arXiv subjects

Wei Dai

Publications and source records attributed to Wei Dai.

At least 163 records · Page 9Linked to original sources

arXiv2023

Multi-scale MRI reconstruction via dilated ensemble networks

As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this inadvertently impedes fine detail recovery as downsampling creates a resolution bottleneck. Moreover, real and imaginary features are commonly split into separate channels, discarding phase information particularly important to high frequency textures. In this work, we introduce an efficient multi-scale reconstruction network using dilated convolutions to preserve resolution and experiment with a complex-valued version using complex convolutions. Inspired by parallel dilated filters, multiple receptive fields are processed simultaneously with branches that see both large structural artefacts and fine local features. We also adopt dense residual connections for feature aggregation to efficiently increase scale and the deep cascade global architecture to reduce overfitting. The real-valued version of this model outperformed common reconstruction architectures as well as a state-of-the-art multi-scale network whilst being three times more efficient. The complex-valued network yielded better qualitative results when more phase information was present.

eess.IV↗

arXiv2023

Erasure detection of a dual-rail qubit encoded in a double-post superconducting cavity

Qubits with predominantly erasure errors present distinctive advantages for quantum error correction(QEC) and fault tolerant quantum computing. Logical qubits based on dual-rail encoding that exploit erasure detection have been recently proposed in superconducting circuit architectures, either with coupled transmons or cavities. Here, we implement a dual-rail qubit encoded in a compact, double-post superconducting cavity. Using an auxiliary transmon, we perform erasure detection on the dual-rail subspace. We characterize the behaviour of the codespace by a novel method to perform joint-Wigner tomography. This is based on modifying the cross-Kerr interaction between the cavity modes and the transmon. We measure an erasure rate of 3.981 +/- 0.003 (ms)-1 and a residual dephasing error rate up to 0.17 (ms)-1 within the codespace. This strong hierarchy of error rates, together with the compact and hardware-efficient nature of this novel architecture, hold promise in realising QEC schemes with enhanced thresholds and improved scaling.

quant-ph↗

arXiv2023

Efficient General Waveform Catching by a cavity at a Virtual Absorbing Exceptional Point

State transfer and photon detection are fundamental processes that have direct implications in fields such as quantum computing and photonic circuits. However, while naturally emitted photons decay exponentially in time, to perfectly capture a photon its envelope should increase exponentially to match the time-reversed response of the absorbing cavity. Here we show that a cavity at a virtual absorbing exceptional point captures additional temporal orders of an incoming waveform, resulting in efficient passive state transfer and photon detection. This approach paves the way for state transfer at optical frequencies and efficient detection of a spontaneously emitted photon.

quant-ph↗

arXiv2023

The global behaviors for defocusing wave equations in two dimensional exterior region

We study the defocusing semilinear wave equation in ${\mathbb{R}}\times{\mathbb{R}}^2\backslash{\mathcal K}$ with the Dirichlet boundary condition, where ${\mathcal K}$ is a star-shaped obstacle with smooth boundary. We first show that the potential energy of the solution will decay appropriately. Based on it, we show that the solution also pointwisely decays to $0$. Finally, we show that the solution scatters both in energy space and the critical Sobolev space. In general, we show that most of the conclusions obtained in \cite{MR4395159}, which hold on ${\mathbb{R}}^{1+2}$, remain valid on ${\mathbb{R}}\times{\mathbb{R}}^{2}\backslash{\mathcal K}$.

math.AP↗

arXiv2023

SoccerNet 2023 Challenges Results

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

cs.CV↗

arXiv2023

Combing for Credentials: Active Pattern Extraction from Smart Reply

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is tuned to provide suggested responses for a given query message. Since the tuning data is often sensitive data such as emails or chat transcripts, it is important to understand and mitigate the risk that the model leaks its tuning data. We investigate potential information leakage vulnerabilities in a typical Smart Reply pipeline. We consider a realistic setting where the adversary can only interact with the underlying model through a front-end interface that constrains what types of queries can be sent to the model. Previous attacks do not work in these settings, but require the ability to send unconstrained queries directly to the model. Even when there are no constraints on the queries, previous attacks typically require thousands, or even millions, of queries to extract useful information, while our attacks can extract sensitive data in just a handful of queries. We introduce a new type of active extraction attack that exploits canonical patterns in text containing sensitive data. We show experimentally that it is possible for an adversary to extract sensitive user information present in the training data, even in realistic settings where all interactions with the model must go through a front-end that limits the types of queries. We explore potential mitigation strategies and demonstrate empirically how differential privacy appears to be a reasonably effective defense mechanism to such pattern extraction attacks.

cs.CR↗

arXiv2023

Constructive Incremental Learning for Fault Diagnosis of Rolling Bearings with Ensemble Domain Adaptation

Given the prevalence of rolling bearing fault diagnosis as a practical issue across various working conditions, the limited availability of samples compounds the challenge. Additionally, the complexity of the external environment and the structure of rolling bearings often manifests faults characterized by randomness and fuzziness, hindering the effective extraction of fault characteristics and restricting the accuracy of fault diagnosis. To overcome these problems, this paper presents a novel approach termed constructive Incremental learning-based ensemble domain adaptation (CIL-EDA) approach. Specifically, it is implemented on stochastic configuration networks (SCN) to constructively improve its adaptive performance in multi-domains. Concretely, a cloud feature extraction method is employed in conjunction with wavelet packet decomposition (WPD) to capture the uncertainty of fault information from multiple resolution aspects. Subsequently, constructive Incremental learning-based domain adaptation (CIL-DA) is firstly developed to enhance the cross-domain learning capability of each hidden node through domain matching and construct a robust fault classifier by leveraging limited labeled data from both target and source domains. Finally, fault diagnosis results are obtained by a majority voting of CIL-EDA which integrates CIL-DA and parallel ensemble learning. Experimental results demonstrate that our CIL-DA outperforms several domain adaptation methods and CIL-EDA consistently outperforms state-of-art fault diagnosis methods in few-shot scenarios.

cs.AI↗

arXiv2023

DPAN: Dynamic Preference-based and Attribute-aware Network for Relevant Recommendations

In e-commerce platforms, the relevant recommendation is a unique scenario providing related items for a trigger item that users are interested in. However, users' preferences for the similarity and diversity of recommendation results are dynamic and vary under different conditions. Moreover, individual item-level diversity is too coarse-grained since all recommended items are related to the trigger item. Thus, the two main challenges are to learn fine-grained representations of similarity and diversity and capture users' dynamic preferences for them under different conditions. To address these challenges, we propose a novel method called the Dynamic Preference-based and Attribute-aware Network (DPAN) for predicting Click-Through Rate (CTR) in relevant recommendations. Specifically, based on Attribute-aware Activation Values Generation (AAVG), Bi-dimensional Compression-based Re-expression (BCR) is designed to obtain similarity and diversity representations of user interests and item information. Then Shallow and Deep Union-based Fusion (SDUF) is proposed to capture users' dynamic preferences for the diverse degree of recommendation results according to various conditions. DPAN has demonstrated its effectiveness through extensive offline experiments and online A/B testing, resulting in a significant 7.62% improvement in CTR. Currently, DPAN has been successfully deployed on our e-commerce platform serving the primary traffic for relevant recommendations. The code of DPAN has been made publicly available.

cs.IR↗

arXiv2023

MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild

Dynamic facial expression recognition (FER) databases provide important data support for affective computing and applications. However, most FER databases are annotated with several basic mutually exclusive emotional categories and contain only one modality, e.g., videos. The monotonous labels and modality cannot accurately imitate human emotions and fulfill applications in the real world. In this paper, we propose MAFW, a large-scale multi-modal compound affective database with 10,045 video-audio clips in the wild. Each clip is annotated with a compound emotional category and a couple of sentences that describe the subjects' affective behaviors in the clip. For the compound emotion annotation, each clip is categorized into one or more of the 11 widely-used emotions, i.e., anger, disgust, fear, happiness, neutral, sadness, surprise, contempt, anxiety, helplessness, and disappointment. To ensure high quality of the labels, we filter out the unreliable annotations by an Expectation Maximization (EM) algorithm, and then obtain 11 single-label emotion categories and 32 multi-label emotion categories. To the best of our knowledge, MAFW is the first in-the-wild multi-modal database annotated with compound emotion annotations and emotion-related captions. Additionally, we also propose a novel Transformer-based expression snippet feature learning method to recognize the compound emotions leveraging the expression-change relations among different emotions and modalities. Extensive experiments on MAFW database show the advantages of the proposed method over other state-of-the-art methods for both uni- and multi-modal FER. Our MAFW database is publicly available from https://mafw-database.github.io/MAFW.

cs.CV↗

arXiv2023

Radiatively-cooled quantum microwave amplifiers

Superconducting microwave amplifiers are essential for sensitive signal readout in superconducting quantum processors. Typically based on Josephson Junctions, these amplifiers require operation at milli-Kelvin temperatures to achieve quantum-limited performance. Here we demonstrate a quantum microwave amplifier that employs radiative cooling to operate at elevated temperatures. This kinetic-inductance-based parametric amplifier, patterned from a single layer of high-$T_\mathrm{c}$ NbN thin film\cmt{in the form of a nanobridge}, maintains a high gain and meanwhile enables low added noise of 1.3 quanta when operated at 1.5 Kelvin. Remarkably, this represents only a 0.2 quanta increase compared to the performance at a base temperature of 0.1 Kelvin. By uplifting the parametric amplifiers from the mixing chamber without compromising readout efficiency, this work represents an important step for realizing scalable microwave quantum technologies.

quant-ph↗

arXiv2023

Cloud Ensemble Learning for Fault Diagnosis of Rolling Bearings with Stochastic Configuration Networks

Fault diagnosis of rolling bearings is of great significance for post-maintenance in rotating machinery, but it is a challenging work to diagnose faults efficiently with a few samples. Additionally, faults commonly occur with randomness and fuzziness due to the complexity of the external environment and the structure of rolling bearings, hindering effective mining of fault characteristics and eventually restricting accuracy of fault diagnosis. To overcome these problems, stochastic configuration network (SCN) based cloud ensemble learning, called SCN-CEL, is developed in this work. Concretely, a cloud feature extraction method is first developed by using a backward cloud generator of normal cloud model to mine the uncertainty of fault information. Then, a cloud sampling method, which generates enough cloud droplets using bidirectional cloud generator, is proposed to extend the cloud feature samples. Finally, an ensemble model with SCNs is developed to comprehensively characterize the uncertainty of fault information and advance the generalization performance of fault diagnosis machine. Experimental results demonstrate that the proposed method indeed performs favorably for distinguishing fault categories of rolling bearings in the few shot scenarios.

cs.LG↗

arXiv2023

Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation

This paper adds to the fundamental body of work on benchmarking the robustness of deep learning (DL) classifiers. We innovate a new benchmarking methodology to evaluate robustness of DL classifiers. Also, we introduce a new four-quadrant statistical visualization tool, including minimum accuracy, maximum accuracy, mean accuracy, and coefficient of variation, for benchmarking robustness of DL classifiers. To measure robust DL classifiers, we created a comprehensive 69 benchmarking image set, including a clean set, sets with single factor perturbations, and sets with two-factor perturbation conditions. After collecting experimental results, we first report that using two-factor perturbed images improves both robustness and accuracy of DL classifiers. The two-factor perturbation includes (1) two digital perturbations (salt & pepper noise and Gaussian noise) applied in both sequences, and (2) one digital perturbation (salt & pepper noise) and a geometric perturbation (rotation) applied in both sequences. All source codes, related image sets, and preliminary data, figures are shared on a GitHub website to support future academic research and industry projects. The web resources locate at https://github.com/caperock/robustai

cs.LG↗

arXiv2023

A Generic Closed-form Optimal Step-size for ADMM

In this work, we present a generic step-size choice for the ADMM type proximal algorithms. It admits a closed-form expression and is theoretically optimal with respect to a worst-case convergence rate bound. It is simply given by the ratio of Euclidean norms of the dual and primal solutions, i.e., $ ||λ^\star|| / ||{x}^\star||$. Numerical tests show that its practical performance is near-optimal in general. The only challenge is that such a ratio is not known a priori and we provide two strategies to address it. The derivation of our step-size choice is based on studying the fixed-point structure of ADMM using the proximal operator. However, we demonstrate that the classical proximal operator definition contains an input scaling issue. This leads to a scaled step-size optimization problem which would yield a false solution. Such an issue is naturally avoided by our proposed new definition of the proximal operator. A series of its properties is established.

math.OC↗

arXiv2023

A Mask Free Neural Network for Monaural Speech Enhancement

In speech enhancement, the lack of clear structural characteristics in the target speech phase requires the use of conservative and cumbersome network frameworks. It seems difficult to achieve competitive performance using direct methods and simple network architectures. However, we propose the MFNet, a direct and simple network that can not only map speech but also map reverse noise. This network is constructed by stacking global local former blocks (GLFBs), which combine the advantages of Mobileblock for global processing and Metaformer architecture for local interaction. Our experimental results demonstrate that our network using mapping method outperforms masking methods, and direct mapping of reverse noise is the optimal solution in strong noise environments. In a horizontal comparison on the 2020 Deep Noise Suppression (DNS) challenge test set without reverberation, to the best of our knowledge, MFNet is the current state-of-the-art (SOTA) mapping model.

cs.SD↗

arXiv2023

Transformer-Based Hierarchical Clustering for Brain Network Analysis

Brain networks, graphical models such as those constructed from MRI, have been widely used in pathological prediction and analysis of brain functions. Within the complex brain system, differences in neuronal connection strengths parcellate the brain into various functional modules (network communities), which are critical for brain analysis. However, identifying such communities within the brain has been a nontrivial issue due to the complexity of neuronal interactions. In this work, we propose a novel interpretable transformer-based model for joint hierarchical cluster identification and brain network classification. Extensive experimental results on real-world brain network datasets show that with the help of hierarchical clustering, the model achieves increased accuracy and reduced runtime complexity while providing plausible insight into the functional organization of brain regions. The implementation is available at https://github.com/DDVD233/THC.

cs.LG↗

arXiv2023

Does Prompt-Tuning Language Model Ensure Privacy?

Prompt-tuning has received attention as an efficient tuning method in the language domain, i.e., tuning a prompt that is a few tokens long, while keeping the large language model frozen, yet achieving comparable performance with conventional fine-tuning. Considering the emerging privacy concerns with language models, we initiate the study of privacy leakage in the setting of prompt-tuning. We first describe a real-world email service pipeline to provide customized output for various users via prompt-tuning. Then we propose a novel privacy attack framework to infer users' private information by exploiting the prompt module with user-specific signals. We conduct a comprehensive privacy evaluation on the target pipeline to demonstrate the potential leakage from prompt-tuning. The results also demonstrate the effectiveness of the proposed attack.

cs.CR↗

arXiv2023

$Z^0$ boson associated b-jet production in high-energy nuclear collisions

The production of vector boson tagged heavy quark jets potentially provides new tools to probe the jet quenching effect. In this paper, we present the first theoretical study on the angular correlations ($Δϕ_{bZ}$), transverse momentum imbalance ($x_{bZ}$), and nuclear modification factor ($I_{AA}$) of $Z^0$ boson tagged b-jets in heavy-ion collisions, which was performed using a Monte Carlo transport model. We find that the medium modification of the $Δϕ_{bZ}$ for $Z^0\,+\,$b-jet has a weaker dependence on $Δϕ_{bZ}$ than that for $Z^0\,+\,$jet, and the modification patterns are sensitive to the initial jet $p_T$ distribution. Additionally, with the high purity of the quark jet in $Z^0\,+\,$(b-)jet production, we calculate the momentum imbalance $x_{bZ}$ and the nuclear modification factor $I_{AA}$ of $Z^0\,+\,$b-jet in Pb+Pb collisions. We observe a smaller $Δ\left\langle x_{jZ} \right\rangle$ and larger $I_{AA}$ of $Z^0\,+\,$b-jet in Pb+Pb collisions relative to those of $Z^0\,+\,$jet, which may be an indication of the mass effect of jet quenching and can be tested in future measurements.

hep-ph↗

arXiv2023

Heavy-Flavour Jets in High-Energy Nuclear Collisions

Reconstructed jets initiated from heavy quarks provide a powerful tool to probe the properties of the quark-gluon plasma (QGP) and to explore the mass hierarchy of jet quenching. In this article, we review the recent theoretical progresses on heavy-flavour jets in high-energy nuclear collisions at the RHIC and LHC. We focus on the yields and substructures of charm and bottom quark jets with jet quenching effect, such as the nuclear modification factors, transverse momentum imbalance, angular correlation, radial profiles, fragmentation functions, the "dead-cone" effect, etc.

nucl-th↗