arXiv subjects

Wei Xia

Publications and source records attributed to Wei Xia.

At least 163 records · Page 9Linked to original sources

arXiv2021

Multiband superconductivity with sign-preserving order parameter in kagome superconductor CsV3Sb5

The superconductivity of a kagome superconductor CsV3Sb5 is studied by scanning tunneling microscopy / spectroscopy at an ultralow temperature with high resolution. Two kinds of superconducting gaps with multiple sets of coherent peaks and residual zero-energy density of states are observed on both half-Cs and Sb surfaces, implying multiband superconductivity with gap nodes. Sixfold star-shaped magnetic vortex is observed with conventional Caroli-de Gennes-Matricon bound states inside. Magnetic impurities suppress the superconductivity, while nonmagnetic impurities do not, suggesting the absence of sign-change in the superconducting order parameter. Moreover, the interplay between charge density waves and superconductivity differs on various bands, resulting in different density of state distributions. Our study provides critical clues for further understanding the superconductivity and its relation to charge density waves in CsV3Sb5.

cond-mat.supr-con↗

arXiv2021

The Reservoir Learning Power across Quantum Many-Boby Localization Transition

Harnessing the quantum computation power of the present noisy-intermediate-size-quantum devices has received tremendous interest in the last few years. Here we study the learning power of a one-dimensional long-range randomly-coupled quantum spin chain, within the framework of reservoir computing. In time sequence learning tasks, we find the system in the quantum many-body localized (MBL) phase holds long-term memory, which can be attributed to the emergent local integrals of motion. On the other hand, MBL phase does not provide sufficient nonlinearity in learning highly-nonlinear time sequences, which we show in a parity check task. This is reversed in the quantum ergodic phase, which provides sufficient nonlinearity but compromises memory capacity. In a complex learning task of Mackey-Glass prediction that requires both sufficient memory capacity and nonlinearity, we find optimal learning performance near the MBL-to-ergodic transition. This leads to a guiding principle of quantum reservoir engineering at the edge of quantum ergodicity reaching optimal learning power for generic complex reservoir learning tasks. Our theoretical finding can be readily tested with present experiments.

quant-ph↗

arXiv2021

CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results

As facial interaction systems are prevalently deployed, security and reliability of these systems become a critical issue, with substantial research efforts devoted. Among them, face anti-spoofing emerges as an important area, whose objective is to identify whether a presented face is live or spoof. Recently, a large-scale face anti-spoofing dataset, CelebA-Spoof which comprised of 625,537 pictures of 10,177 subjects has been released. It is the largest face anti-spoofing dataset in terms of the numbers of the data and the subjects. This paper reports methods and results in the CelebA-Spoof Challenge 2020 on Face AntiSpoofing which employs the CelebA-Spoof dataset. The model evaluation is conducted online on the hidden test set. A total of 134 participants registered for the competition, and 19 teams made valid submissions. We will analyze the top ranked solutions and present some discussion on future work directions.

cs.CV↗

arXiv2021

DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to disentangle speaker-related and domain-specific features and apply domain adaptation on the speaker-related feature space solely. Instead of performing domain adaptation directly on the feature space where domain information is not removed, using disentanglement can efficiently boost adaptation performance. To be specific, our model's input speech from the source and target domains is first encoded into different latent feature spaces. The adversarial domain adaptation is conducted on the shared speaker-related feature space to encourage the property of domain-invariance. Further, we minimize the mutual information between speaker-related and domain-specific features for both domains to enforce the disentanglement. Experimental results on the VOiCES dataset demonstrate that our proposed framework can effectively generate more speaker-discriminative and domain-invariant speaker representations with a relative 20.3% reduction of EER compared to the original ResNet-based system.

eess.AS↗

arXiv2021

DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results

This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection. The challenge employs the DeeperForensics-1.0 dataset, one of the most extensive publicly available real-world face forgery detection datasets, with 60,000 videos constituted by a total of 17.6 million frames. The model evaluation is conducted online on a high-quality hidden test set with multiple sources and diverse distortions. A total of 115 participants registered for the competition, and 25 teams made valid submissions. We will summarize the winning solutions and present some discussions on potential research directions.

cs.CV↗

arXiv2021

Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo speaker embedding system utilizes a queue to maintain a large set of negative examples. We show that better speaker embeddings can be learned by momentum contrastive learning. Next, alternative augmentation strategies are explored to normalize extrinsic speaker variabilities of two random segments from the same speech utterance. Specifically, augmentation in the waveform largely improves the speaker representations for SV tasks. The proposed MoCo speaker embedding is further improved when a prototypical memory bank is introduced, which encourages the speaker embeddings to be closer to their assigned prototypes with an intermediate clustering step. In addition, we generalize the self-supervised framework to a semi-supervised scenario where only a small portion of the data is labeled. Comprehensive experiments on the Voxceleb dataset demonstrate that our proposed self-supervised approach achieves competitive performance compared with existing techniques, and can approach fully supervised results with partially labeled data.

eess.AS↗

arXiv2021

Towards Backward-Compatible Representation Learning

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then "new" features can be compared directly to "old" features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the embedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.

cs.CV↗

arXiv2020

SMOT: Single-Shot Multi Object Tracking

We present single-shot multi-object tracker (SMOT), a new tracking framework that converts any single-shot detector (SSD) model into an online multiple object tracker, which emphasizes simultaneously detecting and tracking of the object paths. Contrary to the existing tracking by detection approaches which suffer from errors made by the object detectors, SMOT adopts the recently proposed scheme of tracking by re-detection. We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module. With this design SMOT is able to generate tracklets with a constant per-frame runtime. A light-weighted linkage algorithm is then used for online tracklet linking. On three benchmarks of object tracking: Hannah, Music Videos, and MOT17, the proposed SMOT achieves state-of-the-art performance.

cs.CV↗

arXiv2020

3D-Aided Data Augmentation for Robust Face Understanding

Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and expensive to acquire. In face recognition, large pose and illumination variation of face images has been a key factor for performance degradation. However, human annotation for the various face understanding tasks including face landmark localization, face attributes classification and face recognition under these challenging scenarios are highly costly to acquire. Therefore, it would be desirable to perform data augmentation for these cases. But simple 2D data augmentation techniques on the image domain are not able to satisfy the requirement of these challenging cases. As such, 3D face modeling, in particular, single image 3D face modeling, stands a feasible solution for these challenging conditions beyond 2D based data augmentation. To this end, we propose a method that produces realistic 3D augmented images from multiple viewpoints with different illumination conditions through 3D face modeling, each associated with geometrically accurate face landmarks, attributes and identity information. Experiments demonstrate that the proposed 3D data augmentation method significantly improves the performance and robustness of various face understanding tasks while achieving state-of-arts on multiple benchmarks.

cs.CV↗

arXiv2020

Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias

In forensic applications, it is very common that only small naturalistic datasets consisting of short utterances in complex or unknown acoustic environments are available. In this study, we propose a pipeline solution to improve speaker verification on a small actual forensic field dataset. By leveraging large-scale out-of-domain datasets, a knowledge distillation based objective function is proposed for teacher-student learning, which is applied for short utterance forensic speaker verification. The objective function collectively considers speaker classification loss, Kullback-Leibler divergence, and similarity of embeddings. In order to advance the trained deep speaker embedding network to be robust for a small target dataset, we introduce a novel strategy to fine-tune the pre-trained student model towards a forensic target domain by utilizing the model as a finetuning start point and a reference in regularization. The proposed approaches are evaluated on the 1st48-UTD forensic corpus, a newly established naturalistic dataset of actual homicide investigations consisting of short utterances recorded in uncontrolled conditions. We show that the proposed objective function can efficiently improve the performance of teacher-student learning on short utterances and that our fine-tuning strategy outperforms the commonly used weight decay method by providing an explicit inductive bias towards the pre-trained model.

eess.AS↗

arXiv2020

Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context information to enhance important channels and recalibrate salient time-frequency locations by computing the similarity between the global context and local features. The proposed modules, together with a popular ResNet based model, are evaluated on the VoxCeleb1 dataset, which is a large scale speaker verification corpus collected in the wild. This lightweight block can be easily incorporated into a CNN model with little additional computational costs and effectively improves the speaker verification performance compared to the baseline ResNet-LDE model and the Squeeze&Excitation block by a large margin. Detailed ablation studies are also performed to analyze various factors that may impact the performance of the proposed modules. We find that by employing the proposed L2-tf-GTFC transformation block, the Equal Error Rate decreases from 4.56% to 3.07%, a relative 32.68% reduction, and a relative 27.28% improvement in terms of the DCF score. The results indicate that our proposed global context guided transformation modules can efficiently improve the learned speaker representations by achieving time-frequency and channel-wise feature recalibration.

eess.AS↗

arXiv2020

Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification

Forensic audio analysis for speaker verification offers unique challenges due to location/scenario uncertainty and diversity mismatch between reference and naturalistic field recordings. The lack of real naturalistic forensic audio corpora with ground-truth speaker identity represents a major challenge in this field. It is also difficult to directly employ small-scale domain-specific data to train complex neural network architectures due to domain mismatch and loss in performance. Alternatively, cross-domain speaker verification for multiple acoustic environments is a challenging task which could advance research in audio forensics. In this study, we introduce a CRSS-Forensics audio dataset collected in multiple acoustic environments. We pre-train a CNN-based network using the VoxCeleb data, followed by an approach which fine-tunes part of the high-level network layers with clean speech from CRSS-Forensics. Based on this fine-tuned model, we align domain-specific distributions in the embedding space with the discrepancy loss and maximum mean discrepancy (MMD). This maintains effective performance on the clean set, while simultaneously generalizes the model to other acoustic domains. From the results, we demonstrate that diverse acoustic environments affect the speaker verification performance, and that our proposed approach of cross-domain adaptation can significantly improve the results in this scenario.

eess.AS↗

arXiv2020

6VecLM: Language Modeling in Vector Space for IPv6 Target Generation

Fast IPv6 scanning is challenging in the field of network measurement as it requires exploring the whole IPv6 address space but limited by current computational power. Researchers propose to obtain possible active target candidate sets to probe by algorithmically analyzing the active seed sets. However, IPv6 addresses lack semantic information and contain numerous addressing schemes, leading to the difficulty of designing effective algorithms. In this paper, we introduce our approach 6VecLM to explore achieving such target generation algorithms. The architecture can map addresses into a vector space to interpret semantic relationships and uses a Transformer network to build IPv6 language models for predicting address sequence. Experiments indicate that our approach can perform semantic classification on address space. By adding a new generation approach, our model possesses a controllable word innovation capability compared to conventional language models. The work outperformed the state-of-the-art target generation algorithms on two active address datasets by reaching more quality candidate sets.

cs.NI↗

arXiv2020

SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mapping

The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder network with skip connections. In this study, we propose `SkipConvNet' where we replace each skip connection with multiple convolutional modules to provide decoder with intuitive feature maps rather than encoder's output to improve the learning capacity of the network. We also propose the use of optimal smoothing of power spectral density (PSD) as a pre-processing step, which helps to further enhance the efficiency of the network. To evaluate our proposed system, we use the REVERB challenge corpus to assess the performance of various enhancement approaches under the same conditions. We focus solely on monitoring improvements in speech quality and their contribution to improving the efficiency of back-end speech systems, such as speech recognition and speaker verification, trained on only clean speech. Experimental findings show that the proposed system consistently outperforms other approaches.

eess.AS↗

arXiv2020

Towards causal benchmarking of bias in face analysis algorithms

Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current methods to measure algorithmic bias in computer vision, which are based on observational datasets, are inadequate for this task because they conflate algorithmic bias with dataset bias. To address this problem we develop an experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change. Our proposed method is based on generating synthetic ``transects'' of matched sample images that are designed to differ along specific attributes while leaving other attributes constant. A crucial aspect of our approach is relying on the perception of human observers, both to guide manipulations, and to measure algorithmic bias. Besides allowing the measurement of algorithmic bias, synthetic transects have other advantages with respect to observational datasets: they sample attributes more evenly allowing for more straightforward bias analysis on minority and intersectional groups, they enable prediction of bias in new scenarios, they greatly reduce ethical and legal challenges, and they are economical and fast to obtain, helping make bias testing affordable and widely available. We validate our method by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms. The two methods reach different conclusions. While the observational method reports gender and skin color biases, the experimental method reveals biases due to gender, hair length, age, and facial hair.

cs.CV↗

arXiv2020

Magnetism-induced topological transition in EuAs3

The nature of the interaction between magnetism and topology in magnetic topological semimetals remains mysterious, but may be expected to lead to a variety of novel physics. We present $ab$ $initio$ band calculations, electrical transport and angle-resolved photoemission spectroscopy (ARPES) measurements on the magnetic semimetal EuAs$_3$, demonstrating a magnetism-induced topological transition from a topological nodal-line semimetal in the paramagnetic or the spin-polarized state to a topological massive Dirac metal in the antiferromagnetic (AFM) ground state at low temperature, featuring a pair of massive Dirac points, inverted bands and topological surface states on the (010) surface. Shubnikov-de Haas (SdH) oscillations in the AFM state identify nonzero Berry phase and a negative longitudinal magnetoresistance ($n$-LMR) induced by the chiral anomaly, confirming the topological nature predicted by band calculations. When magnetic moments are fully polarized by an external magnetic field, an unsaturated and extremely large magnetoresistance (XMR) of $\sim$ 2$\times10^5$ % at 1.8 K and 28.3 T is observed, likely arising from topological protection. Consistent with band calculations for the spin-polarized state, four new bands in quantum oscillations different from those in the AFM state are discerned, of which two are topologically protected. Nodal-line structures at the $Y$ point in the Brillouin zone (BZ) are proposed in both the spin-polarized and paramagnetic states, and the latter is proven by ARPES. Moreover, a temperature-induced Lifshitz transition accompanied by the emergence of a new band below 3 K is revealed. These results indicate that magnetic EuAs$_3$ provides a rich platform to explore exotic physics arising from the interaction of magnetism with topology.

cond-mat.mtrl-sci↗

arXiv2020

On Improving Temporal Consistency for Online Face Liveness Detection

In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system. Most of the existing frame-based methods are suffering from the prediction inconsistency across time. To address the issue, a simple yet effective solution based on temporal consistency is proposed. Specifically, in the training stage, to integrate the temporal consistency constraint, a temporal self-supervision loss and a class consistency loss are proposed in addition to the softmax cross-entropy loss. In the deployment stage, a training-free non-parametric uncertainty estimation module is developed to smooth the predictions adaptively. Beyond the common evaluation approach, a video segment-based evaluation is proposed to accommodate more practical scenarios. Extensive experiments demonstrated that our solution is more robust against several presentation attacks in various scenarios, and significantly outperformed the state-of-the-art on multiple public datasets by at least 40% in terms of ACER. Besides, with much less computational complexity (33% fewer FLOPs), it provides great potential for low-latency online applications.

cs.CV↗

arXiv2020

Electronic Origin for the Enhanced Thermoelectric Efficiency of Cu2Se

Thermoelectric materials (TMs) can uniquely convert waste heat into electricity, which provides a potential solution for the global energy crisis that is increasingly severe. Bulk Cu2Se, with ionic conductivity of Cu ions, exhibits a significant enhancement of its thermoelectric figure of merit zT by a factor of ~3 near its structural transition around 400 K. Here, we show a systematic study of the electronic structure of Cu2Se and its temperature evolution using high-resolution angle-resolved photoemission spectroscopy. Upon heating across the structural transition, the electronic states near the corner of the Brillouin zone gradually disappear, while the bands near the centre of Brillouin zone shift abruptly towards high binding energies and develop an energy gap. Interestingly, the observed band reconstruction well reproduces the temperature evolution of the Seebeck coefficient of Cu2Se, providing an electronic origin for the drastic enhancement of the thermoelectric performance near 400 K. The current results not only bridge among structural phase transition, electronic structures, and thermoelectric properties in a condensed matter system, but also provide valuable insights into the search and design of new generation of thermoelectric materials.

cond-mat.mtrl-sci↗