Searcharxiv⌕ Search

arXiv subjects

Yuhang Zhang

Publications and source records attributed to Yuhang Zhang.

At least 91 records · Page 5Linked to original sources
arXiv2023

Ferromagnetism and insulating behavior with a logarithmic temperature dependence of resistivity in $Pb_{10-x}Cu_x\left( PO_4 \right) _6O$

Recent claim of discovering above-room-temperature superconductivity (Tc about 400 K) at ambient pressure in copper doped apatite $Pb_{10}\left( PO_4 \right) _6O$ has stimulated world-wide enthusiasm and impulse of motion. A lot of follow-up works have been carried out with controversial conclusions. To check whether superconductivity is really present or absent in the material, we need samples which should have a rather pure phase of $Pb_{10-x}Cu_x\left( PO_4 \right) _6O$. Here we report the characterization results from the $Pb_{10-x}Cu_x\left( PO_4 \right) _6O$ with a fraction of about 97 wt.% inferred from the fitting to the x-ray diffraction pattern. The resistivity measurements show that it is a semiconductor characterized roughly by a ln(1/T) temperature dependence in wide temperature region without trace of superconductivity. Magnetization measurements show that it has a general ferromagnetic signal with a weak superparamagnetic background. Many grains of the sample show clear interactions with a NbFeB magnet. The detected Cu concentration is much lower than the expected nominal one and the conduction may be improved if more Cu atoms are successfully doped into the system. Our results show the absence of metallicity and superconductivity in $Pb_{10-x}Cu_x\left( PO_4 \right) _6O$ at ambient pressure, and suggest the presence of strong correlation effect.

cond-mat.supr-con↗
arXiv2023

Signature of superconductivity in pressurized La$_4$Ni$_3$O$_{10}$

The discovery of high-temperature superconductivity near 80 K in bilayer nickelate La$_3$Ni$_2$O$_7$ under high pressures has renewed the exploration of superconducting nickelate in bulk materials. The extension of superconductivity in other nickelates in a broader family is also essential. Here, we report the experimental observation of superconducting signature in trilayer nickelate La$_4$Ni$_3$O$_{10}$ under high pressures. By using a modified sol-gel method and post-annealing treatment under high oxygen pressure, we successfully obtained polycrystalline La$_4$Ni$_3$O$_{10}$ samples with different transport behaviors at ambient pressure. Then we performed high-pressure electrical resistance measurements on these samples in a diamond-anvil-cell (DAC) apparatus. Surprisingly, the signature of possible superconducting transition with a maximum transition temperature ($T_\text{c}$) of about 20 K under high pressures is observed, as evidenced by a clear drop of resistance and the suppression of resistance drops under magnetic fields. Although the resistance drop is sample-dependent and relatively small, it appears in all of our measured samples. We argue that the observed superconducting signal is most likely to originate from the main phase of La$_4$Ni$_3$O$_{10}$. Our findings will motivate the exploration of superconductivity in a broader family of nickelates and shed light on the understanding of the underlying mechanisms of high-$T_\text{c}$ superconductivity in nickelates.

cond-mat.supr-con↗
arXiv2023

Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition

Facial expression data is characterized by a significant imbalance, with most collected data showing happy or neutral expressions and fewer instances of fear or disgust. This imbalance poses challenges to facial expression recognition (FER) models, hindering their ability to fully understand various human emotional states. Existing FER methods typically report overall accuracy on highly imbalanced test sets but exhibit low performance in terms of the mean accuracy across all expression classes. In this paper, our aim is to address the imbalanced FER problem. Existing methods primarily focus on learning knowledge of minor classes solely from minor-class samples. However, we propose a novel approach to extract extra knowledge related to the minor classes from both major and minor class samples. Our motivation stems from the belief that FER resembles a distribution learning task, wherein a sample may contain information about multiple classes. For instance, a sample from the major class surprise might also contain useful features of the minor class fear. Inspired by that, we propose a novel method that leverages re-balanced attention maps to regularize the model, enabling it to extract transformation invariant information about the minor classes from all training samples. Additionally, we introduce re-balanced smooth labels to regulate the cross-entropy loss, guiding the model to pay more attention to the minor classes by utilizing the extra information regarding the label distribution of the imbalanced training data. Extensive experiments on different datasets and backbones show that the two proposed modules work together to regularize the model and achieve state-of-the-art performance under the imbalanced FER task. Code is available at https://github.com/zyh-uaiaaaa.

cs.CV↗
arXiv2023

Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images

Transformer-based object detectors (DETR) have shown significant performance across machine vision tasks, ultimately in object detection. This detector is based on a self-attention mechanism along with the transformer encoder-decoder architecture to capture the global context in the image. The critical issue to be addressed is how this model architecture can handle different image nuisances, such as occlusion and adversarial perturbations. We studied this issue by measuring the performance of DETR with different experiments and benchmarking the network with convolutional neural network (CNN) based detectors like YOLO and Faster-RCNN. We found that DETR performs well when it comes to resistance to interference from information loss in occlusion images. Despite that, we found that the adversarial stickers put on the image require the network to produce a new unnecessary set of keys, queries, and values, which in most cases, results in a misdirection of the network. DETR also performed poorer than YOLOv5 in the image corruption benchmark. Furthermore, we found that DETR depends heavily on the main query when making a prediction, which leads to imbalanced contributions between queries since the main query receives most of the gradient flow.

cs.CV↗
arXiv2023

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https:// github.com/ 24wenjie-li/ Awesome-Face-Restoration.

cs.CV↗
arXiv2023

Constructing Synthetic Treatment Groups without the Mean Exchangeability Assumption

The purpose of this work is to transport the information from multiple randomized controlled trials to the target population where we only have the control group data. Previous works rely critically on the mean exchangeability assumption. However, as pointed out by many current studies, the mean exchangeability assumption might be violated. Motivated by the synthetic control method, we construct a synthetic treatment group for the target population by a weighted mixture of treatment groups of source populations. We estimate the weights by minimizing the conditional maximum mean discrepancy between the weighted control groups of source populations and the target population. We establish the asymptotic normality of the synthetic treatment group estimator based on the sieve semiparametric theory. Our method can serve as a novel complementary approach when the mean exchangeability assumption is violated. Experiments are conducted on synthetic and real-world datasets to demonstrate the effectiveness of our methods.

stat.ML↗
arXiv2023

Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation

Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-invariant features recently. These methods are based on the assumption that the prototypes, which are represented as the central value of the same class in a certain domain, are domain-invariant. Since the prototypes of different domains have discrepancies as well, the class-wise domain-invariant features learned from the source domain by PCL need to be aligned with the prototypes of other domains simultaneously. However, the prototypes of the same class in different domains may be different while the prototypes of different classes may be similar, which may affect the learning of class-wise domain-invariant features. Based on these observations, a calibration-based dual prototypical contrastive learning (CDPCL) approach is proposed to reduce the domain discrepancy between the learned class-wise features and the prototypes of different domains for domain generalization semantic segmentation. It contains an uncertainty-guided PCL (UPCL) and a hard-weighted PCL (HPCL). Since the domain discrepancies of the prototypes of different classes may be different, we propose an uncertainty probability matrix to represent the domain discrepancies of the prototypes of all the classes. The UPCL estimates the uncertainty probability matrix to calibrate the weights of the prototypes during the PCL. Moreover, considering that the prototypes of different classes may be similar in some circumstances, which means these prototypes are hard-aligned, the HPCL is proposed to generate a hard-weighted matrix to calibrate the weights of the hard-aligned prototypes during the PCL. Extensive experiments demonstrate that our approach achieves superior performance over current approaches on domain generalization semantic segmentation tasks.

cs.CV↗
arXiv2023

Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation

Deep neural networks are vulnerable to universal adversarial perturbation (UAP), an instance-agnostic perturbation capable of fooling the target model for most samples. Compared to instance-specific adversarial examples, UAP is more challenging as it needs to generalize across various samples and models. In this paper, we examine the serious dilemma of UAP generation methods from a generalization perspective -- the gradient vanishing problem using small-batch stochastic gradient optimization and the local optima problem using large-batch optimization. To address these problems, we propose a simple and effective method called Stochastic Gradient Aggregation (SGA), which alleviates the gradient vanishing and escapes from poor local optima at the same time. Specifically, SGA employs the small-batch training to perform multiple iterations of inner pre-search. Then, all the inner gradients are aggregated as a one-step gradient estimation to enhance the gradient stability and reduce quantization errors. Extensive experiments on the standard ImageNet dataset demonstrate that our method significantly enhances the generalization ability of UAP and outperforms other state-of-the-art methods. The code is available at https://github.com/liuxuannan/Stochastic-Gradient-Aggregation.

cs.CV↗
arXiv2023

CAV Traffic Control to Mitigate the Impact of Congestion from Bottlenecks: A Linear Quadratic Regulator Approach and Microsimulation Study

This work investigates traffic control via controlled connected and automated vehicles (CAVs) using novel controllers derived from the linear-quadratic regulator (LQR) theory. CAV-platoons are modeled as moving bottlenecks impacting the surrounding traffic with their speeds as control inputs. An iterative controller algorithm based on the LQR theory is proposed along with a variant that allows for penalizing abrupt changes in platoons speeds. The controllers use the Lighthill-Whitham-Richards (LWR) model implemented using an extended cell transmission model (CTM) which considers the capacity drop phenomenon for a realistic representation of traffic in congestion. The impact of various parameters of the proposed controller on the control performance is analyzed. The effectiveness of the proposed traffic control algorithms is tested using a traffic control example and compared with existing proportional-integral (PI)- and model predictive control (MPC)- based controllers from the literature. A case study using the TransModeler traffic microsimulation software is conducted to test the usability of the proposed controller as well as existing controllers in a realistic setting and derive qualitative insights. It is observed that the proposed controller works well in both settings to mitigate the impact of the jam caused by a fixed bottleneck. The computation time required by the controller is also small making it suitable for real-time control.

eess.SY↗
arXiv2023

Detecting Socially Abnormal Highway Driving Behaviors via Recurrent Graph Attention Networks

With the rapid development of Internet of Things technologies, the next generation traffic monitoring infrastructures are connected via the web, to aid traffic data collection and intelligent traffic management. One of the most important tasks in traffic is anomaly detection, since abnormal drivers can reduce traffic efficiency and cause safety issues. This work focuses on detecting abnormal driving behaviors from trajectories produced by highway video surveillance systems. Most of the current abnormal driving behavior detection methods focus on a limited category of abnormal behaviors that deal with a single vehicle without considering vehicular interactions. In this work, we consider the problem of detecting a variety of socially abnormal driving behaviors, i.e., behaviors that do not conform to the behavior of other nearby drivers. This task is complicated by the variety of vehicular interactions and the spatial-temporal varying nature of highway traffic. To solve this problem, we propose an autoencoder with a Recurrent Graph Attention Network that can capture the highway driving behaviors contextualized on the surrounding cars, and detect anomalies that deviate from learned patterns. Our model is scalable to large freeways with thousands of cars. Experiments on data generated from traffic simulation software show that our model is the only one that can spot the exact vehicle conducting socially abnormal behaviors, among the state-of-the-art anomaly detection models. We further show the performance on real world HighD traffic dataset, where our model detects vehicles that violate the local driving norms.

cs.AI↗
arXiv2023

Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective

Out-of-distribution (OOD) detection methods assume that they have test ground truths, i.e., whether individual test samples are in-distribution (IND) or OOD. However, in the real world, we do not always have such ground truths, and thus do not know which sample is correctly detected and cannot compute the metric like AUROC to evaluate the performance of different OOD detection methods. In this paper, we are the first to introduce the unsupervised evaluation problem in OOD detection, which aims to evaluate OOD detection methods in real-world changing environments without OOD labels. We propose three methods to compute Gscore as an unsupervised indicator of OOD detection performance. We further introduce a new benchmark Gbench, which has 200 real-world OOD datasets of various label spaces to train and evaluate our method. Through experiments, we find a strong quantitative correlation betwwen Gscore and the OOD detection performance. Extensive experiments demonstrate that our Gscore achieves state-of-the-art performance. Gscore also generalizes well with different IND/OOD datasets, OOD detection methods, backbones and dataset sizes. We further provide interesting analyses of the effects of backbones and IND/OOD datasets on OOD detection performance. The data and code will be available.

cs.CV↗
arXiv2022

A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation

Video semantic segmentation (VSS) is beneficial for dealing with dynamic scenes due to the continuous property of the real-world environment. On the one hand, some methods alleviate the predicted inconsistent problem between continuous frames. On the other hand, other methods employ the previous frame as the prior information to assist in segmenting the current frame. Although the previous methods achieve superior performances on the independent and identically distributed (i.i.d) data, they can not generalize well on other unseen domains. Thus, we explore a new task, the video generalizable semantic segmentation (VGSS) task that considers both continuous frames and domain generalization. In this paper, we propose a class-wise non-salient region generalized (CNSG) framework for the VGSS task. Concretely, we first define the class-wise non-salient feature, which describes features of the class-wise non-salient region that carry more generalizable information. Then, we propose a class-wise non-salient feature reasoning strategy to select and enhance the most generalized channels adaptively. Finally, we propose an inter-frame non-salient centroid alignment loss to alleviate the predicted inconsistent problem in the VGSS task. We also extend our video-based framework to the image-based generalizable semantic segmentation (IGSS) task. Experiments demonstrate that our CNSG framework yields significant improvement in the VGSS and IGSS tasks.

cs.CV↗
arXiv2022

Model and Data Agreement for Learning with Noisy Labels

Learning with noisy labels is a vital topic for practical deep learning as models should be robust to noisy open-world datasets in the wild. The state-of-the-art noisy label learning approach JoCoR fails when faced with a large ratio of noisy labels. Moreover, selecting small-loss samples can also cause error accumulation as once the noisy samples are mistakenly selected as small-loss samples, they are more likely to be selected again. In this paper, we try to deal with error accumulation in noisy label learning from both model and data perspectives. We introduce mean point ensemble to utilize a more robust loss function and more information from unselected samples to reduce error accumulation from the model perspective. Furthermore, as the flip images have the same semantic meaning as the original images, we select small-loss samples according to the loss values of flip images instead of the original ones to reduce error accumulation from the data perspective. Extensive experiments on CIFAR-10, CIFAR-100, and large-scale Clothing1M show that our method outperforms state-of-the-art noisy label learning methods with different levels of label noise. Our method can also be seamlessly combined with other noisy label learning methods to further improve their performance and generalize well to other tasks. The code is available in https://github.com/zyh-uaiaaaa/MDA-noisy-label-learning.

cs.CV↗
arXiv2022

Quasi two-dimensional nature of high-Tc superconductivity in iron-based (Li,Fe)OHFeSe

The intercalated iron selenide (Li,Fe)OHFeSe has a strongly layered structure analogous to the quasi two-dimensional (2D) bismuth cuprate superconductors, and exhibits both high-temperature (Tc) and topological superconductivity. However, the issue of its superconductivity dimensionality has not yet been fully investigated so far. Here we report that the quasi-2D superconductivity features, including the high anisotropy γ = 151 and the associated quasi-2D vortices, are also revealed for (Li,Fe)OHFeSe, based on systematic experiments of the electrical transport and magnetization and model fittings. Thus, we establish a new vortex phase diagram for (Li,Fe)OHFeSe, which delineates an emergent quasi-2D vortex-liquid state, and a subsequent vortex-solid dimensional crossover from a pancake-like to a three-dimensional state with decreasing temperature and magnetic field. Furthermore, we find that all the quasi-2D characteristics revealed here for the high-Tc iron selenide superconductor are very similar to those reported for the high-Tc bismuth cuprate superconductors.

cond-mat.supr-con↗
arXiv2022

Superconductivity and orbital-selective nematic order in a new titanium-based kagome metal CsTi3Bi5

Fabrication of new types of superconductors with novel physical properties has always been a major thread in the research of superconducting materials. An example is the enormous interests generated by the cascade of correlated topological quantum states in the newly discovered vanadium-based kagome superconductors AV3Sb5 (A=K, Rb, and Cs) with a Z2 topological band structure. Here we report the successful fabrication of single-crystals of titanium-based kagome metal CsTi3Bi5 and the observation of superconductivity and electronic nematicity. The onset of the superconducting transition temperature Tc is around 4.8 K. In sharp contrast to the charge density wave superconductor AV3Sb5, we find that the kagome superconductor CsTi3Bi5 preserves translation symmetry, but breaks rotational symmetry and exhibits an electronic nematicity. The angular-dependent magnetoresistivity shows a remarkable two-fold rotational symmetry as the magnetic field rotates in the kagome plane. The scanning tunneling microscopy and spectroscopic imaging detect rotational-symmetry breaking C2 quasiparticle interference patterns (QPI) at low energies, providing further microscopic evidence for electronic nematicity. Combined with first-principle calculations, we find that the nematic QPI is orbital-selective and dominated by the Ti dxz and dyz orbitals, possibly originating from the intriguing orbital bond nematic order. Our findings in the new "135" material CsTi3Bi5 provide new directions for exploring the multi-orbital correlation effect and the role of orbital or bond order in the electron liquid crystal phases evidenced by the symmetry breaking states in kagome superconductors.

cond-mat.supr-con↗
arXiv2022

Titanium doped kagome superconductor CsV3-xTixSb5 and two distinct phases

The vanadium-based kagome superconductor CsV3Sb5 has attracted tremendous attention due to its unexcepted anomalous Hall effect (AHE), charge density waves (CDWs), nematicity, and a pseudogap pair density wave (PDW) coexisting with unconventional strong-coupling superconductivity (SC). The origins of CDWs, unconventional SC, and their correlation with different electronic states in this kagome system are of great significance, but so far, are still under debate. Chemical doping in the kagome layer provides one of the most direct ways to reveal the intrinsic physics, but remains unexplored. Here, we report, for the first time, the synthesis of Ti-substituted CsV3Sb5 single crystals and its rich phase diagram mapping the evolution of intertwining electronic states. The Ti atoms directly substitute for V in the kagome layers. CsV3-xTixSb5 shows two distinct SC phases upon substitution. The Ti slightly-substituted phase displays an unconventional V-shaped SC gap, coexisting with weakening CDW, PDW, AHE, and nematicity. The Ti highly-substituted phase has a U-shaped SC gap concomitant with a short-range rotation symmetry breaking CDW, while long-range CDW, twofold symmetry of in-plane resistivity, AHE, and PDW are absent. Furthermore, we also demonstrate the chemical substitution of V atoms with other elements such as Cr and Nb, showing a different modulation on the SC phase and CDWs. These findings open up a way to synthesise a new family of doped CsV3Sb5 materials, and further representing a new platform for tuning the different correlated electronic states and superconducting pairing in kagome superconductors.

cond-mat.supr-con↗
arXiv2022

Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition

Noisy label Facial Expression Recognition (FER) is more challenging than traditional noisy label classification tasks due to the inter-class similarity and the annotation ambiguity. Recent works mainly tackle this problem by filtering out large-loss samples. In this paper, we explore dealing with noisy labels from a new feature-learning perspective. We find that FER models remember noisy samples by focusing on a part of the features that can be considered related to the noisy labels instead of learning from the whole features that lead to the latent truth. Inspired by that, we propose a novel Erasing Attention Consistency (EAC) method to suppress the noisy samples during the training process automatically. Specifically, we first utilize the flip semantic consistency of facial images to design an imbalanced framework. We then randomly erase input images and use flip attention consistency to prevent the model from focusing on a part of the features. EAC significantly outperforms state-of-the-art noisy label FER methods and generalizes well to other tasks with a large number of classes like CIFAR100 and Tiny-ImageNet. The code is available at https://github.com/zyh-uaiaaaa/Erasing-Attention-Consistency.

cs.CV↗
arXiv2022

Titanium-based kagome superconductor CsTi_3Bi_5 and topological states

Since the discovery of a new family of vanadium-based kagome superconductor AV3Sb5 (A=K, Rb, and Cs) with topological band structures, extensive effort has been devoted to exploring the origin of superconducting states and the intertwined orders. Meanwhile, searching for new types of superconductors with novel physical properties and higher superconducting transition temperatures has always been a major thread in the history of superconductor research. Here we report a successful fabrication and the topological states of a Titanium-based kagome metal CsTi3Bi5 (CT3B5) crystal. The as-grown CT3B5 crystal is of high quality and possesses a perfect two-dimensional kagome net of Titanium. The superconductivity of the CT3B5 crystal shows that the critical temperature Tc is of ~4.8 K. First-principle calculations predict that the CT3B5 has robust topological surface states, implying that CT3B5 is a Z2 topological kagome superconductor. This finding provides a new type of superconductors and the base for exploring the origin of superconductivity and topological states in kagome superconductors.

cond-mat.supr-con↗