Searcharxiv⌕ Search

arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,207 records · Page 67Linked to original sources
arXiv2021

Lorentzian Coxeter systems and Boyd-Maxwell ball packings

In the recent study of infinite root systems, fractal patterns of ball packings were observed while visualizing roots in affine space. In this paper, we show that the observed fractals are exactly the ball packings described by Boyd and Maxwell. This correspondence is a corollary of a more fundamental result: Given a geometric representation of a Coxeter group in a Lorentz space, the set of limit directions of weights equals the set of limit roots. Additionally, we use Coxeter complexes to describe tangency graphs of the corresponding Boyd--Maxwell ball packings. Finally, we enumerate all the Coxeter systems that generate Boyd-Maxwell ball packings.

math.GR↗
arXiv2021

Adversarial Neural Trip Recommendation

Trip recommender system, which targets at recommending a trip consisting of several ordered Points of Interest (POIs), has long been treated as an important application for many location-based services. Currently, most prior arts generate trips following pre-defined objectives based on constraint programming, which may fail to reflect the complex latent patterns hidden in the human mobility data. And most of these methods are usually difficult to respond in real time when the number of POIs is large. To that end, we propose an Adversarial Neural Trip Recommendation (ANT) framework to tackle the above challenges. First of all, we devise a novel attention-based encoder-decoder trip generator that can learn the correlations among POIs and generate well-designed trips under given constraints. Another novelty of ANT relies on an adversarial learning strategy integrating with reinforcement learning to guide the trip generator to produce high-quality trips. For this purpose, we introduce a discriminator, which distinguishes the generated trips from real-life trips taken by users, to provide reward signals to optimize the generator. Moreover, we devise a novel pre-train schema based on learning from demonstration, which speeds up the convergence to achieve a sufficient-and-efficient training process. Extensive experiments on four real-world datasets validate the effectiveness and efficiency of our proposed ANT framework, which demonstrates that ANT could remarkably outperform the state-of-the-art baselines with short response time.

cs.LG↗
arXiv2021

Chiral Phonons in Chiral Materials

The concept of chirality makes ubiquitous appearance in nature. Particularly, both a structure and its collective excitations may acquire well defined chiralities. In this work, we reveal an intrinsic connection between the chiralities of a crystal structure and its phonon excitations. We show that the phonon chirality and its propagation direction are strongly coupled with the lattice chirality, which will be reversed when a chiral lattice is switched to its enantiomorph. In addition, distinct from achiral lattices, propagating chiral phonons exist for chiral crystals also on the principal axis through the $Γ$ point, which strengthens its relevance to various physical processes. We demonstrate our theory with a 1D helix-chain model and with a concrete and important 3D material, the $α$-quartz. We predict a chirality diode effect in these systems, namely, at certain frequency window, a chiral signal can only pass the system in one way but not the other, specified by the system chirality. Experimental setups to test our theory are proposed. Our work discovers fundamental physics of chirality coupling between different levels of a system, and the predicted effects will provide a new way to control thermal transport and design information devices.

cond-mat.mtrl-sci↗
arXiv2021

X_1(2900) as a D_1 K molecule

The analyses of the LHCb data on X(2900) in the D^- K^+ spectrum are performed. Both dynamically generated and explicitly introduced X_1(2900) are considered. The results show that both these two approaches support the interpretation of X_1(2900) as a bar{D}_1 K molecular state, with J^{P}=1^- and an iso-singlet interpretation is much more favorable. The effect of triangle singularity on the production of X_1(2900) is also discussed, and it is found that it cannot be interpreted as a pure triangle cusp.

hep-ph↗
arXiv2021

Asymptotic distribution-free change-point detection for data with repeated observations

In the regime of change-point detection, a nonparametric framework based on scan statistics utilizing graphs representing similarities among observations is gaining attention due to its flexibility and good performances for high-dimensional and non-Euclidean data sequences, which are ubiquitous in this big data era. However, this graph-based framework encounters problems when there are repeated observations in the sequence, which often happens for discrete data, such as network data. In this work, we extend the graph-based framework to solve this problem by averaging or taking union of all possible optimal graphs resulted from repeated observations. We consider both the single change-point alternative and the changed-interval alternative, and derive analytic formulas to control the type I error for the new methods, making them fast applicable to large datasets. The extended methods are illustrated on an application in detecting changes in a sequence of dynamic networks over time. All proposed methods are implemented in an R package gSeg available on CRAN.

stat.ME↗
arXiv2021

Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning

Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome. For example, attackers attempt to poison the model by either presenting inaccurate misrepresentative data or altering the models' parameters. In addition, Byzantine faults including software, hardware, network issues occur in distributed systems which also lead to a negative impact on the prediction outcome. In this paper, we propose a novel distributed training algorithm, partial synchronous stochastic gradient descent (ParSGD), which defends adversarial attacks and/or tolerates Byzantine faults. We demonstrate the effectiveness of our algorithm under three common adversarial attacks again the ML models and a Byzantine fault during the training phase. Our results show that using ParSGD, ML models can still produce accurate predictions as if it is not being attacked nor having failures at all when almost half of the nodes are being compromised or failed. We will report the experimental evaluations of ParSGD in comparison with other algorithms.

cs.CR↗
arXiv2021

Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection

This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based on two motivations: 1) the estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation; and 2) the joint alignment of distributions for inputs (feature alignment) and outputs (self-training) is needed. To this end, we compose a Bayesian CNN-based framework for uncertainty estimation in object detection, and propose an algorithm for generation of uncertainty-aware pseudo-labels. We also devise a scheme for joint feature alignment and self-training of the object detection model with uncertainty-aware pseudo-labels. Experiments on multiple cross-domain object detection benchmarks show that our proposed method achieves state-of-the-art performance.

cs.CV↗
arXiv2021

ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification

Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised representation learning. The main idea of instance contrastive learning is to match a same instance in different augmented views. However, the relationship between different instances has not been fully explored in previous contrastive methods, especially for instance-level contrastive loss. To address this issue, we propose Inter-instance Contrastive Encoding (ICE) that leverages inter-instance pairwise similarity scores to boost previous class-level contrastive ReID methods. We first use pairwise similarity ranking as one-hot hard pseudo labels for hard instance contrast, which aims at reducing intra-class variance. Then, we use similarity scores as soft pseudo labels to enhance the consistency between augmented and original views, which makes our model more robust to augmentation perturbations. Experiments on several large-scale person ReID datasets validate the effectiveness of our proposed unsupervised method ICE, which is competitive with even supervised methods. Code is made available at https://github.com/chenhao2345/ICE.

cs.CV↗
arXiv2021

Structure Parameter Optimized Kernel Based Online Prediction with a Generalized Optimization Strategy for Nonstationary Time Series

In this paper, sparsification techniques aided online prediction algorithms in a reproducing kernel Hilbert space are studied for nonstationary time series. The online prediction algorithms as usual consist of the selection of kernel structure parameters and the kernel weight vector updating. For structure parameters, the kernel dictionary is selected by some sparsification techniques with online selective modeling criteria, and moreover the kernel covariance matrix is intermittently optimized in the light of the covariance matrix adaptation evolution strategy (CMA-ES). Optimizing the real symmetric covariance matrix can not only improve the kernel structure's flexibility by the cross relatedness of the input variables, but also partly alleviate the prediction uncertainty caused by the kernel dictionary selection for nonstationary time series. In order to sufficiently capture the underlying dynamic characteristics in prediction-error time series, a generalized optimization strategy is designed to construct the kernel dictionary sequentially in multiple kernel connection modes. The generalized optimization strategy provides a more self-contained way to construct the entire kernel connections, which enhances the ability to adaptively track the changing dynamic characteristics. Numerical simulations have demonstrated that the proposed approach has superior prediction performance for nonstationary time series.

eess.SP↗
arXiv2021

NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications

We propose a new general Graph Adversarial Domain Adaptation (GADA) based on semantic knowledge reasoning of class structure for solving the problem of unsupervised domain adaptation (UDA) from the big data with non-shared and imbalanced classes to specified small and imbalanced applications (NI-UDA), where non-shared classes mean the label space out of the target domain. Our goal is to leverage priori hierarchy knowledge to enhance domain adversarial aligned feature representation with graph reasoning. In this paper, to address two challenges in NI-UDA, we equip adversarial domain adaptation with Hierarchy Graph Reasoning (HGR) layer and the Source Classifier Filter (SCF). For sparse classes transfer challenge, our HGR layer can aggregate local feature to hierarchy graph nodes by node prediction and enhance domain adversarial aligned feature with hierarchy graph reasoning for sparse classes. Our HGR contributes to learn direct semantic patterns for sparse classes by hierarchy attention in self-attention, non-linear mapping and graph normalization. our SCF is proposed for the challenge of knowledge sharing from non-shared data without negative transfer effect by filtering low-confidence non-shared data in HGR layer. Experiments on two benchmark datasets show our GADA methods consistently improve the state-of-the-art adversarial UDA algorithms, e.g. GADA(HGR) can greatly improve f1 of the MDD by \textbf{7.19\%} and GVB-GD by \textbf{7.89\%} respectively on imbalanced source task in Meal300 dataset. The code is available at https://gadatransfer.wixsite.com/gada.

cs.CV↗
arXiv2021

Estimating Linear Mixed Effects Models with Truncated Normally Distributed Random Effects

Linear Mixed Effects (LME) models have been widely applied in clustered data analysis in many areas including marketing research, clinical trials, and biomedical studies. Inference can be conducted using maximum likelihood approach if assuming Normal distributions on the random effects. However, in many applications of economy, business and medicine, it is often essential to impose constraints on the regression parameters after taking their real-world interpretations into account. Therefore, in this paper we extend the classical (unconstrained) LME models to allow for sign constraints on its overall coefficients. We propose to assume a symmetric doubly truncated Normal (SDTN) distribution on the random effects instead of the unconstrained Normal distribution which is often found in classical literature. With the aforementioned change, difficulty has dramatically increased as the exact distribution of the dependent variable becomes analytically intractable. We then develop likelihood-based approaches to estimate the unknown model parameters utilizing the approximation of its exact distribution. Simulation studies have shown that the proposed constrained model not only improves real-world interpretations of results, but also achieves satisfactory performance on model fits as compared to the existing model.

stat.ME↗
arXiv2021

Selective Feature Compression for Efficient Activity Recognition Inference

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference efficiency of current action recognition backbones on trimmed videos, and illustrate that one action model can also cover then informative region by dropping non-informative features. We present Selective Feature Compression (SFC), an action recognition inference strategy that greatly increase model inference efficiency without any accuracy compromise. Differently from previous works that compress kernel sizes and decrease the channel dimension, we propose to compress feature flow at spatio-temporal dimension without changing any backbone parameters. Our experiments on Kinetics-400, UCF101 and ActivityNet show that SFC is able to reduce inference speed by 6-7x and memory usage by 5-6x compared with the commonly used 30 crops dense sampling procedure, while also slightly improving Top1 Accuracy. We thoroughly quantitatively and qualitatively evaluate SFC and all its components and show how does SFC learn to attend to important video regions and to drop temporal features that are uninformative for the task of action recognition.

cs.CV↗
arXiv2021

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

End-to-end text-spotting, which aims to integrate detection and recognition in a unified framework, has attracted increasing attention due to its simplicity of the two complimentary tasks. It remains an open problem especially when processing arbitrarily-shaped text instances. Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output. Here, we tackle end-to-end text spotting by presenting Adaptive Bezier Curve Network v2 (ABCNet v2). Our main contributions are four-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve, which, compared with segmentation-based methods, can not only provide structured output but also controllable representation. 2) We design a novel BezierAlign layer for extracting accurate convolution features of a text instance of arbitrary shapes, significantly improving the precision of recognition over previous methods. 3) Different from previous methods, which often suffer from complex post-processing and sensitive hyper-parameters, our ABCNet v2 maintains a simple pipeline with the only post-processing non-maximum suppression (NMS). 4) As the performance of text recognition closely depends on feature alignment, ABCNet v2 further adopts a simple yet effective coordinate convolution to encode the position of the convolutional filters, which leads to a considerable improvement with negligible computation overhead. Comprehensive experiments conducted on various bilingual (English and Chinese) benchmark datasets demonstrate that ABCNet v2 can achieve state-of-the-art performance while maintaining very high efficiency.

cs.CV↗
arXiv2021

Evaluating Performance and Gameplay of Virtual Reality Sickness Techniques in a First-Person Shooter Game

In virtual reality (VR) games, playability and immersion levels are important because they affect gameplay, enjoyment, and performance. However, they can be adversely affected by VR sickness (VRS) symptoms. VRS can be minimized by manipulating users' perception of the virtual environment via the head-mounted display (HMD). One extreme example is the Teleport mitigation technique, which lets users navigate discretely, skipping sections of the virtual space. Other techniques are less extreme but still rely on controlling what and how much users see via the HMD. This research examines the effect on players' performance and gameplay of these mitigation techniques in fast-paced VR games. Our focus is on two types of visual reduction techniques. This study aims to identify specifically the trade-offs these techniques have in a first-person shooter game regarding immersion, performance, and VRS. The main contributions in this paper are (1) a deeper understanding of one of the most popular techniques (Teleport) when it comes to gameplay; (2) the replication and validation of a novel VRS mitigation technique based on visual reduction; and (3) a comparison of their effect on players' performance and gameplay.

cs.HC↗
arXiv2021

MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition

As an essential element for the diagnosis and rehabilitation of psychiatric disorders, the electroencephalogram (EEG) based emotion recognition has achieved significant progress due to its high precision and reliability. However, one obstacle to practicality lies in the variability between subjects and sessions. Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation. We therefore propose the multi-source marginal distribution adaptation (MS-MDA) for EEG emotion recognition, which takes both domain-invariant and domain-specific features into consideration. First, we assume that different EEG data share the same low-level features, then we construct independent branches for multiple EEG data source domains to adopt one-to-one domain adaptation and extract domain-specific features. Finally, the inference is made by multiple branches. We evaluate our method on SEED and SEED-IV for recognizing three and four emotions, respectively. Experimental results show that the MS-MDA outperforms the comparison methods and state-of-the-art models in cross-session and cross-subject transfer scenarios in our settings. Codes at https://github.com/VoiceBeer/MS-MDA.

cs.LG↗
arXiv2021

Geographical Knowledge-driven Representation Learning for Remote Sensing Images

The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images. However, due to human and material resource constraints, the vast majority of remote sensing images remain unlabeled. As a result, it cannot be applied to currently available deep learning methods. To fully utilize the remaining unlabeled images, we propose a Geographical Knowledge-driven Representation learning method for remote sensing images (GeoKR), improving network performance and reduce the demand for annotated data. The global land cover products and geographical location associated with each remote sensing image are regarded as geographical knowledge to provide supervision for representation learning and network pre-training. An efficient pre-training framework is proposed to eliminate the supervision noises caused by imaging times and resolutions difference between remote sensing images and geographical knowledge. A large scale pre-training dataset Levir-KR is proposed to support network pre-training. It contains 1,431,950 remote sensing images from Gaofen series satellites with various resolutions. Experimental results demonstrate that our proposed method outperforms ImageNet pre-training and self-supervised representation learning methods and significantly reduces the burden of data annotation on downstream tasks such as scene classification, semantic segmentation, object detection, and cloud / snow detection. It demonstrates that our proposed method can be used as a novel paradigm for pre-training neural networks. Codes will be available on https://github.com/flyakon/Geographical-Knowledge-driven-Representaion-Learning.

cs.CV↗