arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 631 records · Page 35Linked to original sources

arXiv2021

Optimal Classification for Functional Data

A central topic in functional data analysis is how to design an optimaldecision rule, based on training samples, to classify a data function. We exploit the optimal classification problem when data functions are Gaussian processes. Sharp nonasymptotic convergence rates for minimax excess mis-classification risk are derived in both settings that data functions are fully observed and discretely observed. We explore two easily implementable classifiers based on discriminant analysis and deep neural network, respectively, which are both proven to achieve optimality in Gaussian setting. Our deepneural network classifier is new in literature which demonstrates outstanding performance even when data functions are non-Gaussian. In case of discretely observed data, we discover a novel critical sampling frequency thatgoverns the sharp convergence rates. The proposed classifiers perform favorably in finite-sample applications, as we demonstrate through comparisonswith other functional classifiers in simulations and one real data application.

stat.ME↗

arXiv2021

Coherent spin rotation-induced zero thermal expansion in MnCoSi-based spiral magnets

Materials exhibiting zero thermal expansion (ZTE), namely, volume invariance during temperature change, can resist thermal shock and are highly desired in modern industries as high-precision components. However, pure ZTE materials are rare, especially those that are metallic. Here, we report the discovery of a pure metallic ZTE material: an orthorhombic Mn1-xNixCoSi spiral magnet. The introduction of Ni can efficiently enhance the ferromagnetic exchange interaction and construct the transition from a spiral magnetic state to a ferromagnetic-like state in MnCoSi-based alloys. Systematic in situ neutron powder diffraction revealed a new cycloidal spiral magnetic structure in bc plane at ground state which would transform to the helical spiral in the ab plane with increasing temperature. Combined with Lorentz transmission electron microscopy techniques, the cycloidal and helical spin order coherently rotated at varying periods along the c axis during the magnetic transition. This spin rotation drove the continuous movement of the coupled crystalline lattice and induced a large negative thermal expansion along the a axis, eventually leading to a wide-temperature ZTE effect. Our work not only introduces a new ZTE alloy but also presents a new mechanism by which to discover or design ZTE magnets.

cond-mat.mtrl-sci↗

arXiv2021

Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation

Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event and the clinical decision of treatment planning. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features. In this paper, we propose a novel domain adaptation (DA) method with two components to address these problems. The first component is a stochastic class-balanced boosting sampling strategy that overcomes the imbalanced learning problem and improves the classification performance on poorly-predicted classes. The second component is a representation learning that guarantees three properties: 1) domain-transferability by prototype triplet loss, 2) discriminant by conditional maximum mean discrepancy loss, and 3) completeness by multi-view reconstruction loss. Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i.e., class centers) in a hyper-sphere manifold. Experiments on cross-site severity assessment of COVID-19 from CT images show that the proposed method can effectively tackle the imbalanced learning problem and outperform recent DA approaches.

eess.IV↗

arXiv2021

RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

Segmenting each moving object instance in a scene is essential for many applications. But like many other computer vision tasks, this task performs well in optimal weather, but then adverse weather tends to fail. To be robust in weather conditions, the usual way is to train network in data of given weather pattern or to fuse multiple sensors. We focus on a new possibility, that is, to improve its resilience to weather interference through the network's structural design. First, we propose a novel FPN structure called RiWFPN with a progressive top-down interaction and attention refinement module. RiWFPN can directly replace other FPN structures to improve the robustness of the network in non-optimal weather conditions. Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet. Finally, in order to verify the effect of moving instance segmentation in different weather disturbances, we propose a VKTTI-moving dataset which is a moving instance segmentation dataset based on the VKTTI dataset, taking into account different weather scenes such as rain, fog, sunset, morning as well as overcast. The experiment proves how RiWFPN improves the network's resilience to adverse weather effects compared to other FPN structures. We compare RiWNet to several other state-of-the-art methods in some challenging datasets, and RiWNet shows better performance especially under adverse weather conditions.

cs.CV↗

arXiv2021

Learning Inner-Group Relations on Point Clouds

The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.

cs.CV↗

arXiv2021

Intra-Day Variability Observations of Two Dozens of Blazars at 4.8 GHz

Two dozens of radio loud active galactic nuclei (AGNs) have been observed with Urumqi 25 m radio telescope in order to search for intra-day variability (IDV). The target sources are blazars (namely flat spectrum radio quasars and BL Lac objects) which are mostly selected from the observing list of RadioAstron AGN monitoring campaigns. The observations were carried out at 4.8 GHz in two sessions of 8-12 February 2014 and 7-9 March respectively. We report the data reduction and the first results of observations. The results show that the majority of the blazars exhibit IDV in 99.9% confidence level, some of them show quite strong IDV. We find the strong IDV of blazar 1357 + 769 for the first time. The IDV at centimeter-wavelength is believed to be predominately caused by the scintillation of blazar emission through the local interstellar medium in a few hundreds parsecs away from Sun. No significant correlation between the IDV strength and either redshift or Galactic latitude is found in our sample. The IDV timescale along with source structure and brightness temperature analysis will be presented in a forthcoming paper.

astro-ph.HE↗

arXiv2021

The Multi-Modal Video Reasoning and Analyzing Competition

In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021. This competition is composed of four different tracks, namely, video question answering, skeleton-based action recognition, fisheye video-based action recognition, and person re-identification, which are based on two datasets: SUTD-TrafficQA and UAV-Human. We summarize the top-performing methods submitted by the participants in this competition and show their results achieved in the competition.

cs.CV↗

arXiv2021

Seirios: Leveraging Multiple Channels for LoRaWAN Indoor and Outdoor Localization

Localization is important for a large number of Internet of Things (IoT) endpoint devices connected by LoRaWAN. Due to the bandwidth limitations of LoRaWAN, existing localization methods without specialized hardware (e.g., GPS) produce poor performance. To increase the localization accuracy, we propose a super-resolution localization method, called Seirios, which features a novel algorithm to synchronize multiple non-overlapped communication channels by exploiting the unique features of the radio physical layer to increase the overall bandwidth. By exploiting both the original and the conjugate of the physical layer, Seirios can resolve the direct path from multiple reflectors in both indoor and outdoor environments. We design a Seirios prototype and evaluate its performance in an outdoor area of 100 m $\times$ 60 m, and an indoor area of 25 m $\times$ 15 m, which shows that Seirios can achieve a median error of 4.4 m outdoors (80% samples < 6.4 m), and 2.4 m indoors (80% samples < 6.1 m), respectively. The results show that Seirios produces 42% less localization error than the baseline approach. Our evaluation also shows that, different to previous studies in Wi-Fi localization systems that have wider bandwidth, time-of-fight (ToF) estimation is less effective for LoRaWAN localization systems with narrowband radio signals.

eess.SP↗

arXiv2021

UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

Human behavior understanding with unmanned aerial vehicles (UAVs) is of great significance for a wide range of applications, which simultaneously brings an urgent demand of large, challenging, and comprehensive benchmarks for the development and evaluation of UAV-based models. However, existing benchmarks have limitations in terms of the amount of captured data, types of data modalities, categories of provided tasks, and diversities of subjects and environments. Here we propose a new benchmark - UAVHuman - for human behavior understanding with UAVs, which contains 67,428 multi-modal video sequences and 119 subjects for action recognition, 22,476 frames for pose estimation, 41,290 frames and 1,144 identities for person re-identification, and 22,263 frames for attribute recognition. Our dataset was collected by a flying UAV in multiple urban and rural districts in both daytime and nighttime over three months, hence covering extensive diversities w.r.t subjects, backgrounds, illuminations, weathers, occlusions, camera motions, and UAV flying attitudes. Such a comprehensive and challenging benchmark shall be able to promote the research of UAV-based human behavior understanding, including action recognition, pose estimation, re-identification, and attribute recognition. Furthermore, we propose a fisheye-based action recognition method that mitigates the distortions in fisheye videos via learning unbounded transformations guided by flat RGB videos. Experiments show the efficacy of our method on the UAV-Human dataset. The project page: https://github.com/SUTDCV/UAV-Human

cs.CV↗

arXiv2021

Revisiting the Reduction of Thermal Conductivity in Nano- to Micro-Grained Bismuth Telluride: The Importance of Grain-Boundary Thermal Resistance

Nanograined bulk alloys based on bismuth telluride (Bi2Te3) are the dominant materials for room-temperature thermoelectric applications. In numerous studies, existing bulk phonon mean free path (MFP) spectra predicted by atomistic simulations suggest sub-100 nm grain sizes are necessary to reduce the lattice thermal conductivity by decreasing phonon MFPs. This is in contrast with available experimental data, where a remarkable thermal conductivity reduction is observed even for micro-grained Bi2Te3 samples. In this work, first-principles phonon MFPs along both the in-plane and cross-plane directions are re-computed for bulk Bi2Te3. These phonon MFPs can explain new and existing experimental data on flake-like Bi2Te3 nanostructures with various thicknesses. For polycrystalline Bi2Te3-based materials, a better explanation of the experimental data requires further consideration of the grain-boundary thermal resistance that can largely suppress the transport of high-frequency optical phonons.

physics.app-ph↗

arXiv2021

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often expensive to collect. We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. Specifically, we represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. We evaluate our skeleton cloud colorization approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Extensive experiments on NTU RGB+D and NW-UCLA datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins, and it achieves competitive performance in supervised 3D action recognition as well.

cs.CV↗

arXiv2021

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

Semantic segmentation is a crucial image understanding task, where each pixel of image is categorized into a corresponding label. Since the pixel-wise labeling for ground-truth is tedious and labor intensive, in practical applications, many works exploit the synthetic images to train the model for real-word image semantic segmentation, i.e., Synthetic-to-Real Semantic Segmentation (SRSS). However, Deep Convolutional Neural Networks (CNNs) trained on the source synthetic data may not generalize well to the target real-world data. In this work, we propose two simple yet effective texture randomization mechanisms, Global Texture Randomization (GTR) and Local Texture Randomization (LTR), for Domain Generalization based SRSS. GTR is proposed to randomize the texture of source images into diverse unreal texture styles. It aims to alleviate the reliance of the network on texture while promoting the learning of the domain-invariant cues. In addition, we find the texture difference is not always occurred in entire image and may only appear in some local areas. Therefore, we further propose a LTR mechanism to generate diverse local regions for partially stylizing the source images. Finally, we implement a regularization of Consistency between GTR and LTR (CGL) aiming to harmonize the two proposed mechanisms during training. Extensive experiments on five publicly available datasets (i.e., GTA5, SYNTHIA, Cityscapes, BDDS and Mapillary) with various SRSS settings (i.e., GTA5/SYNTHIA to Cityscapes/BDDS/Mapillary) demonstrate that the proposed method is superior to the state-of-the-art methods for domain generalization based SRSS.

cs.CV↗

arXiv2021

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database. In this way, when updating the deployed model, we can bypass the inflexible and time-consuming feature re-extraction process. However, the old feature space that needs to be compatible is not ideal and faces the distribution discrepancy problem with the new space caused by different supervision losses. In this work, we propose a global optimization Dual-Tuning method to obtain feature compatibility against different networks and losses. A feature-level prototype loss is proposed to explicitly align two types of embedding features, by transferring global prototype information. Furthermore, we design a component-level mutual structural regularization to implicitly optimize the feature intrinsic structure. Experimental results on million-scale datasets demonstrate that our Dual-Tuning is able to obtain feature compatibility without sacrificing performance. (Our code will be avaliable at https://github.com/yanbai1993/Dual-Tuning)

cs.CV↗

arXiv2021

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the labeled source domain's knowledge to improve the model's discriminability on the unlabeled target domain. From a novel perspective, we argue that the bridging between the source and target domains can be utilized to tackle the UDA re-ID task, and we focus on explicitly modeling appropriate intermediate domains to characterize this bridging. Specifically, we propose an Intermediate Domain Module (IDM) to generate intermediate domains' representations on-the-fly by mixing the source and target domains' hidden representations using two domain factors. Based on the "shortest geodesic path" definition, i.e., the intermediate domains along the shortest geodesic path between the two extreme domains can play a better bridging role, we propose two properties that these intermediate domains should satisfy. To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors. The bridge losses aim at guiding the distribution of appropriate intermediate domains to keep the right distance to the source and target domains. The diversity loss serves as a regularization to prevent the generated intermediate domains from being over-fitting to either of the source and target domains. Our proposed method outperforms the state-of-the-arts by a large margin in all the common UDA re-ID tasks, and the mAP gain is up to 7.7% on the challenging MSMT17 benchmark. Code is available at https://github.com/SikaStar/IDM.

cs.CV↗

arXiv2021

An adaptive variational model for multireference alignment with mixed noise

Multireference alignment (MRA) problem is to estimate an underlying signal from a large number of noisy circularly-shifted observations. The existing methods are always proposed under the hypothesis of a single Gaussian noise. However, the hypothesis of a single-type noise is inefficient for solving practical problems like single particle cryo-EM. In this paper, We focus on the MRA problem under the assumption of Gaussian mixture noise. We derive an adaptive variational model by combining maximum a posteriori (MAP) estimation and soft-max method. There are two adaptive weights which are for detecting cyclical shifts and types of noise. Furthermore, we provide a statistical interpretation of our model by using expectation-maximization(EM) algorithm. The existence of a minimizer is mathematically proved. The numerical results show that the proposed model has a more impressive performance than the existing methods when one Gaussian noise is large and the other is small.

math.OC↗

arXiv2021

Performance Analysis on Machine Learning-Based Channel Estimation

Recently, machine learning-based channel estimation has attracted much attention. The performance of machine learning-based estimation has been validated by simulation experiments. However, little attention has been paid to the theoretical performance analysis. In this paper, we investigate the mean square error (MSE) performance of machine learning-based estimation. Hypothesis testing is employed to analyze its MSE upper bound. Furthermore, we build a statistical model for hypothesis testing, which holds when the linear learning module with a low input dimension is used in machine learning-based channel estimation, and derive a clear analytical relation between the size of the training data and performance. Then, we simulate the machine learning-based channel estimation in orthogonal frequency division multiplexing (OFDM) systems to verify our analysis results. Finally, the design considerations for the situation where only limited training data is available are discussed. In this situation, our analysis results can be applied to assess the performance and support the design of machine learning-based channel estimation.

eess.SP↗

arXiv2021

A Low Complexity Learning-based Channel Estimation for OFDM Systems with Online Training

In this paper, we devise a highly efficient machine learning-based channel estimation for orthogonal frequency division multiplexing (OFDM) systems, in which the training of the estimator is performed online. A simple learning module is employed for the proposed learning-based estimator. The training process is thus much faster and the required training data is reduced significantly. Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission. The feasibility of this novel construction approach is verified by theoretical analysis and simulations. Based on this construction approach, two alternative training data generation schemes are proposed. One scheme transmits additional block pilot symbols to create training data, while the other scheme adopts a decision-directed method and does not require extra pilot overhead. Simulation results show the robustness of the proposed channel estimation method. Furthermore, the proposed method shows better adaptation to practical imperfections compared with the conventional minimum mean-square error (MMSE) channel estimation. It outperforms the existing machine learning-based channel estimation techniques under varying channel conditions.

eess.SP↗

arXiv2021

Bilinear Control of Convection-Cooling: From Open-Loop to Closed-Loop

This paper is concerned with a bilinear control problem for enhancing convection-cooling via an incompressible velocity field. Both optimal open-loop control and closed-loop feedback control designs are addressed. First and second order optimality conditions for characterizing the optimal solution are discussed. In particular, the method of instantaneous control is applied to establish the feedback laws. Moreover, the construction of feedback laws is also investigated by directly utilizing the optimality system with appropriate numerical discretization schemes. Computationally, it is much easier to implement the closed-loop feedback control than the optimal open-loop control, as the latter requires to solve the state equations forward in time, coupled with the adjoint equations backward in time together with a nonlinear optimality condition. Rigorous analysis and numerical experiments are presented to demonstrate our ideas and validate the efficacy of the control designs.

math.OC↗