arXiv subjects

Xin Huang

Publications and source records attributed to Xin Huang.

At least 217 records · Page 12Linked to original sources

arXiv2021

Efficient and Optimal Algorithms for Tree Summarization with Weighted Terminologies

Data summarization that presents a small subset of a dataset to users has been widely applied in numerous applications and systems. Many datasets are coded with hierarchical terminologies, e.g., the international classification of Diseases-9, Medical Subject Heading, and Gene Ontology, to name a few. In this paper, we study the problem of selecting a diverse set of k elements to summarize an input dataset with hierarchical terminologies, and visualize the summary in an ontology structure. We propose an efficient greedy algorithm to solve the problem with (1-1/e) = 62% -approximation guarantee. Although this greedy solution achieves quality-guaranteed answers approximately but it is still not optimal. To tackle the problem optimally, we further develop a dynamic programming algorithm to obtain optimal answers for graph visualization of log-data using ontology terminologies called OVDO . The complexity and correctness of OVDO are theoretically analyzed. In addition, we propose a useful optimization technique of tree reduction to remove useless nodes with zero weights and shrink the tree into a smaller one, which ensures the efficiency acceleration of OVDO in many real-world applications. Extensive experimental results on real-world datasets show the effectiveness and efficiency of our proposed approximate and exact algorithms for tree data summarization.

cs.DB↗

arXiv2021

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. A few works investigated manually combining those operators to design visual network architectures, and can achieve satisfactory performances to some extent. In this paper, we propose to jointly search the optimal combination of convolution, transformer, and MLP for building a series of all-operator network architectures with high performances on visual tasks. We empirically identify that the widely-used strided convolution or pooling based down-sampling modules become the performance bottlenecks when the operators are combined to form a network. To better tackle the global context captured by the transformer and MLP operators, we propose two novel context-aware down-sampling modules, which can better adapt to the global information encoded by transformer and MLP operators. To this end, we jointly search all operators and down-sampling modules in a unified search space. Notably, Our searched network UniNet (Unified Network) outperforms state-of-the-art pure convolution-based architecture, EfficientNet, and pure transformer-based architecture, Swin-Transformer, on multiple public visual benchmarks, ImageNet classification, COCO object detection, and ADE20K semantic segmentation.

cs.CV↗

arXiv2021

HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling

Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over longer horizons. To overcome this limitation, we introduce HYPER, a general and expressive hybrid prediction framework that models evolving human intent. By modeling traffic agents as a hybrid discrete-continuous system, our approach is capable of predicting discrete intent changes over time. We learn the probabilistic hybrid model via a maximum likelihood estimation problem and leverage neural proposal distributions to sample adaptively from the exponentially growing discrete space. The overall approach affords a better trade-off between accuracy and coverage. We train and validate our model on the Argoverse dataset, and demonstrate its effectiveness through comprehensive ablation studies and comparisons with state-of-the-art models.

cs.RO↗

arXiv2021

Unified Fair Allocation of Goods and Chores via Copies

We consider fair allocation of indivisible items in a model with goods, chores, and copies, as a unified framework for studying: (1)~the existence of EFX and other solution concepts for goods with copies; (2)~the existence of EFX and other solution concepts for chores. We establish a tight relation between these issues via two conceptual contributions: First, a refinement of envy-based fairness notions that we term envy \emph{without commons} (denoted $\efxwc$ when applied to EFX). Second, a formal \emph{duality theorem} relating the existence of a host of (refined) fair allocation concepts for copies to their existence for chores. We demonstrate the usefulness of our duality result by using it to characterize the existence of EFX for chores through the dual environment, as well as to prove EFX existence in the special case of leveled preferences over the chores. We further study the hierarchy among envy-freeness notions without commons and their $α$-MMS guarantees, showing for example that any $\efxwc$ allocation guarantees at least $\frac{4}{11}$-MMS for goods with copies.

cs.GT↗

arXiv2021

Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures

This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts. We show that the problem of risk assessment when Gaussian mixture models (GMMs) of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using nonlinear Chebyshev's Inequality and sums-of-squares (SOS) programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require higher order statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent control inputs as opposed to positions, we propagate the moments of uncertain control inputs through the nonlinear motion dynamics to obtain the exact moments of uncertain position over the planning horizon. To this end, we construct deterministic linear dynamical systems that govern the exact time evolution of the moments of uncertain position in the presence of uncertain control inputs. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events.

cs.LG↗

arXiv2021

An Indoor Crowd Movement Trajectory Benchmark Dataset

In recent years, technologies of indoor crowd positioning and movement data analysis have received widespread attention in the fields of reliability management, indoor navigation, and crowd behavior monitoring. However, only a few indoor crowd movement trajectory datasets are available to the public, thus restricting the development of related research and application. This paper contributes a new benchmark dataset of indoor crowd movement trajectories. This dataset records the movements of over 5000 participants at a three day large academic conference in a two story indoor venue. The conference comprises varied activities, such as academic seminars, business exhibitions, a hacking contest, interviews, tea breaks, and a banquet. The participants are divided into seven types according to participation permission to the activities. Some of them are involved in anomalous events, such as loss of items, unauthorized accesses, and equipment failures, forming a variety of spatial temporal movement patterns. In this paper, we first introduce the scenario design, entity and behavior modeling, and data generator of the dataset. Then, a detailed ground truth of the dataset is presented. Finally, we describe the process and experience of applying the dataset to the contest of ChinaVis Data Challenge 2019. Evaluation results of the 75 contest entries and the feedback from 359 contestants demonstrate that the dataset has satisfactory completeness, and usability, and can effectively identify the performance of methods, technologies, and systems for indoor trajectory analysis.

cs.OH↗

arXiv2021

Accurately Quantifying Radiative Cooling Potentials: A Temperature-correction to the Transmittance-based approximation

Theoretical calculations of the cooling potential of radiative cooling materials are crucial for determining their cooling capability under different meteorological conditions and evaluating their performance. To enable these calculations, accurate models of long-wave infrared downwelling atmospheric irradiance are needed, However, the transmittance-based cosine approximation, which is widely used to determine radiative cooling potentials, does not account for the cooling potential arising from heat loss to the colder reaches of the atmosphere itself. Here, we show that use of the approximation can lead to > 10% underestimation of the cooling potential relative to MODTRAN 6 outputs. We propose a temperature correction to the transmittance-based approximation which accounts for heat loss to the cold upper atmosphere, and significantly reduces this underestimation, while retaining the advantages of the original model. In light of the widespread and continued use of the transmittance-based model, our results highlight an important source of potential errors and a means to correct for them.

physics.ao-ph↗

arXiv2021

Risk Conditioned Neural Motion Planning

Risk-bounded motion planning is an important yet difficult problem for safety-critical tasks. While existing mathematical programming methods offer theoretical guarantees in the context of constrained Markov decision processes, they either lack scalability in solving larger problems or produce conservative plans. Recent advances in deep reinforcement learning improve scalability by learning policy networks as function approximators. In this paper, we propose an extension of soft actor critic model to estimate the execution risk of a plan through a risk critic and produce risk-bounded policies efficiently by adding an extra risk term in the loss function of the policy network. We define the execution risk in an accurate form, as opposed to approximating it through a summation of immediate risks at each time step that leads to conservative plans. Our proposed model is conditioned on a continuous spectrum of risk bounds, allowing the user to adjust the risk-averse level of the agent on the fly. Through a set of experiments, we show the advantage of our model in terms of both computational time and plan quality, compared to a state-of-the-art mathematical programming baseline, and validate its performance in more complicated scenarios, including nonlinear dynamics and larger state space.

cs.LG↗

arXiv2021

Non-line-of-sight imaging with picosecond temporal resolution

Non-line-of-sight (NLOS) imaging enables monitoring around corners and is promising for diverse applications. The resolution of transient NLOS imaging is limited to a centimeter scale, mainly by the temporal resolution of the detectors. Here, we construct an up-conversion single-photon detector with a high temporal resolution of ~1.4 ps and a low noise count rate of 5 counts per second (cps). Notably, the detector operates at room temperature, near-infrared wavelength. Using this detector, we demonstrate high-resolution and low-noise NLOS imaging. Our system can provide a 180 μm axial resolution and a 2 mm lateral resolution, which is more than one order of magnitude better than that in previous experiments. These results open avenues for high-resolution NLOS imaging techniques in relevant applications.

physics.optics↗

arXiv2021

An Algorithmic Framework for Approximating Maximin Share Allocation of Chores

In this paper, we consider the problem of how to fairly dividing $m$ indivisible chores among $n$ agents. The fairness measure we considered here is the maximin share. The previous best known result is that there always exists a $\frac{4}{3}$ approximation maximin share allocation. With a novel algorithm, we can always find a $\frac{11}{9}$ approximation maximin share allocation for any instances. We also discuss how to improve the efficiency of the algorithm and its connection to the job scheduling problem.

cs.GT↗

arXiv2021

Butterfly-Core Community Search over Labeled Graphs

Community search aims at finding densely connected subgraphs for query vertices in a graph. While this task has been studied widely in the literature, most of the existing works only focus on finding homogeneous communities rather than heterogeneous communities with different labels. In this paper, we motivate a new problem of cross-group community search, namely Butterfly-Core Community (BCC), over a labeled graph, where each vertex has a label indicating its properties and an edge between two vertices indicates their cross relationship. Specifically, for two query vertices with different labels, we aim to find a densely connected cross community that contains two query vertices and consists of butterfly networks, where each wing of the butterflies is induced by a k-core search based on one query vertex and two wings are connected by these butterflies. Indeed, the BCC structure admits the structure cohesiveness and minimum diameter, and thus can effectively capture the heterogeneous and concise collaborative team. Moreover, we theoretically prove this problem is NP-hard and analyze its non-approximability. To efficiently tackle the problem, we develop a heuristic algorithm, which first finds a BCC containing the query vertices, then iteratively removes the farthest vertices to the query vertices from the graph. The algorithm can achieve a 2-approximation to the optimal solution. To further improve the efficiency, we design a butterfly-core index and develop a suite of efficient algorithms for butterfly-core identification and maintenance as vertices are eliminated. Extensive experiments on eight real-world networks and four novel case studies validate the effectiveness and efficiency of our algorithms.

cs.SI↗

arXiv2021

PP-YOLOv2: A Practical Object Detector

Being effective and efficient is essential to an object detector for practical use. To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged. This paper will analyze a collection of refinements and empirically evaluate their impact on the final model performance through incremental ablation study. Things we tried that didn't work will also be discussed. By combining multiple effective refinements, we boost PP-YOLO's performance from 45.9% mAP to 49.5% mAP on COCO2017 test-dev. Since a significant margin of performance has been made, we present PP-YOLOv2. In terms of speed, PP-YOLOv2 runs in 68.9FPS at 640x640 input size. Paddle inference engine with TensorRT, FP16-precision, and batch size = 1 further improves PP-YOLOv2's infer speed, which achieves 106.5 FPS. Such a performance surpasses existing object detectors with roughly the same amount of parameters (i.e., YOLOv4-CSP, YOLOv5l). Besides, PP-YOLOv2 with ResNet101 achieves 50.3% mAP on COCO2017 test-dev. Source code is at https://github.com/PaddlePaddle/PaddleDetection.

cs.CV↗

arXiv2021

CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy

Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems. Traditional confidence measures on predictions often ignore the way predicted trajectories affect downstream decisions for safe driving. In this paper, we propose a novel multi-task intent recognition neural network that predicts not only probabilistic driver trajectories, but also utility statistics associated with the predictions for a given downstream task. We establish a decision criterion for parallel autonomy that takes into account the role of driver trajectory prediction in real-time decision making by reasoning about estimated task-specific utility statistics. We further improve the robustness of our system by considering uncertainties in downstream planning tasks that may lead to unsafe decisions. We test our online system on a realistic urban driving dataset, and demonstrate its advantage in terms of recall and fall-out metrics compared to baseline methods, and demonstrate its effectiveness in intervention and warning use cases.

cs.RO↗

arXiv2021

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection

Label assignment has been widely studied in general object detection because of its great impact on detectors' performance. However, none of these works focus on label assignment in dense pedestrian detection. In this paper, we propose a simple yet effective assigning strategy called Loss-aware Label Assignment (LLA) to boost the performance of pedestrian detectors in crowd scenarios. LLA first calculates classification (cls) and regression (reg) losses between each anchor and ground-truth (GT) pair. A joint loss is then defined as the weighted summation of cls and reg losses as the assigning indicator. Finally, anchors with top K minimum joint losses for a certain GT box are assigned as its positive anchors. Anchors that are not assigned to any GT box are considered negative. Loss-aware label assignment is based on an observation that anchors with lower joint loss usually contain richer semantic information and thus can better represent their corresponding GT boxes. Experiments on CrowdHuman and CityPersons show that such a simple label assigning strategy can boost MR by 9.53% and 5.47% on two famous one-stage detectors - RetinaNet and FCOS, respectively, demonstrating the effectiveness of LLA.

cs.CV↗

arXiv2021

Single-photon imaging over 200 km

Long-range active imaging has widespread applications in remote sensing and target recognition. Single-photon light detection and ranging (lidar) has been shown to have high sensitivity and temporal resolution. On the application front, however, the operating range of practical single-photon lidar systems is limited to about tens of kilometers over the Earth's atmosphere, mainly due to the weak echo signal mixed with high background noise. Here, we present a compact coaxial single-photon lidar system capable of realizing 3D imaging at up to 201.5 km. It is achieved by using high-efficiency optical devices for collection and detection, and what we believe is a new noise-suppression technique that is efficient for long-range applications. We show that photon-efficient computational algorithms enable accurate 3D imaging over hundreds of kilometers with as few as 0.44 signal photons per pixel. The results represent a significant step toward practical, low-power lidar over extra-long ranges.

eess.IV↗

arXiv2021

A preconditioner based on sine transform for two-dimensional Riesz space factional diffusion equations in convex domains

In this paper, we develop a fast numerical method for solving the time-dependent Riesz space fractional diffusion equations with a nonlinear source term in the convex domain. An implicit finite difference method is employed to discretize the Riesz space fractional diffusion equations with a penalty term in a rectangular region by the volume-penalization approach. The stability and the convergence of the proposed method are studied. As the coefficient matrix is with the Toeplitz-like structure, the generalized minimum residual method with a preconditioner based on the sine transform is exploited to solve the discretized linear system, where the preconditioner is constructed in view of the combination of two approximate inverse $τ$ matrices, which can be diagonalized by the sine transform. The spectrum of the preconditioned matrix is also investigated. Numerical experiments are carried out to demonstrate the efficiency of the proposed method.

math.NA↗

arXiv2021

Smart Build Targets Batching Service at Google

Google has a monolithic codebase with tens of millions build targets. Each build target specifies the information that is needed to build a software artifact or run tests. It is common to execute a subset of build targets at each revision and make sure that the change does not break the codebase. Google's build service system uses Bazel to build targets. Bazel takes as input a build that specifies the execution context, flags and build targets to run. The outputs are the build libraries, binaries or test results. To be able to support developer's daily activities, the build service system runs millions of builds per day. It is a known issue that a build with many targets could run out of the allocated memory or exceed its execution deadline. This is problematic because it reduces the developer's productivity, e.g. code submissions or binary releases. In this paper, we propose a technique that predicts the memory usage and executor occupancy of a build. The technique batches a set of targets such that the build created with those targets does not run out of memory or exceed its deadline. This approach significantly reduces the number of builds that run out of memory or exceed the deadlines, hence improving developer's productivity.

cs.SE↗

arXiv2021

Using Machine Learning to Automate Mammogram Images Analysis

Breast cancer is the second leading cause of cancer-related death after lung cancer in women. Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate. However, a relatively high false positive rate and a low specificity in mammography technology still exist. In this work, a computer-aided automatic mammogram analysis system is proposed to process the mammogram images and automatically discriminate them as either normal or cancerous, consisting of three consecutive image processing, feature selection, and image classification stages. In designing the system, the discrete wavelet transforms (Daubechies 2, Daubechies 4, and Biorthogonal 6.8) and the Fourier cosine transform were first used to parse the mammogram images and extract statistical features. Then, an entropy-based feature selection method was implemented to reduce the number of features. Finally, different pattern recognition methods (including the Back-propagation Network, the Linear Discriminant Analysis, and the Naive Bayes Classifier) and a voting classification scheme were employed. The performance of each classification strategy was evaluated for sensitivity, specificity, and accuracy and for general performance using the Receiver Operating Curve. Our method is validated on the dataset from the Eastern Health in Newfoundland and Labrador of Canada. The experimental results demonstrated that the proposed automatic mammogram analysis system could effectively improve the classification performances.

eess.IV↗