arXiv subjects

Yi Liu

Publications and source records attributed to Yi Liu.

At least 595 records · Page 33Linked to original sources

arXiv2022

Improved-Flow Warp Module for Remote Sensing Semantic Segmentation

Remote sensing semantic segmentation aims to assign automatically each pixel on aerial images with specific label. In this letter, we proposed a new module, called improved-flow warp module (IFWM), to adjust semantic feature maps across different scales for remote sensing semantic segmentation. The improved-flow warp module is applied along with the feature extraction process in the convolutional neural network. First, IFWM computes the offsets of pixels by a learnable way, which can alleviate the misalignment of the multi-scale features. Second, the offsets help with the low-resolution deep feature up-sampling process to improve the feature accordance, which boosts the accuracy of semantic segmentation. We validate our method on several remote sensing datasets, and the results prove the effectiveness of our method..

cs.CV↗

arXiv2022

de Haas-van Alphen effect and the first-principles study of the possible topological stannide Cu$_3$Sn

The quest for quantum materials with diverse symmetry-protected topological states has been the focus of recent research interest, primarily due to their fascinating physical properties and the potential technological utility. In this work, we report on the magnetotransport, de Haas-van Alphen (dHvA) oscillations, and the first-principles calculations of the stannide Cu$_3$Sn that is isostructural with the recently reported topological semimetal Ag$_3$Sn. The magnetoresistance was found to vary quasi-linearly in field. Clear dHvA oscillations were observed under a field as low as 1 Tesla at 2 K, with three major oscillation frequencies $F_α$=8.74 T, $F_β$=150.19 T and $F_γ$=229.66 T and extremely small effective masses. The analysis of dHvA quantum oscillations revealed a possible nonzero Berry phase, suggestive of the nontrivial band topology. The corroborating evidence for the nontrivial electronic topology also comes from the first-principles calculations which yield a nonzero $\mathbb{Z}_2$ topological index. These results collectively suggest that Cu$_3$Sn, in analogy to its homologue Ag$_3$Sn, may be another intermetallic stannide hosting topological Dirac fermions.

cond-mat.mtrl-sci↗

arXiv2022

Sub-MHz spectral dip in a resonator-free twisted gain medium

Ultra-narrow optical spectral features resulting from highly dispersive light-matter interactions are essential for a broad range of applications such as spectroscopy, slow-light, and high-precision sensing. Features approaching sub-MHz, or equivalently, Q-factors approaching ~1 billion and beyond, are challenging to obtain in solid-state systems, ultimately limited by loss. We present a novel approach to achieve tunable sub-MHz spectral features, at room temperature, without resonators. We exploit gain-enhanced polarization pulling in a twisted birefringent medium where polarization eigenmodes are frequency-dependent. Using Brillouin gain in a commercial spun fiber, we experimentally achieve a 0.72 MHz spectral dip, the narrowest backward Brillouin scattering feature ever reported. Further optimization can potentially reduce the linewidth to <0.1 MHz. Our approach is simple and broadly applicable, offering on-demand tunability and high sensitivity, with a wide range of applications such as microwave photonic filters, slow and fast light, and optical sensing.

physics.optics↗

arXiv2022

Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses

Semi-supervised Federated Learning (SSFL) has recently drawn much attention due to its practical consideration, i.e., the clients may only have unlabeled data. In practice, these SSFL systems implement semi-supervised training by assigning a "guessed" label to the unlabeled data near the labeled data to convert the unsupervised problem into a fully supervised problem. However, the inherent properties of such semi-supervised training techniques create a new attack surface. In this paper, we discover and reveal a simple yet powerful poisoning attack against SSFL. Our attack utilizes the natural characteristic of semi-supervised learning to cause the model to be poisoned by poisoning unlabeled data. Specifically, the adversary just needs to insert a small number of maliciously crafted unlabeled samples (e.g., only 0.1\% of the dataset) to infect model performance and misclassification. Extensive case studies have shown that our attacks are effective on different datasets and common semi-supervised learning methods. To mitigate the attacks, we propose a defense, i.e., a minimax optimization-based client selection strategy, to enable the server to select the clients who hold the correct label information and high-quality updates. Our defense further employs a quality-based aggregation rule to strengthen the contributions of the selected updates. Evaluations under different attack conditions show that the proposed defense can well alleviate such unlabeled poisoning attacks. Our study unveils the vulnerability of SSFL to unlabeled poisoning attacks and provides the community with potential defense methods.

cs.LG↗

arXiv2022

Virtual homological eigenvalues and the Weil--Petersson translation length

For any pseudo-Anosov automorphism on an orientable closed surface, an inquality is established bounding certain growth of virtual homological eigenvalues with the Weil--Petersson translation length. The new inquality fits nicely with other known inequalities due to Kojima and McShane, and due to Lê. The new quantity to be considered is the square sum of the logarithmic radii of the homological eigenvalues (with multiplicity) outside the complex unit circle, called the homological Jensen square sum. The main theorem is as follows. For any cofinal sequence of regular finite covers of a given surface, together with lifts of a given pseudo-Anosov, the homological Jensen square sum of the lifts grows at most linearly fast compared to the covering degree, and the square root of the growth rate is at most $1/\sqrt{4π}$ times the Weil--Petersson translation length of the given pseudo-Anosov.

math.GT↗

arXiv2022

Rate-Constrained Shaping Codes for Finite-State Channels With Cost

Shaping codes are used to generate code sequences in which the symbols obey a prescribed probability distribution. They arise naturally in the context of source coding for noiseless channels with unequal symbol costs. Recently, shaping codes have been proposed to extend the lifetime of flash memory and reduce DNA synthesis time. In this paper, we study a general class of shaping codes for noiseless finite-state channels with cost and i.i.d. sources. We establish a relationship between the code rate and minimum average symbol cost. We then determine the rate that minimizes the average cost per source symbol (total cost). An equivalence is established between codes minimizing average symbol cost and codes minimizing total cost, and a separation theorem is proved, showing that optimal shaping can be achieved by a concatenation of optimal compression and optimal shaping for a uniform i.i.d. source.

cs.IT↗

arXiv2022

Morest: Model-based RESTful API Testing with Execution Feedback

RESTful APIs are arguably the most popular endpoints for accessing Web services. Blackbox testing is one of the emerging techniques for ensuring the reliability of RESTful APIs. The major challenge in testing RESTful APIs is the need for correct sequences of API operation calls for in-depth testing. To build meaningful operation call sequences, researchers have proposed techniques to learn and utilize the API dependencies based on OpenAPI specifications. However, these techniques either lack the overall awareness of how all the APIs are connected or the flexibility of adaptively fixing the learned knowledge. In this paper, we propose Morest, a model-based RESTful API testing technique that builds and maintains a dynamically updating RESTful-service Property Graph (RPG) to model the behaviors of RESTful-services and guide the call sequence generation. We empirically evaluated Morest and the results demonstrate that Morest can successfully request an average of 152.66%-232.45% more API operations, cover 26.16%-103.24% more lines of code, and detect 40.64%-215.94% more bugs than state-of-the-art techniques. In total, we applied Morest to 6 real-world projects and found 44 bugs (13 of them cannot be detected by existing approaches). Specifically, 2 of the confirmed bugs are from Bitbucket, a famous code management service with more than 6 million users.

cs.SE↗

arXiv2022

Bulk domain Meissner state in the ferromagnetic superconductor EuFe$_{2}$(As$_{0.8}$P$_{0.2}$)$_{2}$: Consequence of compromise between ferromagnetism and superconductivity

Small-angle neutron scattering (SANS) measurements are performed on the ferromagnetic superconductor EuFe$_{2}$(As$_{0.8}$P$_{0.2}$)$_{2}$ ($T\rm_{sc}=22.5\,$K) to probe the delicate interplay between ferromagnetism and superconductivity. A clear signature of large ferromagnetic domains is found below the ferromagnetic ordering temperature $T\rm_{C}$ = 18.5 K. In a small temperature interval of $\sim$ 1.5 K below $T\rm_{C}$, additional SANS signal is observed, of which the indirect Fourier transform reveals characteristic length scales in between $\sim$ 80 nm to $\sim$ 160 nm. These nanometer-scaled domain structures are identified to result from an intermediate inhomogeneous Meissner effect denoted domain Meissner state, which was recently observed on the surface of EuFe$_{2}$(As$_{0.79}$P$_{0.21}$)$_{2}$ crystals by means of magnetic force microscopy [V. S. Stolyarov $\mathit{et}$ $\mathit{al.}$, Sci. Adv. 4, 1061 (2018)], ascribing to the competition between ferromagnetism and superconductivity. Our measurements clearly render the domain Meissner state as a bulk phenomenon and provide a key solution to the mystery regarding the intriguing coexistence of strong ferromagnetism and bulk superconductivity in these compounds.

cond-mat.supr-con↗

arXiv2022

PP-Matting: High-Accuracy Natural Image Matting

Natural image matting is a fundamental and challenging computer vision task. It has many applications in image editing and composition. Recently, deep learning-based approaches have achieved great improvements in image matting. However, most of them require a user-supplied trimap as an auxiliary input, which limits the matting applications in the real world. Although some trimap-free approaches have been proposed, the matting quality is still unsatisfactory compared to trimap-based ones. Without the trimap guidance, the matting models suffer from foreground-background ambiguity easily, and also generate blurry details in the transition area. In this work, we propose PP-Matting, a trimap-free architecture that can achieve high-accuracy natural image matting. Our method applies a high-resolution detail branch (HRDB) that extracts fine-grained details of the foreground with keeping feature resolution unchanged. Also, we propose a semantic context branch (SCB) that adopts a semantic segmentation subtask. It prevents the detail prediction from local ambiguity caused by semantic context missing. In addition, we conduct extensive experiments on two well-known benchmarks: Composition-1k and Distinctions-646. The results demonstrate the superiority of PP-Matting over previous methods. Furthermore, we provide a qualitative evaluation of our method on human matting which shows its outstanding performance in the practical application. The code and pre-trained models will be available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.

cs.CV↗

arXiv2022

Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images

Rotated object detection in aerial images is a meaningful yet challenging task as objects are densely arranged and have arbitrary orientations. The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions. As ln-norm losses are mainly based on non-scale-invariant Minkowski distance, using ln-norm losses will lead to inconsistency with the detection metric rotational Intersection-over-Union (IoU) and training instability. To address the problems, we use Mahalanobis distance to calculate loss between the predicted and the target box vertices' vectors, proposing a new loss function called Mahalanobis Distance Loss (MDL) for eight-parameter rotated object detection. As Mahalanobis distance is scale-invariant, MDL is more consistent with detection metric and more stable during training than ln-norm losses. To alleviate the problem of boundary discontinuity like all other eight-parameter methods, we further take the minimum loss value to make MDL continuous at boundary cases. We achieve state-of-art performance on DOTA-v1.0 with the proposed method MDL. Furthermore, compared to the experiment that uses smooth L1 loss, we find that MDL performs better in rotated object detection.

cs.CV↗

arXiv2022

PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we propose PP-LiteSeg, a novel lightweight model for the real-time semantic segmentation task. Specifically, we present a Flexible and Lightweight Decoder (FLD) to reduce computation overhead of previous decoder. To strengthen feature representations, we propose a Unified Attention Fusion Module (UAFM), which takes advantage of spatial and channel attention to produce a weight and then fuses the input features with the weight. Moreover, a Simple Pyramid Pooling Module (SPPM) is proposed to aggregate global context with low computation cost. Extensive evaluations demonstrate that PP-LiteSeg achieves a superior trade-off between accuracy and speed compared to other methods. On the Cityscapes test set, PP-LiteSeg achieves 72.0% mIoU/273.6 FPS and 77.5% mIoU/102.6 FPS on NVIDIA GTX 1080Ti. Source code and models are available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.

cs.CV↗

arXiv2022

A Weak Galerkin Mixed Finite Element Method for second order elliptic equations on 2D Curved Domains

This article concerns the weak Galerkin mixed finite element method (WG-MFEM) for second order elliptic equations on 2D domains with curved boundary. The Neumann boundary condition is considered since it becomes the essential boundary condition in this case. It is well-known that the discrepancy between the curved physical domain and the polygonal approximation domain leads to a loss of accuracy for discretization with polynomial order $α>1$. The purpose of this paper is two-fold. First, we present a detailed error analysis of the original WG-MFEM for solving problems on curved domains, which exhibits an $O(h^{1/2})$ convergence for all $α\ge 1$. It is a little surprising to see that even the lowest-order WG-MFEM ($α=1$) experiences a loss of accuracy. This is different from known results for the finite element method (FEM) or the mixed FEM, and appears to be a combined effect of the WG-MFEM design and the fact that the outward normal vector on the polygonal approximation domain is different from the one on the curved domain. Second, we propose a remedy to bring the approximation rate back to optimal by employing two techniques. One is a specially designed boundary correction technique. The other is to take full advantage of the nice feature that weak Galerkin discretization can be defined on polygonal meshes, which allows the curved boundary to be better approximated by multiple short edges without increasing the total number of mesh elements. Rigorous analysis shows that a combination of the above two techniques renders optimal convergence for all $α$. Numerical results further confirm this conclusion.

math.NA↗

arXiv2022

The effect of $f$-$c$ hybridization on the $γ\rightarrowα$ phase transition of cerium studied by lanthanum doping

The hybridization between the localized 4$f$ level ($f$) with conduction ($c$) states in $γ$-Ce upon cooling has been previously revealed in single crystalline thin films experimentally and theoretically, whereas its influence on the $γ\rightarrowα$ phase transition was not explicitly verified, due to the fact that the phase transition happened in the bulk-layer, leaving the surface in the $γ$ phase. Here in our work, we circumvent this issue by investigating the effect of alloying addition of La on Ce, by means of crystal structure, electronic transport and ARPES measurements, together with a phenomenological periodic Anderson model and a modified Anderson impurity model. Our current researches indicate that the weakening of $f$-$c$ hybridization is the major factor in the suppression of $γ\rightarrowα$ phase transition by La doping. The consistency of our results with the effects of other rare earth and actinide alloying additions on the $γ\rightarrowα$ phase transition of Ce is also discussed. Our work demonstrates the importance of the interaction of $f$ and $c$ electrons in understanding the unconventional phase transition in Ce, which is intuitive for further researches on other rare earth and actinide metals and alloys with similar phase transition behaviors.

cond-mat.str-el↗

arXiv2022

Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block

Spiking neural networks (SNNs), as one of the brain-inspired models, has spatio-temporal information processing capability, low power feature, and high biological plausibility. The effective spatio-temporal feature makes it suitable for event streams classification. However, neuromorphic datasets, such as N-MNIST, CIFAR10-DVS, DVS128-gesture, need to aggregate individual events into frames with a new higher temporal resolution for event stream classification, which causes high training and inference latency. In this work, we proposed a spatio-temporal compression method to aggregate individual events into a few time steps of synaptic current to reduce the training and inference latency. To keep the accuracy of SNNs under high compression ratios, we also proposed a synaptic convolutional block to balance the dramatic change between adjacent time steps. And multi-threshold Leaky Integrate-and-Fire (LIF) with learnable membrane time constant is introduced to increase its information processing capability. We evaluate the proposed method for event streams classification tasks on neuromorphic N-MNIST, CIFAR10-DVS, DVS128 gesture datasets. The experiment results show that our proposed method outperforms the state-of-the-art accuracy on nearly all datasets, using fewer time steps.

cs.NE↗

arXiv2022

Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow

For marketing, we sometimes need to recommend content for multiple pages in sequence. Different from general sequential decision making process, the use cases have a simpler flow where customers per seeing recommended content on each page can only return feedback as moving forward in the process or dropping from it until a termination state. We refer to this type of problems as sequential decision making in linear--flow. We propose to formulate the problem as an MDP with Bandits where Bandits are employed to model the transition probability matrix. At recommendation time, we use Thompson sampling (TS) to sample the transition probabilities and allocate the best series of actions with analytical solution through exact dynamic programming. The way that we formulate the problem allows us to leverage TS's efficiency in balancing exploration and exploitation and Bandit's convenience in modeling actions' incompatibility. In the simulation study, we observe the proposed MDP with Bandits algorithm outperforms Q-learning with $ε$-greedy and decreasing $ε$, independent Bandits, and interaction Bandits. We also find the proposed algorithm's performance is the most robust to changes in the across-page interdependence strength.

cs.LG↗

arXiv2022

GOMP-FIT: Grasp-Optimized Motion Planning for Fast Inertial Transport

High-speed motions in pick-and-place operations are critical to making robots cost-effective in many automation scenarios, from warehouses and manufacturing to hospitals and homes. However, motions can be too fast -- such as when the object being transported has an open-top, is fragile, or both. One way to avoid spills or damage, is to move the arm slowly. We propose an alternative: Grasp-Optimized Motion Planning for Fast Inertial Transport (GOMP-FIT), a time-optimizing motion planner based on our prior work, that includes constraints based on accelerations at the robot end-effector. With GOMP-FIT, a robot can perform high-speed motions that avoid obstacles and use inertial forces to its advantage. In experiments transporting open-top containers with varying tilt tolerances, whereas GOMP computes sub-second motions that spill up to 90% of the contents during transport, GOMP-FIT generates motions that spill 0% of contents while being slowed by as little as 0% when there are few obstacles, 30% when there are high obstacles and 45-degree tolerances, and 50% when there 15-degree tolerances and few obstacles. Videos and more at: https://berkeleyautomation.github.io/gomp-fit/.

cs.RO↗

arXiv2022

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

In Machine Learning, the emergence of \textit{the right to be forgotten} gave birth to a paradigm named \textit{machine unlearning}, which enables data holders to proactively erase their data from a trained model. Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process. It remains largely underexplored about how to achieve unlearning when full access to all training data becomes unavailable. One noteworthy example is Federated Learning (FL), where each participating data holder trains locally, without sharing their training data to the central server. In this paper, we investigate the problem of machine unlearning in FL systems. We start with a formal definition of the unlearning problem in FL and propose a rapid retraining approach to fully erase data samples from a trained FL model. The resulting design allows data holders to jointly conduct the unlearning process efficiently while keeping their training data locally. Our formal convergence and complexity analysis demonstrate that our design can preserve model utility with high efficiency. Extensive evaluations on four real-world datasets illustrate the effectiveness and performance of our proposed realization.

cs.CR↗

arXiv2022

Muon-spin relaxation study of the layered kagome superconductor CsV$_3$Sb$_5$

The ${\mathbb{Z}}_{2}$ topological metals $R$V$_3$Sb$_5$ ($R$ = K, Rb, Cs) with a layered kagome structure provide a unique opportunity to investigate the interplay between charge order, superconductivity and topology. Here, we report muon-spin relaxation/rotation ($μ$SR) measurements performed on CsV$_3$Sb$_5$ across a broad temperature range, in order to uncover the nature of the charge-density wave order and superconductivity in this material. From zero-field $μ$SR, we find that spontaneous magnetic fields appear below 50 K which is well below the charge-density wave transition ($T^* \sim 93$ K). We show that these spontaneous fields are dynamic in nature making it difficult to associate them with a hidden static order. The superconducting state of CsV$_3$Sb$_5$ is found to preserve time-reversal symmetry and the transverse-field $μ$SR results are consistent with a superconducting state that has two fully open gaps.

cond-mat.supr-con↗