arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 649 records · Page 36Linked to original sources

arXiv2021

Fast Parallel-in-Time Quasi-Boundary Value Methods for Backward Heat Conduction Problems

In this paper we proposed two new quasi-boundary value methods for regularizing the ill-posed backward heat conduction problems. With a standard finite difference discretization in space and time, the obtained all-at-once nonsymmetric sparse linear systems have the desired block $ω$-circulant structure, which can be utilized to design an efficient parallel-in-time (PinT) direct solver that built upon an explicit FFT-based diagonalization of the time discretization matrix. Convergence analysis is presented to justify the optimal choice of the regularization parameter. Numerical examples are reported to validate our analysis and illustrate the superior computational efficiency of our proposed PinT methods.

math.NA↗

arXiv2021

Interventional Video Grounding with Dual Contrastive Learning

Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies, i.e., P(Y|X). Consequently, these models may suffer from spurious correlations between the language and video features due to the selection bias of the dataset. 1) To uncover the causality behind the model and data, we first propose a novel paradigm from the perspective of the causal inference, i.e., interventional video grounding (IVG) that leverages backdoor adjustment to deconfound the selection bias based on structured causal model (SCM) and do-calculus P(Y|do(X)). Then, we present a simple yet effective method to approximate the unobserved confounder as it cannot be directly sampled from the dataset. 2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations. Experiments on three standard benchmarks show the effectiveness of our approaches. Our code is available on GitHub: https://github.com/nanguoshun/IVG.

cs.CV↗

arXiv2021

SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events

Traffic event cognition and reasoning in videos is an important task that has a wide range of applications in intelligent transportation, assisted driving, and autonomous vehicles. In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10,080 in-the-wild videos and annotated 62,535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios. Specifically, we propose 6 challenging reasoning tasks corresponding to various traffic scenarios, so as to evaluate the reasoning capability over different kinds of complex yet practical traffic events. Moreover, we propose Eclipse, a novel Efficient glimpse network via dynamic inference, in order to achieve computation-efficient and reliable video reasoning. The experiments show that our method achieves superior performance while reducing the computation cost significantly. The project page: https://github.com/SUTDCV/SUTD-TrafficQA.

cs.CV↗

arXiv2021

QFCNN: Quantum Fourier Convolutional Neural Network

The neural network and quantum computing are both significant and appealing fields, with their interactive disciplines promising for large-scale computing tasks that are untackled by conventional computers. However, both developments are restricted by the scope of the hardware development. Nevertheless, many neural network algorithms had been proposed before GPUs become powerful enough for running very deep models. Similarly, quantum algorithms can also be proposed as knowledge reserves before real quantum computers are easily accessible. Specifically, taking advantage of both the neural networks and quantum computation and designing quantum deep neural networks (QDNNs) for acceleration on Noisy Intermediate-Scale Quantum (NISQ) processors is also an important research problem. As one of the most widely used neural network architectures, convolutional neural network (CNN) remains to be accelerated by quantum mechanisms, with only a few attempts have been demonstrated. In this paper, we propose a new hybrid quantum-classical circuit, namely Quantum Fourier Convolutional Network (QFCN). Our model achieves exponential speed-up compared with classical CNN theoretically and improves over the existing best result of quantum CNN. We demonstrate the potential of this architecture by applying it to different deep learning tasks, including traffic prediction and image classification.

quant-ph↗

arXiv2021

KGTK: A Toolkit for Large Knowledge Graph Manipulation and Analysis

Knowledge graphs (KGs) have become the preferred technology for representing, sharing and adding knowledge to modern AI applications. While KGs have become a mainstream technology, the RDF/SPARQL-centric toolset for operating with them at scale is heterogeneous, difficult to integrate and only covers a subset of the operations that are commonly needed in data science applications. In this paper we present KGTK, a data science-centric toolkit designed to represent, create, transform, enhance and analyze KGs. KGTK represents graphs in tables and leverages popular libraries developed for data science applications, enabling a wide audience of developers to easily construct knowledge graph pipelines for their applications. We illustrate the framework with real-world scenarios where we have used KGTK to integrate and manipulate large KGs, such as Wikidata, DBpedia and ConceptNet.

cs.AI↗

arXiv2021

Generalizable Person Re-identification with Relevance-aware Mixture of Experts

Domain generalizable (DG) person re-identification (ReID) is a challenging problem because we cannot access any unseen target domain data during training. Almost all the existing DG ReID methods follow the same pipeline where they use a hybrid dataset from multiple source domains for training, and then directly apply the trained model to the unseen target domains for testing. These methods often neglect individual source domains' discriminative characteristics and their relevances w.r.t. the unseen target domains, though both of which can be leveraged to help the model's generalization. To handle the above two issues, we propose a novel method called the relevance-aware mixture of experts (RaMoE), using an effective voting-based mixture mechanism to dynamically leverage source domains' diverse characteristics to improve the model's generalization. Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics. Besides, we design a voting network to adaptively integrate all the experts' features into the more generalizable aggregated features with domain relevance. Considering the target domains' invisibility during training, we propose a novel learning-to-learn algorithm combined with our relation alignment loss to update the voting network. Extensive experiments demonstrate that our proposed RaMoE outperforms the state-of-the-art methods.

cs.CV↗

arXiv2021

Distributed Resilient Submodular Action Selection in Adversarial Environments

In this letter, we consider a distributed submodular maximization problem for multi-robot systems when attacked by adversaries. One of the major challenges for multi-robot systems is to increase resilience against failures or attacks. This is particularly important for distributed systems under attack as there is no central point of command that can detect, mitigate, and recover from attacks. Instead, a distributed multi-robot system must coordinate effectively to overcome adversarial attacks. In this work, our distributed submodular action selection problem models a broad set of scenarios where each robot in a multi-robot system has multiple action selections that may fulfill a global objective, such as exploration or target tracking. To increase resilience in this context, we propose a fully distributed algorithm to guide each robot's action selection when the system is attacked. The proposed algorithm guarantees performance in a worst-case scenario where up to a portion of the robots malfunction due to attacks. Importantly, the proposed algorithm is also consistent, as it is shown to converge to the same solution as a centralized method. Finally, a distributed resilient multi-robot exploration problem is presented to confirm the performance of the proposed algorithm.

cs.RO↗

arXiv2021

Fractal Rosette: A Stable Space-Ground Network Structure in Mega-Constellation

We present F-Rosette, a stable space-ground network structure for low-earth orbit (LEO) satellite mega-constellations at scale. Due to the dynamic many-to-many space-ground mapping in high mobility, existing LEO mega-constellations with IP protocol stack suffer from frequent user IP address changes (every 133~510s per user) and network routing re-convergence (<20% network usability). To provably stabilize the space-ground network under high mobility and many-to-many dynamics, F-Rosette adopts a recursive structure over the Rosette constellation, derives a hierarchical and time-invariant network address space from a new geographical coordinate system, and ensures efficient and stable routing via geographical-to-topological routing embedding without re-convergence. Our hardware-in-the-loop, trace-driven emulations validate F-Rosette's stability, near-optimal routing (<1.4% additional delays), and marginal overhead (<1% CPU, <2MB memory) for resource-constrained satellites.

cs.NI↗

arXiv2021

Asymmetric four-grating compressor for ultrafast high power lasers

The peak power improvement and running safety of petawatt (PW) lasers are limited by laser-induced damage of optical components with limited sizes and damage thresholds. Diffraction gratings in pulse compressors have been the shortest stave of PW lasers up to now, as to manufacture a high quality meter-sized grating remains particularly challenging. Here, the asymmetric four-grating compressor (AFGC) with asymmetric configuration is proposed for PW lasers to increase the maximum bearable output pulse energy and running safety without neither additional optical component nor extra control in comparison to a traditional Treacy four-grating compressor (TFGC) with symmetric configuration. In AFGC, suitable spatial dispersion can be introduced in the output laser beam which is able to decrease the laser spatial intensity modulation (LSIM) of the output beam on the final grating. The introduced spatial dispersion can be automatically compensated at the focal plane by using the spatiotemporal focusing technique. Based on this simple AFGC design, not only the damage risk of the final grating can be reduced, but also the maximum output pulse energy can be improved by about 1.8 times theoretically. As an example, 100 PW output power can be achieved theoretically by using the AFGC with an input beam size of 550*700 mm2.

physics.optics↗

arXiv2021

ParaDiag: parallel-in-time algorithms based on the diagonalization technique

In 2008, Maday and Ronquist introduced an interesting new approach for the direct parallel-in-time (PinT) solution of time-dependent PDEs. The idea is to diagonalize the time stepping matrix, keeping the matrices for the space discretization unchanged, and then to solve all time steps in parallel. Since then, several variants appeared, and we call these closely related algorithms ParaDiag algorithms. ParaDiagalgorithms in the literature can be classified into two groups: ParaDiag-I: direct standalone solvers, ParaDiag-II: iterative solvers. We will explain the basic features of each group in this note. To have concrete examples, we will introduce ParaDiag-I and ParaDiag-II for the advection-diffusion equation. We will also introduce ParaDiag-II for the wave equation and an optimal control problem for the wave equation. We could have used the advection-diffusion equation as well to illustrate ParaDiag-II, but wave equations are known to cause problems for certain PinT algorithms and thus constitute an especially interesting example for which ParaDiag algorithms were tested. We show the main known theoretical results in each case, and also provide Matlab codes for testing. The goal of the Matlab codes is to help the interested reader understand the key features of the ParaDiag algorithms, without intention to be highly tuned for efficiency and/or low memory use. We also provide speedup measurements of ParaDiag algorithms for a 2D linear advection-diffusion equation. These results are obtained on the Tianhe-1 supercomputer in China and the SIUE Campus Cluster in the US and and we compare these results to the performance of parareal and MGRiT, two widely used PinT algorithms.

math.NA↗

arXiv2021

Detection of a rank-one signal with limited training data

In this paper, we reconsider the problem of detecting a matrix-valued rank-one signal in unknown Gaussian noise, which was previously addressed for the case of sufficient training data. We relax the above assumption to the case of limited training data. We re-derive the corresponding generalized likelihood ratio test (GLRT) and two-step GLRT (2S--GLRT) based on certain unitary transformation on the test data. It is shown that the re-derived detectors can work with low sample support. Moreover, in sample-abundant environments the re-derived GLRT is the same as the previously proposed GLRT and the re-derived 2S--GLRT has better detection performance than the previously proposed 2S--GLRT. Numerical examples are provided to demonstrate the effectiveness of the re-derived detectors.

eess.SP↗

arXiv2021

Rank-One Prior: Toward Real-Time Scene Recovery

Scene recovery is a fundamental imaging task for several practical applications, e.g., video surveillance and autonomous vehicles, etc. To improve visual quality under different weather/imaging conditions, we propose a real-time light correction method to recover the degraded scenes in the cases of sandstorms, underwater, and haze. The heart of our work is that we propose an intensity projection strategy to estimate the transmission. This strategy is motivated by a straightforward rank-one transmission prior. The complexity of transmission estimation is $O(N)$ where $N$ is the size of the single image. Then we can recover the scene in real-time. Comprehensive experiments on different types of weather/imaging conditions illustrate that our method outperforms competitively several state-of-the-art imaging methods in terms of efficiency and robustness.

cs.CV↗

arXiv2021

Safety-Critical Control of Stochastic Systems using Stochastic Control Barrier Functions

Control barrier functions have been widely used for synthesizing safety-critical controls, often via solving quadratic programs. However, the existence of Gaussian-type noise may lead to unsafe actions and result in severe consequences. In this paper, we study systems modeled by stochastic differential equations (SDEs) driven by Brownian motions. We propose a notion of stochastic control barrier functions (SCBFs)and show that SCBFs can significantly reduce the control efforts, especially in the presence of noise, compared to stochastic reciprocal control barrier functions (SRCBFs), and offer a less conservative estimation of safety probability, compared to stochastic zeroing control barrier functions (SZCBFs). Based on this less conservative probabilistic estimation for the proposed notion of SCBFs, we further extend the results to handle high relative degree safety constraints using high-order SCBFs. We demonstrate that the proposed SCBFs achieve good trade-offs of performance and control efforts, both through theoretical analysis and numerical simulations.

eess.SY↗

arXiv2021

Constrained Radar Waveform Design for Range Profiling

Range profiling refers to the measurement of target response along the radar slant range. It plays an important role in automatic target recognition. In this paper, we consider the design of transmit waveform to improve the range profiling performance of radar systems. Two design metrics are adopted for the waveform optimization problem: one is to maximize the mutual information between the received signal and the target impulse response (TIR); the other is to minimize the minimum mean-square error for estimating the TIR. In addition, practical constraints on the waveforms are considered, including an energy constraint, a peak-to-average-power-ratio constraint, and a spectral constraint. Based on minorization-maximization, we propose a unified optimization framework to tackle the constrained waveform design problem. Numerical examples show the superiority of the waveforms synthesized by the proposed algorithms.

eess.SP↗

arXiv2021

RL-CSDia: Representation Learning of Computer Science Diagrams

Recent studies on computer vision mainly focus on natural images that express real-world scenes. They achieve outstanding performance on diverse tasks such as visual question answering. Diagram is a special form of visual expression that frequently appears in the education field and is of great significance for learners to understand multimodal knowledge. Current research on diagrams preliminarily focuses on natural disciplines such as Biology and Geography, whose expressions are still similar to natural images. Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank. The main challenges of graphic diagrams understanding are the rarity of data and the confusion of semantics, which are mainly reflected in the diversity of expressions. In this paper, we construct a novel dataset of graphic diagrams named Computer Science Diagrams (CSDia). It contains more than 1,200 diagrams and exhaustive annotations of objects and relations. Considering the visual noises caused by the various expressions in diagrams, we introduce the topology of diagrams to parse topological structure. After that, we propose Diagram Parsing Net (DPN) to represent the diagram from three branches: topology, visual feature, and text, and apply the model to the diagram classification task to evaluate the ability of diagrams understanding. The results show the effectiveness of the proposed DPN on diagrams understanding.

cs.CV↗

arXiv2021

Quadrupling the stored charge by extending the accessible density of states

Nanosized energy storage, energy-harvesting, and functional devices are the three key components for integrated self-power systems. Here, we report on nanoscale electrochemical devices with a nearly three-fold enhanced stored charge under the field effect. We demonstrated the field-effect transistor can not only work as a functional component in nanodevices but also serve as an amplifier for the nanosized energy storage blocks. This unusual increase in energy storage is attributed to having a wide range of accessible electronic density of states (EDOS), hence redox reactions are occurring within the nanowire and not being confined to the surface. Initial results with MoS2 suggest that this field effect modulated energy storage mechanism may also apply to many other redox-active materials. Our work demonstrates the novel application of the field-effect in energy storage devices as a universal strategy to improve ion diffusion and the surface-active ion concentration of the active material, which can greatly enhance the charge storage ability of nanoscale devices. The fabrication process of the field-effect energy storage device is also compatible with microtechnology and can be integrated into other microdevices and nanodevices.

physics.app-ph↗

arXiv2021

A multistep pulse compressor for 10s to 100s PW lasers

High-energy tens (10s) to hundreds (100s) petawatt (PW) lasers are key tools for exploring frontier fundamental researches such as strong-field quantum electrodynamics (QED), and the generation of positron-electron pair from vacuum. Recently, pulse compressor became the main obstacle on achieving higher peak power due to the limitation of damage threshold and size of diffraction gratings. Here, we propose a feasible multistep pulse compressor (MPC) to increase the maximum bearable input and output pulse energies through modifying their spatiotemporal properties. Typically, the new MPC including a prism pair for pre-compression, a four-grating compressor (FGC) for main compression, and a spatiotemporal focusing based self-compressor for post-compression. The prism pair can induce spatial dispersion to smooth and enlarge the laser beam, which increase the maximum input and output pulse energies. As a result, as high as 100 PW laser with single beam or more than 150 PW through combining two beams can be obtained by using MPC and current available optics. This new optical design will simplify the compressor, improve the stability, and save expensive gratings/optics simultaneously. Together with the multi-beam tiled-aperture combining method, the tiled-grating method, larger gratings, or negative chirp pulse based self-compression method, several 100s PW laser beam is expected to be obtained by using this MPC method in the future, which will further extend the ultra-intense laser physics research fields.

physics.optics↗

arXiv2021

A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning

How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world. Currently, the chest CT is regarded as a popular and informative imaging tool for COVID-19 diagnosis. However, we observe that there are two issues -- weak annotation and insufficient data that may obstruct automatic COVID-19 severity assessment with CT images. To address these challenges, we propose a novel three-component method, i.e., 1) a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, 2) a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and 3) a self-supervised pretext component to aid the learning process. We have systematically evaluated our method on the CT images of 229 COVID-19 cases, including 50 severe and 179 non-severe cases. Our method could obtain an average accuracy of 95.8%, with 93.6% sensitivity and 96.4% specificity, which outperformed previous works.

eess.IV↗