arXiv subjects

Chi Zhang

Publications and source records attributed to Chi Zhang.

At least 811 records · Page 45Linked to original sources

arXiv2019

Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints

In this paper, we present a learning approach to goal assignment and trajectory planning for unlabeled robots operating in 2D, obstacle-filled workspaces. More specifically, we tackle the unlabeled multi-robot motion planning problem with motion constraints as a multi-agent reinforcement learning problem with some sparse global reward. In contrast with previous works, which formulate an entirely new hand-crafted optimization cost or trajectory generation algorithm for a different robot dynamic model, our framework is a general approach that is applicable to arbitrary robot models. Further, by using the velocity obstacle, we devise a smooth projection that guarantees collision free trajectories for all robots with respect to their neighbors and obstacles. The efficacy of our algorithm is demonstrated through varied simulations.

cs.RO↗

arXiv2019

Isolating hydrogen in hexagonal boron nitride bubbles by a plasma treatment

Atomically thin hexagonal boron nitride (h-BN) is often regarded as an elastic film that is impermeable to gases. The high stabilities in thermal and chemical properties allow h-BN to serve as a gas barrier under extreme conditions.In this work, we demonstrate the isolation of hydrogen in bubbles of h-BN via plasma treatment.Detailed characterizations reveal that the substrates do not show chemical change after treatment. The bubbles are found to withstand thermal treatment in air,even at 800 degree celsius. Scanning transmission electron microscopy investigation shows that the h-BN multilayer has a unique aligned porous stacking nature, which is essential for the character of being transparent to atomic hydrogen but impermeable to hydrogen molecules. We successfully demonstrated the extraction of hydrogen gases from gaseous compounds or mixtures containing hydrogen element. The successful production of hydrogen bubbles on h-BN flakes has potential for further application in nano/micro-electromechanical systems and hydrogen storage.

physics.app-ph↗

arXiv2019

Accelerating Concurrent Heap on GPUs

Priority queue, often implemented as a heap, is an abstract data type that has been used in many well-known applications like Dijkstra's shortest path algorithm, Prim's minimum spanning tree, Huffman encoding, and the branch-and-bound algorithm. However, it is challenging to exploit the parallelism of the heap on GPUs since the control divergence and memory irregularity must be taken into account. In this paper, we present a parallel generalized heap model that works effectively on GPUs. We also prove the linearizability of our generalized heap model which enables us to reason about the expected results. We evaluate our concurrent heap thoroughly and show a maximum 19.49X speedup compared to the sequential CPU implementation and 2.11X speedup compared with the existing GPU implementation. We also apply our heap to single source shortest path with up to 1.23X speedup and 0/1 knapsack problem with up to 12.19X speedup.

cs.DC↗

arXiv2019

Distributed Optimization for Over-Parameterized Learning

Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee convergence. In this paper, we establish a completely different conclusion that each node can perform an arbitrary number of local optimization steps before communication. Moreover, we show that the more local updating can reduce the overall communication, even for an infinity number of steps where each node is free to update its local model to near-optimality before exchanging information. The extra assumption we make is that the optimal sets of local loss functions have a non-empty intersection, which is inspired by the over-paramterization phenomenon in large-scale optimization and deep learning. Our theoretical findings are confirmed by both distributed convex optimization and deep learning experiments.

cs.DC↗

arXiv2019

Dual-criteria time stepping for weakly compressible smoothed particle hydrodynamics

Implementing particle-interaction configuration and time integration are performance intensive essentials of particle-based methods. In this paper, a dual-criteria time-stepping method is proposed to improve the computational efficiency of the weakly-compressible smoothed particle hydrodynamic (WCSPH) method for modeling incompressible flows. The key idea is to introduce an advection time criterion, which is based on fluid velocity field, for recreating the particle-interaction configuration. Within this time criterion, several steps of pressure relaxation determined by the acoustic time criterion, based on the artificial speed of sound, can be carried out without updating the particle interaction configuration and much larger time-step sizes compared with the conventional counterpart. The method has shown optimized computational performance through CPU cost analysis. Good accuracy and performance is obtained for the presented benchmarks implying promising potential of the proposed method for incompressible flow and fluid-structure interaction simulations.

physics.comp-ph↗

arXiv2019

Bimodal Stereo: Joint Shape and Pose Estimation from Color-Depth Image Pair

Mutual calibration between color and depth cameras is a challenging topic in multi-modal data registration. In this paper, we are confronted with a "Bimodal Stereo" problem, which aims to solve camera pose from a pair of an uncalibrated color image and a depth map from different views automatically. To address this problem, an iterative Shape-from-Shading (SfS) based framework is proposed to estimate shape and pose simultaneously. In the pipeline, the estimated shape is refined by the shape prior from the given depth map under the estimated pose. Meanwhile, the estimated pose is improved by the registration of estimated shape and shape from given depth map. We also introduce a shading based refinement in the pipeline to address noisy depth map with holes. Extensive experiments showed that through our method, both the depth map, the recovered shape as well as its pose can be desirably refined and recovered.

cs.CV↗

arXiv2019

Joint haze image synthesis and dehazing with mmd-vae losses

Fog and haze are weathers with low visibility which are adversarial to the driving safety of intelligent vehicles equipped with optical sensors like cameras and LiDARs. Therefore image dehazing for perception enhancement and haze image synthesis for testing perception abilities are equivalently important in the development of such autonomous driving systems. From the view of image translation, these two problems are essentially dual with each other, which have the potentiality to be solved jointly. In this paper, we propose an unsupervised Image-to-Image Translation framework based on Variational Autoencoders (VAE) and Generative Adversarial Nets (GAN) to handle haze image synthesis and haze removal simultaneously. Since the KL divergence in the VAE objectives could not guarantee the optimal mapping under imbalanced and unpaired training samples with limited size, Maximum mean discrepancy (MMD) based VAE is utilized to ensure the translating consistency in both directions. The comprehensive analysis on both synthesis and dehazing performance of our method demonstrate the feasibility and practicability of the proposed method.

cs.CV↗

arXiv2019

Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention

Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person ReID. Many existing methods tackle this problem by average/maximum temporal pooling or RNNs with attention. However, these methods cannot deal with temporal dependency and spatial misalignment problems at the same time. We are inspired by video action recognition that involves the identification of different actions from video tracks. Firstly, we use 3D convolutions on video volume, instead of using 2D convolutions across frames, to extract spatial and temporal features simultaneously. Secondly, we use a non-local block to tackle the misalignment problem and capture spatial-temporal long-range dependencies. As a result, the network can learn useful spatial-temporal information as a weighted sum of the features in all space and temporal positions in the input feature map. Experimental results on three datasets show that our framework outperforms state-of-the-art approaches by a large margin on multiple metrics.

cs.CV↗

arXiv2019

Highly-polarizable ion in a Paul trap

Usually the influence of the quadratic Stark effect on an ion's trapping potential is minuscule and only needs to be considered in atomic clock experiments. In this work we excite a trapped ion to a Rydberg state with polarizability $\sim$~eight orders of magnitude higher than a low-lying electronic state; we find that the highly-polarizable ion experiences a vastly different trapping potential owing to the Stark effect. We observe changes in trap stiffness, equilibrium position and minimum potential, which can be tuned using the trapping electric fields. These effects lie at the heart of proposals to shape motional mode spectra, simulate quantum magnetism and coherently drive structural phase transitions; in addition we propose using these effects to simulate cosmological particle creation, study quantum fluctuations of work and minimize ion micromotion. Mitigation of Stark effects is important for coherent control of Rydberg ions; we illustrate this by carrying out the first Rabi oscillations between a low-lying electronic state and a Rydberg state of an ion.

quant-ph↗

arXiv2019

Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering

In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention. Our VideoQA model firstly generates the global context-aware visual and textual features respectively by interacting current inputs with memory contents. After that, it makes the attentional fusion of the multimodal visual and textual representations to infer the correct answer. Multiple cycles of reasoning can be made to iteratively refine attention weights of the multimodal data and improve the final representation of the QA pair. Experimental results demonstrate our approach achieves state-of-the-art performance on four VideoQA benchmark datasets.

cs.CV↗

arXiv2019

Neo: A Learned Query Optimizer

Query optimization is one of the most challenging problems in database systems. Despite the progress made over the past decades, query optimizers remain extremely complex components that require a great deal of hand-tuning for specific workloads and datasets. Motivated by this shortcoming and inspired by recent advances in applying machine learning to data management challenges, we introduce Neo (Neural Optimizer), a novel learning-based query optimizer that relies on deep neural networks to generate query executions plans. Neo bootstraps its query optimization model from existing optimizers and continues to learn from incoming queries, building upon its successes and learning from its failures. Furthermore, Neo naturally adapts to underlying data patterns and is robust to estimation errors. Experimental results demonstrate that Neo, even when bootstrapped from a simple optimizer like PostgreSQL, can learn a model that offers similar performance to state-of-the-art commercial optimizers, and in some cases even surpass them.

cs.DB↗

arXiv2019

Re-Identification Supervised Texture Generation

The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discussed. In this paper, we propose an end-to-end learning strategy to generate textures of human bodies under the supervision of person re-identification. We render the synthetic images with textures extracted from the inputs and maximize the similarity between the rendered and input images by using the re-identification network as the perceptual metrics. Experiment results on pedestrian images show that our model can generate the texture from a single image and demonstrate that our textures are of higher quality than those generated by other available methods. Furthermore, we extend the application scope to other categories and explore the possible utilization of our generated textures.

cs.CV↗

arXiv2019

Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification

This paper considers a realistic problem in person re-identification (re-ID) task, i.e., partial re-ID. Under partial re-ID scenario, the images may contain a partial observation of a pedestrian. If we directly compare a partial pedestrian image with a holistic one, the extreme spatial misalignment significantly compromises the discriminative ability of the learned representation. We propose a Visibility-aware Part Model (VPM), which learns to perceive the visibility of regions through self-supervision. The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images). VPM gains two-fold benefit toward higher accuracy for partial re-ID. On the one hand, compared with learning a global feature, VPM learns region-level features and benefits from fine-grained information. On the other hand, with visibility awareness, VPM is capable to estimate the shared regions between two images and thus suppresses the spatial misalignment. Experimental results confirm that our method significantly improves the learned representation and the achieved accuracy is on par with the state of the art.

cs.CV↗

arXiv2019

Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction

Following the success of deep learning in a wide range of applications, neural network-based machine learning techniques have received interest as a means of accelerating magnetic resonance imaging (MRI). A number of ideas inspired by deep learning techniques from computer vision and image processing have been successfully applied to non-linear image reconstruction in the spirit of compressed sensing for both low dose computed tomography and accelerated MRI. The additional integration of multi-coil information to recover missing k-space lines in the MRI reconstruction process, is still studied less frequently, even though it is the de-facto standard for currently used accelerated MR acquisitions. This manuscript provides an overview of the recent machine learning approaches that have been proposed specifically for improving parallel imaging. A general background introduction to parallel MRI is given that is structured around the classical view of image space and k-space based methods. Both linear and non-linear methods are covered, followed by a discussion of recent efforts to further improve parallel imaging using machine learning, and specifically using artificial neural networks. Image-domain based techniques that introduce improved regularizers are covered as well as k-space based methods, where the focus is on better interpolation strategies using neural networks. Issues and open problems are discussed as well as recent efforts for producing open datasets and benchmarks for the community.

eess.SP↗

arXiv2019

Tracking the dynamics of an ideal quantum measurement

The existence of ideal quantum measurements is one of the fundamental predictions of quantum mechanics. In theory the measurement projects onto the eigenbasis of the measurement observable while preserving all coherences of degenerate eigenstates. The question arises whether there are dynamical processes in nature that correspond to such ideal quantum measurements. Here we address this question and present experimental results monitoring the dynamics of a naturally occurring measurement process: the coupling of a trapped ion qutrit to the photon environment. By taking tomographic snapshots during the detection process, we show with an average fidelity of $94\%$ that the process develops in agreement with the model of an ideal quantum measurement.

quant-ph↗

arXiv2019

A weakly compressible SPH method for violent multi-phase flows with high density ratio

The weakly compressible SPH (WCSPH) method is known suffering from low computational efficiency, or unnatural voids and unrealistic phase separation when it is applied to simulate highly violent multi-phase flows with high density ratio, such as that between water and air. In this paper, to remedy these issues, we propose a multi-phase WCSPH method based on a low-dissipation Riemann solver and the transport-velocity formulation. The two-phase Riemann problem is first constructed to handle the pairwise interaction between fluid particles, then modified for the fluid-wall interaction to impose the solid wall boundary condition. Since the method uses the same artificial speed of sound for both heavy and light phases, the computational efficiency increases greatly. Furthermore, due to the transport-velocity formulation employed for the light phase and application of the two-phase Riemann problem, the unnatural voids and unrealistic phase separation are effectively eliminated. The method is validated with several 2- and 3D cases involving violent water-air flows. The results have been compared with existing experimental data, previous numerical and analytical solutions, where the proposed method demonstrates good robustness, improved or comparable accuracy, respectively, comparing to previous methods with same choice of sound speed or those with much less computational efficiency.

physics.comp-ph↗

arXiv2019

Category decoding of visual stimuli from human brain activity using a bidirectional recurrent neural network to simulate bidirectional information flows in human visual cortices

Recently, visual encoding and decoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation. Despite the hierarchically similar representations of deep network and human vision, visual information flows from primary visual cortices to high visual cortices and vice versa based on the bottom-up and top-down manners, respectively. Inspired by the bidirectional information flows, we proposed a bidirectional recurrent neural network (BRNN)-based method to decode the categories from fMRI data. The forward and backward directions in the BRNN module characterized the bottom-up and top-down manners, respectively. The proposed method regarded the selected voxels of each visual cortex region (V1, V2, V3, V4, and LO) as one node in the sequence fed into the BRNN module and combined the output of the BRNN module to decode the categories with the subsequent fully connected layer. This new method allows the efficient utilization of hierarchical information representations and bidirectional information flows in human visual cortices. Experiment results demonstrated that our method improved the accuracy of three-level category decoding than other methods, which implicitly validated the hierarchical and bidirectional human visual representations. Comparative analysis revealed that the category representations of human visual cortices were hierarchical, distributed, complementary, and correlative.

q-bio.NC↗

arXiv2019

Pure temporal dispersion for aberration free ultrafast time-stretch applications

Photonic time-stretch overcomes the speed limitation of conventional digitizers, and enables the observation of non-repetitive and statistically rare phenomena that occur on short timescales. In most of the time-stretch applications, large temporal dispersion is highly desired to satisfy the far-field diffraction regime. However, most conventional spatial disperser or chirped fiber Bragg grating are constrained by its spatial volume, which can be overcome by the ultra-low-loss dispersive fiber, as an ideal medium for large temporal dispersion , while it suffers from the third-order dispersion and aberrations. In this paper, an optical phase conjugation based third-order dispersion compensation scheme is introduced, with accumulated dispersion and eliminated third dispersion, and achieved negative and positive 3400-ps2 pure temporal dispersion of over 30-nm bandwidth. Leveraging this pure temporal dispersion, up to 2% temporal aberrations have been eliminated; furthermore, a Fourier domain spectroscopy has achieved a record 15000 optical effective resolvable points, with non-degraded 2-pm resolution over 30-nm range

physics.optics↗