arXiv subjects

Chen Liu

Publications and source records attributed to Chen Liu.

At least 253 records · Page 14Linked to original sources

arXiv2020

Substituting Gadolinium in Brain MRI Using DeepContrast

Cerebral blood volume (CBV) is a hemodynamic correlate of oxygen metabolism and reflects brain activity and function. High-resolution CBV maps can be generated using the steady-state gadolinium-enhanced MRI technique. Such a technique requires an intravenous injection of exogenous gadolinium based contrast agent (GBCA) and recent studies suggest that the GBCA can accumulate in the brain after frequent use. We hypothesize that endogenous sources of contrast might exist within the most conventional and commonly acquired structural MRI, potentially obviating the need for exogenous contrast. Here, we test this hypothesis by developing and optimizing a deep learning algorithm, which we call DeepContrast, in mice. We find that DeepContrast performs equally well as exogenous GBCA in mapping CBV of the normal brain tissue and enhancing glioblastoma. Together, these studies validate our hypothesis that a deep learning approach can potentially replace the need for GBCAs in brain MRI.

q-bio.QM↗

arXiv2020

Experimental Realization of Two-Dimensional Buckled Lieb lattice

Two-dimensional (2D) materials with a Lieb lattice can host exotic electronic band structures. Such a system does not exist in nature, and it is also difficult to obtain in the laboratory due to its structural instability. Here, we experimentally realized a 2D system composed of a tin overlayer on an aluminum substrate by molecular beam epitaxy. The specific arrangement of Sn atoms on the Al(100) surface, which benefits from favorable interface interactions, forms a stabilized buckled Lieb lattice. Our theoretical calculations indicate a partially broken nodal line loop protected by its mirror reflection symmetry and a topologically nontrivial insulating state with a spin-orbital coupling (SOC) effect in the band structure of this Lieb lattice. The electronic structure of this system has also been experimentally characterized by scanning tunnelling spectroscopy and angle-resolved photoemmision spectroscopy. Our work provides an appealing method for constructing 2D quantum materials based on the Lieb lattice.

cond-mat.mtrl-sci↗

arXiv2019

Coherent and Controllable Outfit Generation

When thinking about dressing oneself, people often have a theme in mind whether they're going to a tropical getaway or wish to appear attractive at a cocktail party. A useful outfit generation system should come up with clothing items that are compatible while matching a theme specified by the user. Existing methods use item-wise compatibility between products but lack an effective way to enforce a global constraint (e.g., style, occasion). We introduce a method that generates outfits whose items match a theme described by a text query. Our method uses text and image embeddings to represent fashion items. We learn a multimodal embedding where the image representation for an item is close to its text representation, and use this embedding to measure item-query coherence. We then use a discriminator to compute compatibility between fashion items. This strategy yields a compatibility prediction method that meets or exceeds the state of the art. Our method combines item-item compatibility and item-query coherence to construct an outfit whose items are (a) close to the query and (b) compatible with one another. Quantitative evaluation shows that the items in our outfits are tightly clustered compared to standard outfits. Furthermore, outfits produced by similar queries are close to one another, and outfits produced by very different queries are far apart. Qualitative evaluation shows that our method responds well to queries. A user study suggests that people understand the match between the queries and the outfits produced by our method.

cs.CV↗

arXiv2019

Exploring Multilingual Syntactic Sentence Representations

We study methods for learning sentence embeddings with syntactic structure. We focus on methods of learning syntactic sentence-embeddings by using a multilingual parallel-corpus augmented by Universal Parts-of-Speech tags. We evaluate the quality of the learned embeddings by examining sentence-level nearest neighbours and functional dissimilarity in the embedding space. We also evaluate the ability of the method to learn syntactic sentence-embeddings for low-resource languages and demonstrate strong evidence for transfer learning. Our results show that syntactic sentence-embeddings can be learned while using less training data, fewer model parameters, and resulting in better evaluation metrics than state-of-the-art language models.

cs.CL↗

arXiv2019

DENS: A Dataset for Multi-class Emotion Analysis

We introduce a new dataset for multi-class emotion analysis from long-form narratives in English. The Dataset for Emotions of Narrative Sequences (DENS) was collected from both classic literature available on Project Gutenberg and modern online narratives available on Wattpad, annotated using Amazon Mechanical Turk. A number of statistics and baseline benchmarks are provided for the dataset. Of the tested techniques, we find that the fine-tuning of a pre-trained BERT model achieves the best results, with an average micro-F1 score of 60.4%. Our results show that the dataset provides a novel opportunity in emotion analysis that requires moving beyond existing sentence-level techniques.

cs.CL↗

arXiv2019

Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path

This paper proposes a new approach for automated floorplan reconstruction from RGBD scans, a major milestone in indoor mapping research. The approach, dubbed Floor-SP, formulates a novel optimization problem, where room-wise coordinate descent sequentially solves dynamic programming to optimize the floorplan graph structure. The objective function consists of data terms guided by deep neural networks, consistency terms encouraging adjacent rooms to share corners and walls, and the model complexity term. The approach does not require corner/edge detection with thresholds, unlike most other methods. We have evaluated our system on production-quality RGBD scans of 527 apartments or houses, including many units with non-Manhattan structures. Qualitative and quantitative evaluations demonstrate a significant performance boost over the current state-of-the-art. Please refer to our project website http://jcchen.me/floor-sp/ for code and data.

cs.CV↗

arXiv2019

Semantic Parsing with Dual Learning

Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing framework with the dual learning algorithm, which enables a semantic parser to make full use of data (labeled and even unlabeled) through a dual-learning game. This game between a primal model (semantic parsing) and a dual model (logical form to query) forces them to regularize each other, and can achieve feedback signals from some prior-knowledge. By utilizing the prior-knowledge of logical form structures, we propose a novel reward signal at the surface and semantic levels which tends to generate complete and reasonable logical forms. Experimental results show that our approach achieves new state-of-the-art performance on ATIS dataset and gets competitive performance on Overnight dataset.

cs.CL↗

arXiv2019

On Certifying Non-uniform Bound against Adversarial Attacks

This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In contrast to the existing approaches that seek regions bounded uniformly along all input features, we consider non-uniform bounds and use it to study the decision boundary of neural network models. We formulate our target as an optimization problem with nonlinear constraints. Then, a framework applicable for general feedforward neural networks is proposed to bound the output logits so that the relaxed problem can be solved by the augmented Lagrangian method. Our experiments show the non-uniform bounds have larger volumes than uniform ones and the geometric similarity of the non-uniform bounds gives a quantitative, data-agnostic metric of input features' robustness. Further, compared with normal models, the robust models have even larger non-uniform bounds and better interpretability.

cs.LG↗

arXiv2019

PhyCode: A Practical Wireless Communication System Exploiting Superimposed Signals

Superimposed signals are anticipated to improve wireless spectrum efficiency to support the ever-growing IoT applications. Implementing the superimposed signal demands on ideally aligned signals in both the time and frequency domains. Prior work applied an average carrier-frequency offset compensation to the superimposed signal under the assumptions of homogeneous devices and static environments. However, this will cause a significant signal distortion in practice when heterogeneous IoT devices are involved in a dynamic environment. This paper presents PhyCode, which exploits the nature of varying offsets across devices, and designs a dynamic decoding scheme which can react to the exact offsets from different signal sources simultaneously. We implement PhyCode via a software-defined radio platform and demonstrate that PhyCode achieves a lower raw BER compared with the existing state-of-the-art method.

eess.SP↗

arXiv2019

Spin image of an atomic vapor cell with a resolution smaller than the diffusion crosstalk free distance

The diffusion crosstalk free distance is an important parameter for spin images in atomic vapor cells and is also regarded as a limit on the spatial resolution. However, by modulating the pumping light both spatially and temporally using a digital micromirror device, a spin image of a vapor cell has been obtained with a distinguishable stripe width of 13.7~$μ$m, which is much smaller than the corresponding diffusion crosstalk free distance of $\sim$138~$μ$m. The fundamental limit on the spatial resolution as determined by diffusion and the uncertainty principle is analyzed.

physics.atom-ph↗

arXiv2019

MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold sparse convolution [3], processes a voxelized point cloud and predicts semantic scores for each occupied voxel as well as the affinity between neighboring voxels at different scales. A simple yet effective clustering algorithm segments points into instances based on the predicted affinity and the mesh topology. The semantic for each instance is determined by the semantic prediction. Experiments show that our method outperforms the state-of-the-art instance segmentation methods by a large margin on the widely used ScanNet benchmark [2]. We share our code publicly at https://github.com/art-programmer/MASC.

cs.CV↗

arXiv2019

Secrecy Outage Analysis of Non-Orthogonal Spectrum Sharing for Heterogeneous Cellular Networks

In this paper, we investigate physical-layer security for a heterogeneous cellular network consisting of a macro cell and a small cell in the presence of a passive eavesdropper that intends to tap both the macro-cell and small-cell transmissions. Both the orthogonal spectrum sharing (OSS) and non-orthogonal spectrum sharing (NOSS) are considered for the heterogeneous cellular network. The OSS allows the macro cell and small cell to access a given spectrum band in an orthogonal manner, whereas the NOSS enables them to access the same spectrum simultaneously and mutual interference exits. As a consequence, we present two NOSS schemes, namely the interference-limited NOSS (IL-NOSS) and interference-canceled NOSS (IC-NOSS), where the mutual interference is constrained below a tolerable level in the IL-NOSS through power control and the IC-NOSS scheme exploits a specially-designed signal for canceling out the interference received a legitimate cellular user while confusing the passive eavesdropper. We derive closed-form expressions for an overall secrecy outage probability of the OSS, IL-NOSS, and IC-NOSS schemes, which take into account the transmission secrecy of both the macro cell and small cell. We further characterize the secrecy diversity of OSS, IL-NOSS and IC-NOSS schemes through an asymptotic secrecy outage analysis in the high signal-to-noise ratio region. It is shown that the OSS and IL-NOSS methods obtain the same secrecy diversity gain of zero only, and a higher secrecy diversity gain of one is achieved by the IC-NOSS scheme. Additionally, numerical results demonstrate that the IC-NOSS scheme significantly performs better than the OSS and IL-NOSS methods in terms of the overall secrecy outage probability.

cs.IT↗

arXiv2019

PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image

This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN employs a variant of Mask R-CNN to detect planes with their plane parameters and segmentation masks. PlaneRCNN then jointly refines all the segmentation masks with a novel loss enforcing the consistency with a nearby view during training. The paper also presents a new benchmark with more fine-grained plane segmentations in the ground-truth, in which, PlaneRCNN outperforms existing state-of-the-art methods with significant margins in the plane detection, segmentation, and reconstruction metrics. PlaneRCNN makes an important step towards robust plane extraction, which would have an immediate impact on a wide range of applications including Robotics, Augmented Reality, and Virtual Reality.

cs.CV↗

arXiv2018

Deep Heterogeneous Autoencoders for Collaborative Filtering

This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems. We propose a model that learns a shared feature space from heterogeneous data, such as item descriptions, product tags and online purchase history, to obtain better predictions. Our model consists of autoencoders, not only for numerical and categorical data, but also for sequential data, which enables capturing user tastes, item characteristics and the recent dynamics of user preference. We learn the autoencoder architecture for each data source independently in order to better model their statistical properties. Our evaluation on two MovieLens datasets and an e-commerce dataset shows that mean average precision and recall improve over state-of-the-art methods.

cs.LG↗

arXiv2018

Darcy law for yield stress fluid

Predicting the flow of non-Newtonian fluids in porous structure is still a challenging issue due to the interplay betwen the microscopic disorder and the non-linear rheology. In this letter, we study the case of an yield stress fluid in a two-dimensional structure. Thanks to a performant optimization algorithm, we show that the system undergoes a continuous phase transition in the behavior of the flow controlled by the applied pressure drop. In analogy with the studies of the plastic depinning of vortex lattices in high-$T_c$ superconductors we characterize the nonlinearity of the flow curve and relate it to the change in the geometry of the open channels. In particular, close to the transition, an universal scale free distribution of the channel length is observed and explained theoretically via a mapping to the KPZ equation.

cond-mat.soft↗

arXiv2018

Numerical analysis of a discontinuous Galerkin method for Cahn-Hilliard-Navier-Stokes equations

In this paper, we derive a theoretical analysis of an interior penalty discontinuous Galerkin methods for solving the Cahn-Hilliard-Navier-Stokes model problem. We prove unconditional unique solvability of the discrete system, obtain unconditional discrete energy dissipation law, and derive stability bounds with a generalized chemical energy density. Convergence of the method is obtained by proving optimal a priori error estimates. Our analysis of the unique solvability is valid for both symmetric and non-symmetric versions of the discontinuous Galerkin formulation.

math.NA↗

arXiv2018

Finding Mixed Nash Equilibria of Generative Adversarial Networks

We reconsider the training objective of Generative Adversarial Networks (GANs) from the mixed Nash Equilibria (NE) perspective. Inspired by the classical prox methods, we develop a novel algorithmic framework for GANs via an infinite-dimensional two-player game and prove rigorous convergence rates to the mixed NE, resolving the longstanding problem that no provably convergent algorithm exists for general GANs. We then propose a principled procedure to reduce our novel prox methods to simple sampling routines, leading to practically efficient algorithms. Finally, we provide experimental evidence that our approach outperforms methods that seek pure strategy equilibria, such as SGD, Adam, and RMSProp, both in speed and quality.

cs.LG↗

arXiv2018

Creep dynamics of athermal amorphous materials: a mesoscopic approach

Yield stress fluids display complex dynamics, in particular when driven into the transient regime between the solid and the flowing state. Inspired by creep experiments on dense amorphous materials, we implement mesocale elasto-plastic descriptions to analyze such transient dynamics in athermal systems. Both our mean-field and space-dependent approaches consistently reproduce the typical experimental strain rate responses to different applied steps in stress. Moreover, they allow us to understand basic processes involved in the strain rate slowing down (creep) and the strain rate acceleration (fluidization) phases. The fluidization time increases in a power-law fashion as the applied external stress approaches a static yield stress. This stress value is related to the stress over-shoot in shear start-up experiments, and it is known to depend on sample preparation and age. By calculating correlations of the accumulated plasticity in the spatially resolved model, we reveal different modes of cooperative motion during the creep dynamics.

cond-mat.soft↗