arXiv subjects

Cheng Zhang

Publications and source records attributed to Cheng Zhang.

At least 379 records · Page 21Linked to original sources

arXiv2021

ThumbTrak: Recognizing Micro-finger Poses Using a Ring with Proximity Sensing

ThumbTrak is a novel wearable input device that recognizes 12 micro-finger poses in real-time. Poses are characterized by the thumb touching each of the 12 phalanges on the hand. It uses a thumb-ring, built with a flexible printed circuit board, which hosts nine proximity sensors. Each sensor measures the distance from the thumb to various parts of the palm or other fingers. ThumbTrak uses a support-vector-machine (SVM) model to classify finger poses based on distance measurements in real-time. A user study with ten participants showed that ThumbTrak could recognize 12 micro finger poses with an average accuracy of 93.6%. We also discuss potential opportunities and challenges in applying ThumbTrak in real-world applications.

cs.HC↗

arXiv2021

Classification of integrable boundary equations for integrable quad-graph systems

In the context of integrable systems on quad-graphs, the boundary consistency around a half of a rhombic dodecahedron, as a companion notion to the three-dimensional consistency around a cube, was introduced as a criterion for defining integrable boundary conditions for quad-graph systems with a boundary. In this paper, we formalize the notions of boundary equations as boundary conditions for quad-graph systems, and provide a systematic method for solving the boundary consistency, which results in a classification of integrable boundary equations for quad-graph equations in the Adler-Bobenko-Suris classification. This relies on factorizing, first the quad-graph equations into pairs of dual boundary equations, and then the consistency on a rhombic dodecahedron into two equivalent boundary consistencies. Generalizations of the method to rhombic-symmetric equations are also considered.

nlin.SI↗

arXiv2021

Theoretical study on hot-carrier generation, transport and injection in TiN/TiO$_2$ junction

Promoting performance of generation, transport and injection of hot carriers in metal/semiconductor junctions is critical for harvesting energy of hot carriers. However, the injection efficiency of hot carriers in the commonly used noble metals such as Au is extremely low, which hinders the hot carrier-based applications. Here, we predict that the plasmonic material TiN might be promising for generating, transporting and injecting hot carriers, based on first-principles calculations and Monte Carlo simulations. We found that the hot-carrier generation rate in TiN is significantly large compared to Au. The transport property of hot carriers in TiN is excellent, due to the long lifetime and mean free path. The TiN/TiO2 junction possesses very low Schottky barrier, which results in much larger injection efficiency than that in the Au/TiO2 junction. Furthermore, it is revealed that the optimal injection efficiency could be achieved in a core/shell cylindrical TiN/TiO2 junction. Our findings provide an in-depth understanding of hot-carrier generation, transport and injection, and hence are helpful for the development of hot carrier-based devices.

cond-mat.mtrl-sci↗

arXiv2021

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or re-weighting. In this paper, we investigate a largely overlooked approach -- post-processing calibration of confidence scores. We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size. We show that separately handling the background class and normalizing the scores over classes for each proposal are keys to achieving superior performance. On the LVIS dataset, NorCal can effectively improve nearly all the baseline models not only on rare classes but also on common and frequent classes. Finally, we conduct extensive analysis and ablation studies to offer insights into various modeling choices and mechanisms of our approach. Our code is publicly available at https://github.com/tydpan/NorCal/.

cs.CV↗

arXiv2021

Plastic Laminate Antireflective Coatings for Millimeter-wave Optics in BICEP Array

The BICEP/Keck series of experiments target the Cosmic Microwave Background at degree-scale resolution from the South Pole. Over the next few years, the "Stage-3" BICEP Array (BA) telescope will improve the program's frequency coverage and sensitivity to primordial B-mode polarization by an order of magnitude. The first receiver in the array, BA1, began observing at 30/40 GHz in early 2020. The next two receivers, BA2 and BA3, are currently being assembled and will map the southern sky at frequencies ranging from 95 GHz to 150 GHz. Common to all BA receivers is a refractive, on-axis, cryogenic optical design that focuses microwave radiation onto a focal plane populated with antenna-coupled bolometers. High-performance antireflective coatings up to 760 mm in aperture are needed for each element in the optical chain, and must withstand repeated thermal cycles down to 4 K. Here we present the design and fabrication of the 30/40 GHz anti-reflection coatings for the recently deployed BA1 receiver, then discuss laboratory measurements of their reflectance. We review the lamination method for these single- and dual-layer plastic coatings with indices matched to various polyethylene, nylon and alumina optics. We also describe ongoing efforts to optimize coatings for the next BA cryostats, which may inform technological choices for future Small-Aperture Telescopes of the CMB "Stage 4" experiment.

astro-ph.IM↗

arXiv2021

Sparse Uncertainty Representation in Deep Learning with Inducing Weights

Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning. Yet these approaches struggle to scale mainly due to memory inefficiency issues, since they require parameter storage several times higher than their deterministic counterparts. To address this, we augment the weight matrix of each layer with a small number of inducing weights, thereby projecting the uncertainty quantification into such low dimensional spaces. We further extend Matheron's conditional Gaussian sampling rule to enable fast weight sampling, which enables our inference method to maintain reasonable run-time as compared with ensembles. Importantly, our approach achieves competitive performance to the state-of-the-art in prediction and uncertainty estimation tasks with fully connected neural networks and ResNets, while reducing the parameter size to $\leq 24.3\%$ of that of a $single$ neural network.

stat.ML↗

arXiv2021

Smart Flood Resilience: Harnessing Community-Scale Big Data for Predictive Flood Risk Monitoring, Rapid Impact Assessment, and Situational Awareness

Smart resilience is the beneficial result of the collision course of the fields of data science and urban resilience to flooding. The objective of this study is to propose and demonstrate a smart flood resilience framework that leverages heterogeneous community-scale big data and infrastructure sensor data to enhance predictive risk monitoring and situational awareness. The smart flood resilience framework focuses on four core capabilities that could be augmented by the use of heterogeneous community-scale big data and analytics techniques: (1) predictive flood risk mapping; (2) automated rapid impact assessment; (3) predictive infrastructure failure prediction and monitoring; and (4) smart situational awareness capabilities. We demonstrate the components of these core capabilities of the smart flood resilience framework in the context of the 2017 Hurricane Harvey in Harris County, Texas. First, we demonstrate the use of flood sensors for the prediction of floodwater overflow in channel networks and inundation of co-located road networks. Second, we discuss the use of social media and machine learning techniques for assessing the impacts of floods on communities and sensing emotion signals to examine societal impacts. Third, we illustrate the use of high-resolution traffic data in network-theoretic models for nowcasting of flood propagation on road networks and the disrupted access to critical facilities, such as hospitals. Fourth, we leverage location-based and credit card transaction data in spatial analyses to proactively evaluate the recovery of communities and the impacts of floods on businesses. These analyses show that the significance of core capabilities of the smart flood resilience framework in helping emergency managers, city planners, public officials, responders, and volunteers to better cope with the impacts of catastrophic flooding events.

physics.soc-ph↗

arXiv2021

Layer-controlled Ferromagnetism in Atomically Thin CrSiTe$_3$ Flakes

The research on two-dimensional (2D) van der Waals (vdW) ferromagnets has promoted the development of ultrahigh-density and nanoscale data storage. However, intrinsic ferromagnetism in layered magnets is always subject to many factors, such as stacking orders, interlayer couplings, and the number of layers. Here, we report a magnetic transition from soft to hard ferromagnetic behaviors as the thickness of CrSiTe$_3$ flakes decreases down to several nanometers. Phenomenally, in contrast to the negligible hysteresis loop in the bulk counterparts, atomically thin CrSiTe$_3$ shows a rectangular loop with finite magnetization and coercivity as thickness decreases down to ~8 nm, indicative of a single-domain and out-of-plane ferromagnetic order. We find that the stray field is weakened with decreasing thickness, which suppresses the formation of the domain wall. In addition, thickness-dependent ferromagnetic properties also reveal a crossover from 3 dimensional to 2 dimensional Ising ferromagnets at a ~7 nm thickness of CrSiTe$_3$, accompanied by a drop of the Curie temperature from 33 K for bulk to ~17 K for 4 nm sample.

cond-mat.mtrl-sci↗

arXiv2021

Identifiable Generative Models for Missing Not at Random Data Imputation

Real-world datasets often have missing values associated with complex generative processes, where the cause of the missingness may not be fully observed. This is known as missing not at random (MNAR) data. However, many imputation methods do not take into account the missingness mechanism, resulting in biased imputation values when MNAR data is present. Although there are a few methods that have considered the MNAR scenario, their model's identifiability under MNAR is generally not guaranteed. That is, model parameters can not be uniquely determined even with infinite data samples, hence the imputation results given by such models can still be biased. This issue is especially overlooked by many modern deep generative models. In this work, we fill in this gap by systematically analyzing the identifiability of generative models under MNAR. Furthermore, we propose a practical deep generative model which can provide identifiability guarantees under mild assumptions, for a wide range of MNAR mechanisms. Our method demonstrates a clear advantage for tasks on both synthetic data and multiple real-world scenarios with MNAR data.

cs.LG↗

arXiv2021

Meta Sequence Learning for Generating Adequate Question-Answer Pairs

Creating multiple-choice questions to assess reading comprehension of a given article involves generating question-answer pairs (QAPs) on the main points of the document. We present a learning scheme to generate adequate QAPs via meta-sequence representations of sentences. A meta sequence is a sequence of vectors comprising semantic and syntactic tags. In particular, we devise a scheme called MetaQA to learn meta sequences from training data to form pairs of a meta sequence for a declarative sentence (MD) and a corresponding interrogative sentence (MIs). On a given declarative sentence, a trained MetaQA model converts it to a meta sequence, finds a matched MD, and uses the corresponding MIs and the input sentence to generate QAPs. We implement MetaQA for the English language using semantic-role labeling, part-of-speech tagging, and named-entity recognition, and show that trained on a small dataset, MetaQA generates efficiently over the official SAT practice reading tests a large number of syntactically and semantically correct QAPs with over 97\% accuracy.

cs.CL↗

arXiv2021

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

Many objects do not appear frequently enough in complex scenes (e.g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e.g., in product images). Yet, these object-centric images are not effectively leveraged for improving object detection in scene-centric images. In this paper, we propose Mosaic of Object-centric images as Scene-centric images (MosaicOS), a simple and novel framework that is surprisingly effective at tackling the challenges of long-tailed object detection. Keys to our approach are three-fold: (i) pseudo scene-centric image construction from object-centric images for mitigating domain differences, (ii) high-quality bounding box imputation using the object-centric images' class labels, and (iii) a multi-stage training procedure. On LVIS object detection (and instance segmentation), MosaicOS leads to a massive 60% (and 23%) relative improvement in average precision for rare object categories. We also show that our framework can be compatibly used with other existing approaches to achieve even further gains. Our pre-trained models are publicly available at https://github.com/czhang0528/MosaicOS/.

cs.CV↗

arXiv2021

DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions

Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed. Violation of any of these assumptions leads to significant error in the effect estimate. However, unlike cross-validation for predictive models, there is no global validator method for a causal estimate. As a result, expressing different causal assumptions formally and validating them (to the extent possible) becomes critical for any analysis. We present DoWhy, a framework that allows explicit declaration of assumptions through a causal graph and provides multiple validation tests to check a subset of these assumptions. Our experience with DoWhy highlights a number of open questions for future research: developing new ways beyond causal graphs to express assumptions, the role of causal discovery in learning relevant parts of the graph, and developing validation tests that can better detect errors, both for average and conditional treatment effects. DoWhy is available at https://github.com/microsoft/dowhy.

cs.LG↗

arXiv2021

DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization

Panorama images have a much larger field-of-view thus naturally encode enriched scene context information compared to standard perspective images, which however is not well exploited in the previous scene understanding methods. In this paper, we propose a novel method for panoramic 3D scene understanding which recovers the 3D room layout and the shape, pose, position, and semantic category for each object from a single full-view panorama image. In order to fully utilize the rich context information, we design a novel graph neural network based context model to predict the relationship among objects and room layout, and a differentiable relationship-based optimization module to optimize object arrangement with well-designed objective functions on-the-fly. Realizing the existing data are either with incomplete ground truth or overly-simplified scene, we present a new synthetic dataset with good diversity in room layout and furniture placement, and realistic image quality for total panoramic 3D scene understanding. Experiments demonstrate that our method outperforms existing methods on panoramic scene understanding in terms of both geometry accuracy and object arrangement. Code is available at https://chengzhag.github.io/publication/dpc.

cs.CV↗

arXiv2021

Holistic 3D Scene Understanding from a Single Image with Implicit Representation

We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate estimation of both shapes and layout especially for the cluttered scene due to the heavy occlusion between objects. We propose to utilize the latest deep implicit representation to solve this challenge. We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features. A novel physical violation loss is also proposed to avoid incorrect context between objects. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of object shape, scene layout estimation, and 3D object detection.

cs.CV↗

arXiv2021

Toward Integrated Human-machine Intelligence for Civil Engineering: An Interdisciplinary Perspective

The purpose of this paper is to examine the opportunities and barriers of Integrated Human-Machine Intelligence (IHMI) in civil engineering. Integrating artificial intelligence's high efficiency and repeatability with humans' adaptability in various contexts can advance timely and reliable decision-making during civil engineering projects and emergencies. Successful cases in other domains, such as biomedical science, healthcare, and transportation, showed the potential of IHMI in data-driven, knowledge-based decision-making in numerous civil engineering applications. However, whether the industry and academia are ready to embrace the era of IHMI and maximize its benefit to the industry is still questionable due to several knowledge gaps. This paper thus calls for future studies in exploring the value, method, and challenges of applying IHMI in civil engineering. Our systematic review of the literature and motivating cases has identified four knowledge gaps in achieving effective IHMI in civil engineering. First, it is unknown what types of tasks in the civil engineering domain can be assisted by AI and to what extent. Second, the interface between human and AI in civil engineering-related tasks need more precise and formal definition. Third, the barriers that impede collecting detailed behavioral data from humans and contextual environments deserve systematic classification and prototyping. Lastly, it is unknown what expected and unexpected impacts will IHMI have on the AEC industry and entrepreneurship. Analyzing these knowledge gaps led to a list of identified research questions. This paper will lay the foundation for identifying relevant studies to form a research roadmap to address the four knowledge gaps identified.

cs.AI↗

arXiv2021

Countering Adversarial Examples: Combining Input Transformation and Noisy Training

Recent studies have shown that neural network (NN) based image classifiers are highly vulnerable to adversarial examples, which poses a threat to security-sensitive image recognition task. Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent. But, as the compression ratio increases, traditional JPEG compression is insufficient to defend those attacks but can cause an abrupt accuracy decline to the benign images. In this paper, with the aim of fully filtering the adversarial perturbations, we firstly make modifications to traditional JPEG compression algorithm which becomes more favorable for NN. Specifically, based on an analysis of the frequency coefficient, we design a NN-favored quantization table for compression. Considering compression as a data augmentation strategy, we then combine our model-agnostic preprocess with noisy training. We fine-tune the pre-trained model by training with images encoded at different compression levels, thus generating multiple classifiers. Finally, since lower (higher) compression ratio can remove both perturbations and original features slightly (aggressively), we use these trained multiple models for model ensemble. The majority vote of the ensemble of models is adopted as final predictions. Experiments results show our method can improve defense efficiency while maintaining original accuracy.

cs.CV↗

arXiv2021

Meta-Learning Divergences of Variational Inference

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability. Crucial to the performance of VI is the selection of the associated divergence measure, as VI approximates the intractable distribution by minimizing this divergence. In this paper we propose a meta-learning algorithm to learn the divergence metric suited for the task of interest, automating the design of VI methods. In addition, we learn the initialization of the variational parameters without additional cost when our method is deployed in the few-shot learning scenarios. We demonstrate our approach outperforms standard VI on Gaussian mixture distribution approximation, Bayesian neural network regression, image generation with variational autoencoders and recommender systems with a partial variational autoencoder.

cs.LG↗

arXiv2021

On an inverse scattering transform for the nonlinear Schödinger equation on the half-line

In this paper, we develop an inverse scattering transform for the integrable focusing nonlinear Schrödinger (NLS) equation on the half-line subject to a class of boundary conditions. The method is based on the notions of integrable boundary conditions and double-row monodromy matrix, developed by Sklyanin, which characterize initial-boundary value problems for NLS on an interval. It follows from Sklyanin's approach that a hierarchy of integrable boundary conditions can be derived based on a semi-discrete type Lax pair involving the time-part Lax matrix of NLS and a reflection matrix. The inverse scattering transform relies on the formulation of a scattering system for the double-row monodromy matrix characterizing an interval problem. The scattering system for the half-line problem for NLS is obtained by extending one endpoint of the interval to infinity. Then, we derive spectral and analytic properties of the scattering systems, and set up the inverse part using a Riemann-Hilbert formulation. We also show that our approach is equivalent to a nonlinear method of reflection by extending the initial-boundary value problem on the half-line to an initial value on the whole axis. Explicit examples of soliton solutions on the half-line are provided. Although we only consider the NLS model as a particular example, the method we present in this paper can be readily applied to a wide range of integrable PDEs on the half-line.

nlin.SI↗