arXiv subjects

Shuai Wang

Publications and source records attributed to Shuai Wang.

At least 559 records · Page 31Linked to original sources

arXiv2023

Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-talker Speech

Target speaker extraction aims to extract the speech of a specific speaker from a multi-talker mixture as specified by an auxiliary reference. Most studies focus on the scenario where the target speech is highly overlapped with the interfering speech. However, this scenario only accounts for a small percentage of real-world conversations. In this paper, we aim at the sparsely overlapped scenarios in which the auxiliary reference needs to perform two tasks simultaneously: detect the activity of the target speaker and disentangle the active speech from any interfering speech. We propose an audio-visual speaker extraction model named ActiveExtract, which leverages speaking activity from audio-visual active speaker detection (ASD). The ASD directly provides the frame-level activity of the target speaker, while its intermediate feature representation is trained to discriminate speech-lip synchronization that could be used for speaker disentanglement. Experimental results show our model outperforms baselines across various overlapping ratios, achieving an average improvement of more than 4 dB in terms of SI-SNR.

cs.SD↗

arXiv2023

PerfCE: Performance Debugging on Databases with Chaos Engineering-Enhanced Causality Analysis

Debugging performance anomalies in real-world databases is challenging. Causal inference techniques enable qualitative and quantitative root cause analysis of performance downgrade. Nevertheless, causality analysis is practically challenging, particularly due to limited observability. Recently, chaos engineering has been applied to test complex real-world software systems. Chaos frameworks like Chaos Mesh mutate a set of chaos variables to inject catastrophic events (e.g., network slowdowns) to "stress" software systems. The systems under chaos stress are then tested using methods like differential testing to check if they retain their normal functionality (e.g., SQL query output is always correct under stress). Despite its ubiquity in the industry, chaos engineering is now employed mostly to aid software testing rather for performance debugging. This paper identifies novel usage of chaos engineering on helping developers diagnose performance anomalies in databases. Our presented framework, PERFCE, comprises an offline phase and an online phase. The offline phase learns the statistical models of the target database system, whilst the online phase diagnoses the root cause of monitored performance anomalies on the fly. During the offline phase, PERFCE leverages both passive observations and proactive chaos experiments to constitute accurate causal graphs and structural equation models (SEMs). When observing performance anomalies during the online phase, causal graphs enable qualitative root cause identification (e.g., high CPU usage) and SEMs enable quantitative counterfactual analysis (e.g., determining "when CPU usage is reduced to 45\%, performance returns to normal"). PERFCE notably outperforms prior works on common synthetic datasets, and our evaluation on real-world databases, MySQL and TiDB, shows that PERFCE is highly accurate and moderately expensive.

cs.DB↗

arXiv2023

Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For evaluation, we propose an iterative decoding method that outputs diarization results for each speaker sequentially. Additionally, we propose an Enhancer module to enhance the frame-level speaker embeddings, enabling the model to handle scenarios with an unseen number of speakers. We also explore replacing the transformer encoder with a Conformer architecture, which better models local information. Furthermore, we discovered that commonly used simulation datasets for speaker diarization have a much higher overlap ratio compared to real data. We found that using simulated training data that is more consistent with real data can achieve an improvement in consistency. Extensive experimental validation demonstrates the effectiveness of our proposed methodologies. Our best system achieved a new state-of-the-art diarization error rate (DER) performance on all the CALLHOME (10.08%), DIHARD II (24.64%), and AMI (13.00%) evaluation benchmarks, when no oracle voice activity detection (VAD) is used. Beyond speaker diarization, our AED-EEND system also shows remarkable competitiveness as a speech type detection model.

cs.SD↗

arXiv2023

Enabling Runtime Verification of Causal Discovery Algorithms with Automated Conditional Independence Reasoning (Extended Version)

Causal discovery is a powerful technique for identifying causal relationships among variables in data. It has been widely used in various applications in software engineering. Causal discovery extensively involves conditional independence (CI) tests. Hence, its output quality highly depends on the performance of CI tests, which can often be unreliable in practice. Moreover, privacy concerns arise when excessive CI tests are performed. Despite the distinct nature between unreliable and excessive CI tests, this paper identifies a unified and principled approach to addressing both of them. Generally, CI statements, the outputs of CI tests, adhere to Pearl's axioms, which are a set of well-established integrity constraints on conditional independence. Hence, we can either detect erroneous CI statements if they violate Pearl's axioms or prune excessive CI statements if they are logically entailed by Pearl's axioms. Holistically, both problems boil down to reasoning about the consistency of CI statements under Pearl's axioms (referred to as CIR problem). We propose a runtime verification tool called CICheck, designed to harden causal discovery algorithms from reliability and privacy perspectives. CICheck employs a sound and decidable encoding scheme that translates CIR into SMT problems. To solve the CIR problem efficiently, CICheck introduces a four-stage decision procedure with three lightweight optimizations that actively prove or refute consistency, and only resort to costly SMT-based reasoning when necessary. Based on the decision procedure to CIR, CICheck includes two variants: ED-CICheck and ED-CICheck, which detect erroneous CI tests (to enhance reliability) and prune excessive CI tests (to enhance privacy), respectively. [abridged due to length limit]

cs.SE↗

arXiv2023

Rate-Splitting and Sum-DoF for the K-User MISO Broadcast Channel with Mixed CSIT and Order-(K-1) Messages

In this paper, we propose a rate-splitting design and characterize the sum-degrees-of-freedom (DoF) for the K-user multiple-input-single-output (MISO) broadcast channel with mixed channel state information at the transmitter (CSIT) and order-(K-1) messages, where mixed CSIT refers to the delayed and imperfect-current CSIT, and order-(K-1) message refers to the message desired by K-1 users simultaneously. In particular, for the sum-DoF lower bound, we propose a rate-splitting scheme embedding with retrospective interference alignment. In addition, we propose a matching sum-DoF upper bound via genie signalings and extremal inequality. Opposed to existing works for K=2, our results show that the sum-DoF is saturated with CSIT quality when CSIT quality thresholds are satisfied for K>2.

cs.IT↗

arXiv2023

Least Squares Maximum and Weighted Generalization-Memorization Machines

In this paper, we propose a new way of remembering by introducing a memory influence mechanism for the least squares support vector machine (LSSVM). Without changing the equation constraints of the original LSSVM, this mechanism, allows an accurate partitioning of the training set without overfitting. The maximum memory impact model (MIMM) and the weighted impact memory model (WIMM) are then proposed. It is demonstrated that these models can be degraded to the LSSVM. Furthermore, we propose some different memory impact functions for the MIMM and WIMM. The experimental results show that that our MIMM and WIMM have better generalization performance compared to the LSSVM and significant advantage in time cost compared to other memory models.

stat.ML↗

arXiv2023

Parsing is All You Need for Accurate Gait Recognition in the Wild

Binary silhouettes and keypoint-based skeletons have dominated human gait recognition studies for decades since they are easy to extract from video frames. Despite their success in gait recognition for in-the-lab environments, they usually fail in real-world scenarios due to their low information entropy for gait representations. To achieve accurate gait recognition in the wild, this paper presents a novel gait representation, named Gait Parsing Sequence (GPS). GPSs are sequences of fine-grained human segmentation, i.e., human parsing, extracted from video frames, so they have much higher information entropy to encode the shapes and dynamics of fine-grained human parts during walking. Moreover, to effectively explore the capability of the GPS representation, we propose a novel human parsing-based gait recognition framework, named ParsingGait. ParsingGait contains a Convolutional Neural Network (CNN)-based backbone and two light-weighted heads. The first head extracts global semantic features from GPSs, while the other one learns mutual information of part-level features through Graph Convolutional Networks to model the detailed dynamics of human walking. Furthermore, due to the lack of suitable datasets, we build the first parsing-based dataset for gait recognition in the wild, named Gait3D-Parsing, by extending the large-scale and challenging Gait3D dataset. Based on Gait3D-Parsing, we comprehensively evaluate our method and existing gait recognition methods. The experimental results show a significant improvement in accuracy brought by the GPS representation and the superiority of ParsingGait. The code and dataset are available at https://gait3d.github.io/gait3d-parsing-hp .

cs.CV↗

arXiv2023

Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation

Source-free domain adaptation aims to adapt deep neural networks using only pre-trained source models and target data. However, accessing the source model still has a potential concern about leaking the source data, which reveals the patient's privacy. In this paper, we study the challenging but practical problem: black-box source-free domain adaptation where only the outputs of the source model and target data are available. We propose a simple but effective two-stage knowledge distillation method. In Stage \uppercase\expandafter{\romannumeral1}, we train the target model from scratch with soft pseudo-labels generated by the source model in a knowledge distillation manner. In Stage \uppercase\expandafter{\romannumeral2}, we initialize another model as the new student model to avoid the error accumulation caused by noisy pseudo-labels. We feed the images with weak augmentation to the teacher model to guide the learning of the student model. Our method is simple and flexible, and achieves surprising results on three cross-domain segmentation tasks.

cs.CV↗

arXiv2023

Deep Equilibrium Object Detection

Query-based object detectors directly decode image features into object instances with a set of learnable queries. These query vectors are progressively refined to stable meaningful representations through a sequence of decoder layers, and then used to directly predict object locations and categories with simple FFN heads. In this paper, we present a new query-based object detector (DEQDet) by designing a deep equilibrium decoder. Our DEQ decoder models the query vector refinement as the fixed point solving of an {implicit} layer and is equivalent to applying {infinite} steps of refinement. To be more specific to object decoding, we use a two-step unrolled equilibrium equation to explicitly capture the query vector refinement. Accordingly, we are able to incorporate refinement awareness into the DEQ training with the inexact gradient back-propagation (RAG). In addition, to stabilize the training of our DEQDet and improve its generalization ability, we devise the deep supervision scheme on the optimization path of DEQ with refinement-aware perturbation~(RAP). Our experiments demonstrate DEQDet converges faster, consumes less memory, and achieves better results than the baseline counterpart (AdaMixer). In particular, our DEQDet with ResNet50 backbone and 300 queries achieves the $49.5$ mAP and $33.0$ AP$_s$ on the MS COCO benchmark under $2\times$ training scheme (24 epochs).

cs.CV↗

arXiv2023

Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor

This paper proposes a novel Attention-based Encoder-Decoder network for End-to-End Neural speaker Diarization (AED-EEND). In AED-EEND system, we incorporate the target speaker enrollment information used in target speaker voice activity detection (TS-VAD) to calculate the attractor, which can mitigate the speaker permutation problem and facilitate easier model convergence. In the training process, we propose a teacher-forcing strategy to obtain the enrollment information using the ground-truth label. Furthermore, we propose three heuristic decoding methods to identify the enrollment area for each speaker during the evaluation process. Additionally, we enhance the attractor calculation network LSTM used in the end-to-end encoder-decoder based attractor calculation (EEND-EDA) system by incorporating an attention-based model. By utilizing such an attention-based attractor decoder, our proposed AED-EEND system outperforms both the EEND-EDA and TS-VAD systems with only 0.5s of enrollment data.

cs.SD↗

arXiv2023

PHYFU: Fuzzing Modern Physics Simulation Engines

A physical simulation engine (PSE) is a software system that simulates physical environments and objects. Modern PSEs feature both forward and backward simulations, where the forward phase predicts the behavior of a simulated system, and the backward phase provides gradients (guidance) for learning-based control tasks, such as a robot arm learning to fetch items. This way, modern PSEs show promising support for learning-based control methods. To date, PSEs have been largely used in various high-profitable, commercial applications, such as games, movies, virtual reality (VR), and robotics. Despite the prosperous development and usage of PSEs by academia and industrial manufacturers such as Google and NVIDIA, PSEs may produce incorrect simulations, which may lead to negative results, from poor user experience in entertainment to accidents in robotics-involved manufacturing and surgical operations. This paper introduces PHYFU, a fuzzing framework designed specifically for PSEs to uncover errors in both forward and backward simulation phases. PHYFU mutates initial states and asserts if the PSE under test behaves consistently with respect to basic Physics Laws (PLs). We further use feedback-driven test input scheduling to guide and accelerate the search for errors. Our study of four PSEs covers mainstream industrial vendors (Google and NVIDIA) as well as academic products. We successfully uncover over 5K error-triggering inputs that generate incorrect simulation results spanning across the whole software stack of PSEs.

cs.SE↗

arXiv2023

Towards Open-Vocabulary Video Instance Segmentation

Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos. To address this limitation, we make the following three contributions. First, we introduce the novel task of Open-Vocabulary Video Instance Segmentation, which aims to simultaneously segment, track, and classify objects in videos from open-set categories, including novel categories unseen during training. Second, to benchmark Open-Vocabulary VIS, we collect a Large-Vocabulary Video Instance Segmentation dataset (LV-VIS), that contains well-annotated objects from 1,196 diverse categories, significantly surpassing the category size of existing datasets by more than one order of magnitude. Third, we propose an efficient Memory-Induced Transformer architecture, OV2Seg, to first achieve Open-Vocabulary VIS in an end-to-end manner with near real-time inference speed. Extensive experiments on LV-VIS and four existing VIS datasets demonstrate the strong zero-shot generalization ability of OV2Seg on novel categories. The dataset and code are released here https://github.com/haochenheheda/LVVIS.

cs.CV↗

arXiv2023

Low Earth Orbit Satellite Security and Reliability: Issues, Solutions, and the Road Ahead

Low Earth Orbit (LEO) satellites undergo a period of rapid development driven by ever-increasing user demands, reduced costs, and technological progress. Since there is a paucity of literature on the security and reliability issues of LEO Satellite Communication Systems (SCSs), we aim to fill this knowledge gap. Specifically, we critically appraise the inherent characteristics of LEO SCSs and elaborate on their security and reliability requirements. In light of this, we further discuss their vulnerabilities, including potential security attacks launched against them and reliability risks, followed by outlining the associated lessons learned. Subsequently, we discuss the corresponding security and reliability enhancement solutions, unveil a range of trade-offs, and summarize the lessons gleaned. Furthermore, we shed light on several promising future research directions for enhancing the security and reliability of LEO SCSs, such as integrated sensing and communication, computer vision aided communications, as well as challenges brought about by mega-constellation and commercialization. Finally, we summarize the lessons inferred and crystallize the take-away messages in our design guidelines.

eess.SP↗

arXiv2023

Chiral magnetovortical instability

We demonstrate that in a chiral plasma subject to an external magnetic field, the chiral vortical effect can induce a new type of magnetohydrodynamic instability which we refer to as the {\it chiral magnetovortical instability}. This instability arises from the mutual evolution of the magnetic and vortical fields. It can cause a rapid amplification of the magnetic fields by transferring the chirality of the constituent particles to the cross helicity of the plasma.

nucl-th↗

arXiv2023

Wespeaker baselines for VoxSRC2023

This report showcases the results achieved using the wespeaker toolkit for the VoxSRC2023 Challenge. Our aim is to provide participants, especially those with limited experience, with clear and straightforward guidelines to develop their initial systems. Via well-structured recipes and strong results, we hope to offer an accessible and good enough start point for all interested individuals. In this report, we describe the results achieved on the VoxSRC2023 dev set using the pretrained models, you can check the CodaLab evaluation server for the results on the evaluation set.

eess.AS↗

arXiv2023

Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving

While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.

cs.RO↗

arXiv2023

DoF Upper Bound on Three-User MISO Broadcast Channel with Two Antennas and Mixed CSIT

With delayed and imperfect current channel state information at the transmitter (CSIT), namely mixed CSIT, the sum degrees-of-freedom (sum-DoF) in the two-user multiple-input multiple-output (MIMO) broadcast channel and the $K$-user multiple-input single-output (MISO) broadcast channel with not-less-than-$K$ transmit antennas have been obtained. However, the case of the three-user broadcast channel with two transmit antennas and mixed CSIT is still unexplored. In this paper, we investigate the sum-DoF upper bound of three-user MISO broadcast channel with two transmit antennas and mixed CSIT. By exploiting genie-aided signaling and extremal inequalities, we derive the sum-DoF upper bound as $(1-α)3/2 + 9α/4$, which is at most $12.5\%$ larger than the expected sum-DoF, given by $(1-α)3/2 + 2α$. This indicates that the gap may mitigate by better bounding the imperfect current CSIT counterpart.

cs.IT↗

arXiv2023

Towards Generalizable Medical Image Segmentation with Pixel-wise Uncertainty Estimation

Deep neural networks (DNNs) achieve promising performance in visual recognition under the independent and identically distributed (IID) hypothesis. In contrast, the IID hypothesis is not universally guaranteed in numerous real-world applications, especially in medical image analysis. Medical image segmentation is typically formulated as a pixel-wise classification task in which each pixel is classified into a category. However, this formulation ignores the hard-to-classified pixels, e.g., some pixels near the boundary area, as they usually confuse DNNs. In this paper, we first explore that hard-to-classified pixels are associated with high uncertainty. Based on this, we propose a novel framework that utilizes uncertainty estimation to highlight hard-to-classified pixels for DNNs, thereby improving its generalization. We evaluate our method on two popular benchmarks: prostate and fundus datasets. The results of the experiment demonstrate that our method outperforms state-of-the-art methods.

eess.IV↗