Searcharxiv⌕ Search

arXiv subjects

Feng Liu

Publications and source records attributed to Feng Liu.

At least 433 records · Page 24Linked to original sources
arXiv2023

Quantitative Susceptibility Mapping through Model-based Deep Image Prior (MoDIP)

The data-driven approach of supervised learning methods has limited applicability in solving dipole inversion in Quantitative Susceptibility Mapping (QSM) with varying scan parameters across different objects. To address this generalization issue in supervised QSM methods, we propose a novel training-free model-based unsupervised method called MoDIP (Model-based Deep Image Prior). MoDIP comprises a small, untrained network and a Data Fidelity Optimization (DFO) module. The network converges to an interim state, acting as an implicit prior for image regularization, while the optimization process enforces the physical model of QSM dipole inversion. Experimental results demonstrate MoDIP's excellent generalizability in solving QSM dipole inversion across different scan parameters. It exhibits robustness against pathological brain QSM, achieving over 32% accuracy improvement than supervised deep learning and traditional iterative methods. It is also 33% more computationally efficient and runs 4 times faster than conventional DIP-based approaches, enabling 3D high-resolution image reconstruction in under 4.5 minutes.

eess.IV↗
arXiv2023

Three-dimensional echo-shifted EPI with simultaneous blip-up and blip-down acquisitions for correcting geometric distortion

Purpose: Echo-planar imaging (EPI) with blip-up/down acquisition (BUDA) can provide high-quality images with minimal distortions by using two readout trains with opposing phase-encoding gradients. Because of the need for two separate acquisitions, BUDA doubles the scan time and degrades the temporal resolution when compared to single-shot EPI, presenting a major challenge for many applications, particularly functional MRI (fMRI). This study aims at overcoming this challenge by developing an echo-shifted EPI BUDA (esEPI-BUDA) technique to acquire both blip-up and blip-down datasets in a single shot. Methods: A three-dimensional (3D) esEPI-BUDA pulse sequence was designed by using an echo-shifting strategy to produce two EPI readout trains. These readout trains produced a pair of k-space datasets whose k-space trajectories were interleaved with opposite phase-encoding gradient directions. The two k-space datasets were separately reconstructed using a 3D SENSE algorithm, from which time-resolved B0-field maps were derived using TOPUP in FSL and then input into a forward model of joint parallel imaging reconstruction to correct for geometric distortion. In addition, Hankel structured low-rank constraint was incorporated into the reconstruction framework to improve image quality by mitigating the phase errors between the two interleaved k-space datasets. Results: The 3D esEPI-BUDA technique was demonstrated in a phantom and an fMRI study on healthy human subjects. Geometric distortions were effectively corrected in both phantom and human brain images. In the fMRI study, the visual activation volumes and their BOLD responses were comparable to those from conventional 3D echo-planar images. Conclusion: The improved imaging efficiency and dynamic distortion correction capability afforded by 3D esEPI-BUDA are expected to benefit many EPI applications.

physics.med-ph↗
arXiv2023

Time-to-event estimands and loss to follow-up in oncology in light of the estimands framework

Time-to-event estimands are central to many oncology clinical trials. The estimand framework (addendum to the ICH E9 guideline) calls for precisely defining the treatment effect of interest to align with the clinical question of interest and requires predefining the handling of intercurrent events that occur after treatment initiation and either preclude the observation of an event of interest or impact the interpretation of the treatment effect. We discuss a practical problem in clinical trial design and execution, i.e. in some clinical contexts it is not feasible to systematically follow patients to an event of interest. Loss to follow-up in the presence of intercurrent events can affect the meaning and interpretation of the study results. We provide recommendations for trial design, stressing the need for close alignment of the clinical question of interest and study design, impact on data collection and other practical implications. When patients cannot be systematically followed, compromise may be necessary to select the best available estimand that can be feasibly estimated under the circumstances. We discuss the use of sensitivity and supplementary analyses to examine assumptions of interest.

stat.AP↗
arXiv2023

Higher-order Topological Point State

Higher-order topological insulators (HOTIs) have attracted increasing interest as a unique class of topological quantum materials. One distinct property of HOTIs is the crystalline symmetry-imposed topological state at the lower-dimensional outer boundary, e.g. the zero-dimensional (0D) corner state of a 2D HOTI, used exclusively as a universal signature to identify higher-order topology but yet with uncertainty. Strikingly, we discover the existence of inner topological point states (TPS) in a 2D HOTI, as the embedded "end" states of 1D first-order TI, as exemplified by those located at the vacancies in a Kekule lattice. Significantly, we demonstrate that such inner TPS can be unambiguously distinguished from the trivial point-defect states, by their unique topology-endowed inter-TPS interaction and correlated magnetic response in spectroscopy measurements, overcoming an outstanding experimental challenge. Furthermore, based on first-principles calculations, we propose γ-graphyne as a promising material to observe the higher-order TPS. Our findings shed new light on our fundamental understanding of HOTIs, and also open an avenue to experimentally distinguishing and tuning TPS in the interior of a 2D sample for potential applications.

cond-mat.mtrl-sci↗
arXiv2023

Combustion Dynamics of Ten-injector Rocket Engine Using Flamelet Progress Variable

The combustion instability is investigated computationally for a ten-injector rocket engine using the compressible flamelet progress variable (FPV) model and detached eddy simulation (DES). An C++ code is developed based on OpenFOAM 4.1 to apply the combustion model. Flamelet tables are generated for methane/oxygen combustion at the background pressure of 200 bar using a 12-species chemical mechanism. The flames at this high pressure level are found having similar structures as those at much lower pressures. A power law is determined to rescale the reaction rate for the progress variable to address the pressure effect. The combustion is also simulated by the one-step-kinetics (OSK) model for comparison with the FPV model. Premixed and diffusion flames are identified locally for both the FPV and OSK models. Study of combustion instability shows that a combined first longitudinal and first tangential mode of 3200 Hz is dominant for the FPV model while the OSK model favors a pure first tangential mode of 2600 Hz. The coupling among pressure oscillation, unsteady transverse flow and helicity fluctuation is discussed. A preliminary study of the resonance in the injectors, which is driven by the acoustic oscillation in the combustion chamber, is also presented.

physics.flu-dyn↗
arXiv2023

Coherent control of a high-orbital hole in a semiconductor quantum dot

Coherently driven semiconductor quantum dots are one of the most promising platforms for non-classical light sources and quantum logic gates which form the foundation of photonic quantum technologies. However, to date, coherent manipulation of single charge carriers in quantum dots is limited mainly to their lowest orbital states. Ultrafast coherent control of high-orbital states is obstructed by the demand for tunable terahertz pulses. To break this constraint, we demonstrate an all-optical method to control high-orbital states of a hole via stimulated Auger process. The coherent nature of the Auger process is proved by Rabi oscillation and Ramsey interference. Harnessing this coherence further enables the investigation of single-hole relaxation mechanism. A hole relaxation time of 161 ps is observed and attributed to the phonon bottleneck effect. Our work opens new possibilities for understanding the fundamental properties of high-orbital states in quantum emitters and developing new types of orbital-based quantum photonic devices.

quant-ph↗
arXiv2023

Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation

Generating unlabeled data has been recently shown to help address the few-shot hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target domain with a few labeled target-domain data and a well-trained source-domain classifier (i.e., a source hypothesis), for the additional information of the highly-compatible unlabeled data. However, the generated data of the existing methods are extremely similar or even the same. The strong dependency among the generated data will lead the learning to fail. In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC). Specifically, DEG-Net will generate data via minimizing the HSIC value (i.e., maximizing the independence) among the semantic features of the generated data. By DEG-Net, the generated unlabeled data are more diverse and more effective for addressing the FHA problem. Experimental results show that the DEG-Net outperforms existing FHA baselines and further verifies that generating diverse data plays a vital role in addressing the FHA problem

cs.LG↗
arXiv2023

Learning Constrained Corner Node Trajectories of a Tether Net System for Space Debris Capture

The earth's orbit is becoming increasingly crowded with debris that poses significant safety risks to the operation of existing and new spacecraft and satellites. The active tether-net system, which consists of a flexible net with maneuverable corner nodes launched from a small autonomous spacecraft, is a promising solution for capturing and disposing of such space debris. The requirement of autonomous operation and the need to generalize over scenarios with debris scenarios in different rotational rates makes the capture process significantly challenging. The space debris could rotate about multiple axes, which, along with sensing/estimation and actuation uncertainties, calls for a robust, generalizable approach to guiding the net launch and flight - one that can guarantee robust capture. This paper proposes a decentralized actuation system combined with reinforcement learning for planning and controlling this tether-net system. In this new system, four microsatellites with cold gas type thrusters act as the corner nodes of the net and can thus help control or correct the flight of the net after launch. The microsatellites pull the net to complete the task of approaching and capturing the space debris. The proposed method uses a RL framework that integrates a proximal policy optimization to find the optimal solution based on the dynamics simulation of the net and the microsatellites performed in Vortex Studio. The RL framework finds the optimal trajectory that is both fuel-efficient and ensures a desired level of capture quality.

eess.SY↗
arXiv2023

CoverHunter: Cover Song Identification with Refined Attention and Alignments

Abstract: Cover song identification (CSI) focuses on finding the same music with different versions in reference anchors given a query track. In this paper, we propose a novel system named CoverHunter that overcomes the shortcomings of existing detection schemes by exploring richer features with refined attention and alignments. CoverHunter contains three key modules: 1) A convolution-augmented transformer (i.e., Conformer) structure that captures both local and global feature interactions in contrast to previous methods mainly relying on convolutional neural networks; 2) An attention-based time pooling module that further exploits the attention in the time dimension; 3) A novel coarse-to-fine training scheme that first trains a network to roughly align the song chunks and then refines the network by training on the aligned chunks. At the same time, we also summarize some important training tricks used in our system that help achieve better results. Experiments on several standard CSI datasets show that our method significantly improves over state-of-the-art methods with an embedding size of 128 (2.3% on SHS100K-TEST and 17.7% on DaTacos).

cs.SD↗
arXiv2023

Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing

Biometric systems are vulnerable to Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for the generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD. During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing generative loss. While De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. The source code of the proposed technique is available at https://github.com/kongzhecn/dfdm.

cs.CV↗
arXiv2023

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score

Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. Unfortunately, estimating or comparing two data distributions is extremely difficult, especially in high-dimension spaces. Recently, the gradient of log probability density (a.k.a., score) w.r.t. the sample is used as an alternative statistic to compute. However, we find that the score is sensitive in identifying adversarial samples due to insufficient information with one sample only. In this paper, we propose a new statistic called expected perturbation score (EPS), which is essentially the expected score of a sample after various perturbations. Specifically, to obtain adequate information regarding one sample, we perturb it by adding various noises to capture its multi-view observations. We theoretically prove that EPS is a proper statistic to compute the discrepancy between two samples under mild conditions. In practice, we can use a pre-trained diffusion model to estimate EPS for each sample. Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples. We also prove that the EPS-based MMD between natural and adversarial samples is larger than that among natural samples. Extensive experiments show the superior adversarial detection performance of our EPS-AD.

cs.LG↗
arXiv2023

DADIN: Domain Adversarial Deep Interest Network for Cross Domain Recommender Systems

Click-Through Rate (CTR) prediction is one of the main tasks of the recommendation system, which is conducted by a user for different items to give the recommendation results. Cross-domain CTR prediction models have been proposed to overcome problems of data sparsity, long tail distribution of user-item interactions, and cold start of items or users. In order to make knowledge transfer from source domain to target domain more smoothly, an innovative deep learning cross-domain CTR prediction model, Domain Adversarial Deep Interest Network (DADIN) is proposed to convert the cross-domain recommendation task into a domain adaptation problem. The joint distribution alignment of two domains is innovatively realized by introducing domain agnostic layers and specially designed loss, and optimized together with CTR prediction loss in a way of adversarial training. It is found that the Area Under Curve (AUC) of DADIN is 0.08% higher than the most competitive baseline on Huawei dataset and is 0.71% higher than its competitors on Amazon dataset, achieving the state-of-the-art results on the basis of the evaluation of this model performance on two real datasets. The ablation study shows that by introducing adversarial method, this model has respectively led to the AUC improvements of 2.34% on Huawei dataset and 16.67% on Amazon dataset.

cs.IR↗
arXiv2023

Attacking Perceptual Similarity Metrics

Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the addition of an imperceptible distortion can still compromise these metrics. In our study, we systematically examine the robustness of these metrics to imperceptible adversarial perturbations. Following the two-alternative forced-choice experimental design with two distorted images and one reference image, we perturb the distorted image closer to the reference via an adversarial attack until the metric flips its judgment. We first show that all metrics in our study are susceptible to perturbations generated via common adversarial attacks such as FGSM, PGD, and the One-pixel attack. Next, we attack the widely adopted LPIPS metric using spatial-transformation-based adversarial perturbations (stAdv) in a white-box setting to craft adversarial examples that can effectively transfer to other similarity metrics in a black-box setting. We also combine the spatial attack stAdv with PGD ($\ell_\infty$-bounded) attack to increase transferability and use these adversarial examples to benchmark the robustness of both traditional and recently developed metrics. Our benchmark provides a good starting point for discussion and further research on the robustness of metrics to imperceptible adversarial perturbations.

cs.CV↗
arXiv2023

Anisotropic-Isotropic Transition of Cages at the Glass Transition

Characterizing the local structural evolution is an essential step in understanding the nature of glass transition. In this work, we probe the evolution of Voronoi cell geometry in simple glass models, and find that the individual particle cages deform anisotropically in supercooled liquid and isotropically in glass. We introduce an anisotropy parameter $k$ for each Voronoi cell, which mean value exhibits a sharp change at the mode-coupling glass transition $ϕ_\mathrm{c}$. Moreover, a power law of packing fraction $ϕ\propto q_1^{-d}$ is discovered in the liquid regime with $d>D$, in contrast to $d=D$ in the glass regime, where $q_1$ is the first peak position of structure factor, and $D$ is the space dimension. This power law is explained by the change of $k$. The active motions in supercooled liquid are spatially correlated with long axes rather than short axes of Voronoi cells. In addition, the dynamic slowing down approaching the glass transition can be well characterized through a modified free volume model based on $k$. These findings reveal that the nonagnostic structural parameter $k$ determines glassy dynamics and is effective in identifying the structure-dynamics correlations and the glass transition.

cond-mat.soft↗
arXiv2023

Anomalous Bilayer Quantum Hall Effect

In parallel to the condensed-matter realization of quantum Hall (Chern insulators), quantum spin Hall (topological insulators), and fractional quantum Hall (fractional Chern insulators) effects, we propose that bilayer flat band (FB) lattices with one FB in each layer constitute solid-state analogues of bilayer quantum Hall (BQH) system, leading to anomalous BQH (ABQH) effect, without magnetic field. By exact diagonalization of a bilayer Kagome lattice Hamiltonian, as a prototypical example, we demonstrate the stabilization of excitonic condensate Halperin's (1,1,1) state at the total filling $v_T=1$ of the two Fbs. Furthermore, by tuning the inter-layer tunneling and distance between the Kagome layers at $v_T=2/3$, we show phase transitions among Halperin's (3,3,0), spin-singlet (1,1,2), and particle-hole conjugate of Laughlin's 1/3 states, as previously observed in BQH systems. Our work opens a new research direction in the field of FB physics by demonstrating bilayer FB materials as an attractive avenue for realizing exotic ABQH states including non-Abelian anyons.

cond-mat.str-el↗
arXiv2023

DCFace: Synthetic Face Generation with Dual Condition Diffusion Model

Generating synthetic datasets for training face recognition models is challenging because dataset generation entails more than creating high fidelity images. It involves generating multiple images of same subjects under different factors (\textit{e.g.}, variations in pose, illumination, expression, aging and occlusion) which follows the real image conditional distribution. Previous works have studied the generation of synthetic datasets using GAN or 3D models. In this work, we approach the problem from the aspect of combining subject appearance (ID) and external factor (style) conditions. These two conditions provide a direct way to control the inter-class and intra-class variations. To this end, we propose a Dual Condition Face Generator (DCFace) based on a diffusion model. Our novel Patch-wise style extractor and Time-step dependent ID loss enables DCFace to consistently produce face images of the same subject under different styles with precise control. Face recognition models trained on synthetic images from the proposed DCFace provide higher verification accuracies compared to previous works by $6.11\%$ on average in $4$ out of $5$ test datasets, LFW, CFP-FP, CPLFW, AgeDB and CALFW. Code is available at https://github.com/mk-minchul/dcface

cs.CV↗
arXiv2023

AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation

To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs. However, downsizing inputs makes the estimation more challenging because objects and motion ranges become smaller. Even though recent approaches have demonstrated high-quality flow estimation, they tend to fail to accurately model small objects and precise boundaries when the input resolution is lowered, restricting their applicability to high-resolution inputs. In this paper, we introduce AnyFlow, a robust network that estimates accurate flow from images of various resolutions. By representing optical flow as a continuous coordinate-based representation, AnyFlow generates outputs at arbitrary scales from low-resolution inputs, demonstrating superior performance over prior works in capturing tiny objects with detail preservation on a wide range of scenes. We establish a new state-of-the-art performance of cross-dataset generalization on the KITTI dataset, while achieving comparable accuracy on the online benchmarks to other SOTA methods.

cs.CV↗
arXiv2023

Distortion-Corrected Image Reconstruction with Deep Learning on an MRI-Linac

Magnetic resonance imaging (MRI) is increasingly utilized for image-guided radiotherapy due to its outstanding soft-tissue contrast and lack of ionizing radiation. However, geometric distortions caused by gradient nonlinearity (GNL) limit anatomical accuracy, potentially compromising the quality of tumour treatments. In addition, slow MR acquisition and reconstruction limit the potential for real-time image guidance. Here, we demonstrate a deep learning-based method that rapidly reconstructs distortion-corrected images from raw k-space data for real-time MR-guided radiotherapy applications. We leverage recent advances in interpretable unrolling networks to develop a Distortion-Corrected Reconstruction Network (DCReconNet) that applies convolutional neural networks (CNNs) to learn effective regularizations and nonuniform fast Fourier transforms for GNL-encoding. DCReconNet was trained on a public MR brain dataset from eleven healthy volunteers for fully sampled and accelerated techniques including parallel imaging (PI) and compressed sensing (CS). The performance of DCReconNet was tested on phantom and volunteer brain data acquired on a 1.0T MRI-Linac. The DCReconNet, CS- and PI-based reconstructed image quality was measured by structural similarity (SSIM) and root-mean-squared error (RMSE) for numerical comparisons. The computation time for each method was also reported. Phantom and volunteer results demonstrated that DCReconNet better preserves image structure when compared to CS- and PI-based reconstruction methods. DCReconNet resulted in highest SSIM (0.95 median value) and lowest RMSE (<0.04) on simulated brain images with four times acceleration. DCReconNet is over 100-times faster than iterative, regularized reconstruction methods. DCReconNet provides fast and geometrically accurate image reconstruction and has potential for real-time MRI-guided radiotherapy applications.

physics.med-ph↗