initial point annotations to more general and thus consistent positions. Extensive experiments show that using such refined consistent annotations to train some advanced (including noise-resistance) object counting models steadily/significantly boosts their performances. Remarkably, the proposed SAE helps to set new records on nine datasets. We will make codes and refined point annotations available.

cs.CV↗

arXiv2023

Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation

Semantic segmentation has recently witnessed great progress. Despite the impressive overall results, the segmentation performance in some hard areas (e.g., small objects or thin parts) is still not promising. A straightforward solution is hard sample mining, which is widely used in object detection. Yet, most existing hard pixel mining strategies for semantic segmentation often rely on pixel's loss value, which tends to decrease during training. Intuitively, the pixel hardness for segmentation mainly depends on image structure and is expected to be stable. In this paper, we propose to learn pixel hardness for semantic segmentation, leveraging hardness information contained in global and historical loss values. More precisely, we add a gradient-independent branch for learning a hardness level (HL) map by maximizing hardness-weighted segmentation loss, which is minimized for the segmentation head. This encourages large hardness values in difficult areas, leading to appropriate and stable HL map. Despite its simplicity, the proposed method can be applied to most segmentation methods with no and marginal extra cost during inference and training, respectively. Without bells and whistles, the proposed method achieves consistent/significant improvement (1.37% mIoU on average) over most popular semantic segmentation methods on Cityscapes dataset, and demonstrates good generalization ability across domains. The source codes are available at https://github.com/Menoly-xin/Hardness-Level-Learning .

cs.CV↗

arXiv2023

Correlating Chemical Reaction and Mass Transport in Hydrogen-based Direct Reduction of Iron Oxide

Steelmaking contributes 8% to the total CO2 emissions globally, primarily due to coal-based iron ore reduction. Clean hydrogen-based ironmaking has variable performance because the dominant gas-solid reduction mechanism is set by the defects and pores inside the mm-nm sized oxide particles that change significantly as the reaction progresses. While these governing dynamics are essential to establish continuous flow of iron and its ores through reactors, the direct link between agglomeration and chemistry is still contested due to missing measurements. In this work, we directly measure the connection between chemistry and agglomeration in the smallest iron oxides relevant to magnetite ores. Using synthesized spherical 10-nm magnetite particles reacting in H2, we resolve the formation and consumption of wüstite (FeO) - the step most commonly attributed to agglomeration. Using X-ray scattering and microscopy, we resolve crystallographic anisotropy in the rate of the initial reaction, which becomes isotropic as the material sinters. Complementing with imaging, we demonstrate how the particles self-assemble, subsequently react and sinter into ~100x oblong grains. Our insights into how morphologically uniform iron oxide particles react and agglomerate H2 reduction enable future size-dependent models to effectively describe the multiscale iron ore reduction.

cond-mat.mtrl-sci↗

arXiv2022

Characterizing Equitable Access to Grocery Stores During Disasters Using Location-based Data

Natural hazards cause disruptions in access to critical facilities, such as grocery stores, impeding residents ability to prepare for and cope with hardships during the disaster and recovery; however, disrupted access to critical facilities is not equal for all residents of a community. In this study, we examine disparate access to grocery stores in the context of the 2017 Hurricane Harvey in Harris County, Texas. We utilized high-resolution location-based datasets in implementing spatial network analysis and dynamic clustering techniques to uncover the overall disparate access to grocery stores for socially vulnerable populations during different phases of the disaster. Three access indicators are examined using network-centric measures: number of unique stores visited, average trip time to stores, and average distance to stores. These access indicators help us capture three dimensions of access: redundancy, rapidity, and proximity. The findings show the insufficiency of focusing merely on the distributional factors, such as location in a food desert and number of facilities, to capture the disparities in access, especially during the preparation and impact/short-term recovery periods. Furthermore, the characterization of access by considering combinations of access indicators reveals that flooding disproportionally affects socially vulnerable populations. High-income areas have better access during preparation as they are able to visit a greater number of stores and commute farther distances to obtain supplies. The conclusions of this study have important implications for urban development (facility distribution), emergency management, and resource allocation by identifying areas most vulnerable to disproportionate access impacts using more equity-focused and data-driven approaches.

physics.soc-ph↗

arXiv2021

FAID Diversity via Neural Networks

Decoder diversity is a powerful error correction framework in which a collection of decoders collaboratively correct a set of error patterns otherwise uncorrectable by any individual decoder. In this paper, we propose a new approach to design the decoder diversity of finite alphabet iterative decoders (FAIDs) for Low-Density Parity Check (LDPC) codes over the binary symmetric channel (BSC), for the purpose of lowering the error floor while guaranteeing the waterfall performance. The proposed decoder diversity is achieved by training a recurrent quantized neural network (RQNN) to learn/design FAIDs. We demonstrated for the first time that a machine-learned decoder can surpass in performance a man-made decoder of the same complexity. As RQNNs can model a broad class of FAIDs, they are capable of learning an arbitrary FAID. To provide sufficient knowledge of the error floor to the RQNN, the training sets are constructed by sampling from the set of most problematic error patterns - trapping sets. In contrast to the existing methods that use the cross-entropy function as the loss function, we introduce a frame-error-rate (FER) based loss function to train the RQNN with the objective of correcting specific error patterns rather than reducing the bit error rate (BER). The examples and simulation results show that the RQNN-aided decoder diversity increases the error correction capability of LDPC codes and lowers the error floor.

cs.IT↗

arXiv2021

Unraveling the Dynamic Importance of County-level Features in Trajectory of COVID-19

The objective of this study was to investigate the importance of multiple county-level features in the trajectory of COVID-19. We examined feature importance across 2,787 counties in the United States using a data-driven machine learning model. We trained random forest models using 23 features representing six key influencing factors affecting pandemic spread: social demographics of counties, population activities, mobility within the counties, movement across counties, disease attributes, and social network structure. Also, we categorized counties into multiple groups according to their population densities, and we divided the trajectory of COVID-19 into three stages: the outbreak stage, the social distancing stage, and the reopening stage. The study aims to answer two research questions: (1) The extent to which the importance of heterogeneous features evolves in different stages; (2) The extent to which the importance of heterogeneous features varies across counties with different characteristics. We fitted a set of random forest models to determine weekly feature importance. The results showed that: (1) Social demographic features, such as gross domestic product, population density, and minority status maintained high-importance features throughout stages of COVID-19 across the 2787 studied counties; (2) Within-county mobility features had the highest importance in county clusters with higher population densities; (3) The feature reflecting the social network structure (Facebook, social connectedness index), had higher importance in the models for counties with higher population densities. The results show that the data-driven machine learning models could provide important insights to inform policymakers regarding feature importance for counties with various population densities and in different stages of a pandemic life cycle.

physics.soc-ph↗

arXiv2020

Disparate Patterns of Movements and Visits to Points of Interests Located in Urban Hotspots across U.S. Metropolitan Cities during COVID-19

We examined the effect of social distancing on changes in visits to urban hotspot points of interest. Urban hotspots, such as central business districts, are gravity activity centers orchestrating movement and mobility patterns in cities. In a pandemic situation, urban hotspots could be potential superspreader areas as visits to urban hotspots can increase the risk of contact and transmission of a disease among a population. We mapped origin-destination networks from census block groups to points of interest (POIs) in sixteen cities in the United States. We adopted a coarse-grain approach to study movement patterns of visits to POIs among the hotspots and non-hotspots from January to May 2020. Also, we conducted chi-square tests to identify POIs with significant flux-in changes during the analysis period. The results showed disparate patterns across cities in terms of reduction in POI visits to hotspot areas. The sixteen cities are divided into two categories based on visits to POIs in hotspot areas. In one category, which includes the cities of, San Francisco, Seattle, and Chicago, we observe a considerable decrease in visits to POIs in hotspot areas, while in another category, including the cites of, Austin, Houston, and San Diego, the visits to hotspot areas did not greatly decrease during the social distancing period. In addition, while all the cities exhibited overall decreasing visits to POIs, one category maintained the proportion of visits to POIs in the hotspots. The proportion of visits to some POIs (e.g., Restaurant and Other Eating Places) remained stable during the social distancing period, while some POIs had an increased proportion of visits (e.g., Grocery Stores). The findings highlight that social distancing orders do yield disparate patterns of reduction in movements to hotspots POIs.

physics.soc-ph↗

arXiv2012

On the Sensitivity of Shape Fitting Problems

In this article, we study shape fitting problems, $ε$-coresets, and total sensitivity. We focus on the $(j,k)$-projective clustering problems, including $k$-median/$k$-means, $k$-line clustering, $j$-subspace approximation, and the integer $(j,k)$-projective clustering problem. We derive upper bounds of total sensitivities for these problems, and obtain $ε$-coresets using these upper bounds. Using a dimension-reduction type argument, we are able to greatly simplify earlier results on total sensitivity for the $k$-median/$k$-means clustering problems, and obtain positively-weighted $ε$-coresets for several variants of the $(j,k)$-projective clustering problem. We also extend an earlier result on $ε$-coresets for the integer $(j,k)$-projective clustering problem in fixed dimension to the case of high dimension.

cs.CG↗