arXiv subjects

Tao Zhang

Publications and source records attributed to Tao Zhang.

At least 505 records · Page 28Linked to original sources

arXiv2022

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of hand-crafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512*512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.

cs.CV↗

arXiv2022

Unified products for Zinbiel 2-algebras

The extending structures problem for Zinbiel 2-algebras is studied. We introduce the concept of unified products for Zinbiel 2-algebras. Some special cases of unified products such as crossed product and matched pair of Zinbiel 2-algebras are investigated. It is proved that the extending problem for Zinbiel 2-algebras can be classified by some non-abelian cohomology theory.

math.RA↗

arXiv2022

RRL:Regional Rotation Layer in Convolutional Neural Networks

Convolutional Neural Networks (CNNs) perform very well in image classification and object detection in recent years, but even the most advanced models have limited rotation invariance. Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features. These methods either increase the workload of training or increase the number of model parameters. To address this problem, this paper proposes a module that can be inserted into the existing networks, and directly incorporates the rotation invariance into the feature extraction layers of the CNNs. This module does not have learnable parameters and will not increase the complexity of the model. At the same time, only by training the upright data, it can perform well on the rotated testing set. These advantages will be suitable for fields such as biomedicine and astronomy where it is difficult to obtain upright samples or the target has no directionality. Evaluate our module with LeNet-5, ResNet-18 and tiny-yolov3, we get impressive results.

cs.CV↗

arXiv2022

End-to-end Alexa Device Arbitration

We introduce a variant of the speaker localization problem, which we call device arbitration. In the device arbitration problem, a user utters a keyword that is detected by multiple distributed microphone arrays (smart home devices), and we want to determine which device was closest to the user. Rather than solving the full localization problem, we propose an end-to-end machine learning system. This system learns a feature embedding that is computed independently on each device. The embeddings from each device are then aggregated together to produce the final arbitration decision. We use a large-scale room simulation to generate training and evaluation data, and compare our system against a signal processing baseline.

eess.AS↗

arXiv2022

Characterization of Pedestal Burst Instabilities during I-mode to H-mode Transition in the EAST Tokamak

Quasi-periodic Pedestal Burst Instabilities (PBIs), featuring alternative turbulence suppression and bursts, have been clearly identified by various edge diagnostics during I-mode to H-mode transition in the EAST Tokamak. The radial distribution of the phase perturbation caused by PBI shows that PBI is localized in the pedestal. Prior to each PBI, a significant increase of density gradient close to the pedestal top can be clearly distinguished, then the turbulence burst is generated, accompanied by the relaxation of the density profile, and then induces an outward particle flux. The relative density perturbation caused by PBIs is about $6 \sim 8\%$. Statistic analyses show that the pedestal normalized density gradient triggering the first PBI has a threshold value, mostly in the range of $22 \sim 24$, suggesting that a PBI triggering instability could be driven by the density gradient. And the pedestal normalized density gradient triggering the last PBI is about $30 \sim 40$ and seems to increase with the loss power and the chord-averaged density. In addition, the frequency of PBI is likely to be inversely proportional to the chord-averaged density and the loss power. These results suggest that PBIs and the density gradient prompt increase prior to PBIs can be considered as the precursor for controlling I-H transition.

physics.plasm-ph↗

arXiv2022

Federated Learning Challenges and Opportunities: An Outlook

Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs. Although many methods and applications have been developed for FL, several critical challenges for practical FL systems remain unaddressed. This paper provides an outlook on FL development, categorized into five emerging directions of FL, namely algorithm foundation, personalization, hardware and security constraints, lifelong learning, and nonstandard data. Our unique perspectives are backed by practical observations from large-scale federated systems for edge devices.

cs.LG↗

arXiv2022

End-to-End Quality-of-Service Assurance with Autonomous Systems: 5G/6G Case Study

Providing differentiated services to meet the unique requirements of different use cases is a major goal of the fifth generation (5G) telecommunication networks and will be even more critical for future 6G systems. Fulfilling this goal requires the ability to assure quality of service (QoS) end to end (E2E), which remains a challenge. A key factor that makes E2E QoS assurance difficult in a telecommunication system is that access networks (ANs) and core networks (CNs) manage their resources autonomously. So far, few results have been available that can ensure E2E QoS over autonomously managed ANs and CNs. Existing techniques rely predominately on each subsystem to meet static local QoS budgets with no recourse in case any subsystem fails to meet its local budgets and, hence will have difficulty delivering E2E assurance. Moreover, most existing distributed optimization techniques that can be applied to assure E2E QoS over autonomous subsystems require the subsystems to exchange sensitive information such as their local decision variables. This paper presents a novel framework and a distributed algorithm that can enable ANs and CNs to autonomously "cooperate" with each other to dynamically negotiate their local QoS budgets and to collectively meet E2E QoS goals by sharing only their estimates of the global constraint functions, without disclosing their local decision variables. We prove that this new distributed algorithm converges to an optimal solution almost surely, and also present numerical results to demonstrate that the convergence occurs quickly even with measurement noise.

eess.SY↗

arXiv2022

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks. However, the effect of the standard PGD attack can be easily weakened by rescaling the logits, while the original decision of every input will not be changed. To mitigate this issue, in this paper, we propose Scale-Invariant Adversarial Attack (SI-PGD), which utilizes the angle between the features in the penultimate layer and the weights in the softmax layer to guide the generation of adversaries. The cosine angle matrix is used to learn angularly discriminative representation and will not be changed with the rescaling of logits, thus making SI-PGD attack to be stable and effective. We evaluate our attack against multiple defenses and show improved performance when compared with existing attacks. Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses. The experimental results show the defense method with our SI mechanism achieves state-of-the-art performance among multi-step and single-step defenses.

cs.CV↗

arXiv2022

Bayesian Promised Persuasion: Dynamic Forward-Looking Multiagent Delegation with Informational Burning

This work studies a dynamic mechanism design problem in which a principal delegates decision makings to a group of privately-informed agents without the monetary transfer or burning. We consider that the principal privately possesses complete knowledge about the state transitions and study how she can use her private observation to support the incentive compatibility of the delegation via informational burning, a process we refer to as the looking-forward persuasion. The delegation mechanism is formulated in which the agents form belief hierarchies due to the persuasion and play a dynamic Bayesian game. We propose a novel randomized mechanism, known as Bayesian promised delegation (BPD), in which the periodic incentive compatibility is guaranteed by persuasions and promises of future delegations. We show that the BPD can achieve the same optimal social welfare as the original mechanism in stationary Markov perfect Bayesian equilibria. A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.

cs.GT↗

arXiv2022

Multi-layer VI-GNSS Global Positioning Framework with Numerical Solution aided MAP Initialization

Motivated by the goal of achieving long-term drift-free camera pose estimation in complex scenarios, we propose a global positioning framework fusing visual, inertial and Global Navigation Satellite System (GNSS) measurements in multiple layers. Different from previous loosely- and tightly- coupled methods, the proposed multi-layer fusion allows us to delicately correct the drift of visual odometry and keep reliable positioning while GNSS degrades. In particular, local motion estimation is conducted in the inner-layer, solving the problem of scale drift and inaccurate bias estimation in visual odometry by fusing the velocity of GNSS, pre-integration of Inertial Measurement Unit (IMU) and camera measurement in a tightly-coupled way. The global localization is achieved in the outer-layer, where the local motion is further fused with GNSS position and course in a long-term period in a loosely-coupled way. Furthermore, a dedicated initialization method is proposed to guarantee fast and accurate estimation for all state variables and parameters. We give exhaustive tests of the proposed framework on indoor and outdoor public datasets. The mean localization error is reduced up to 63%, with a promotion of 69% in initialization accuracy compared with state-of-the-art works. We have applied the algorithm to Augmented Reality (AR) navigation, crowd sourcing high-precision map update and other large-scale applications.

cs.RO↗

arXiv2021

Screener3D: a Gaseous Time Projection Chamber for Ultra-low Radioactive Material Screening

In experiments searching for rare signals, background events from the detector itself are some of the major factors limiting search sensitivity.Screening for ultra-low radioactive detector materials is becoming ever more essential. We propose to develop a gaseous time projection chamber (TPC) with a Micromegas readout for radio screening. The TPC records three-dimensional trajectories of charged particles emitted from a flat sample placed in the active volume of the detector. The detector can distinguish the origin of an event and identify the particle types with information from trajectories, which significantly increases the screening sensitivity. For $α$ particles from the sample surface, we observe that our proposed detector can reach a sensitivity higher than 100 $μ$Bq$\cdot$m$^{-2}$ within two days.

physics.ins-det↗

arXiv2021

On the Differential Private Data Market: Endogenous Evolution, Dynamic Pricing, and Incentive Compatibility

Privacy is an essential issue in data trading markets. This work uses a mechanism design approach to study the optimal market model to economize the value of privacy of personal data, using differential privacy. The buyer uses a finite number of randomized algorithms to get access to the owners' data in a sequential-composition manner, in which each randomized algorithm is differentially private. Each usage of a randomized algorithm is referred to as a period. Due to the composability of differential privacy, there are inevitable privacy losses accumulated over periods. Hence, we allow the owners to leave the market at the end of any period by making stopping decisions. We define an instrumental kernel function to capture the instrumentalness of owners' preferences and model the formation of each owner's (both intrinsic and instrumental) preference over periods by taking into consideration the composability of differential privacy and the time-varying nature of privacy concerns. Our desideratum is to study the buyer's design regime of optimal market models in a dynamic environment when each owner makes coupled decisions of stopping and reporting of their preferences. The buyer seeks to design a privacy allocation rule that dynamically specifies the degree of privacy protections and a payment rule to compensate for the privacy losses of the owners. The buyer additionally chooses a payment rule which is independent of owners' reports of their preferences to influence the owners' stopping decisions. We characterize the dynamic incentive compatibility and provide a design principle to construct the payment rules in terms of the privacy allocation rule. Further, we relax the buyer's market design problem and provide a sufficient condition for an approximated dynamic incentive-compatible market model.

cs.GT↗

arXiv2021

Dark Matter Search Results from the PandaX-4T Commissioning Run

We report the first dark matter search results using the commissioning data from PandaX-4T. Using a time projection chamber with 3.7-tonne of liquid xenon target and an exposure of 0.63 tonne$\cdot$year, 1058 candidate events are identified within an approximate nuclear recoil energy window between 5 and 100 keV. No significant excess over background is observed. Our data set a stringent limit to the dark matter-nucleon spin-independent interactions, with a lowest excluded cross section (90% C.L.) of $3.8\times10^{-47} $cm$^2$ at a dark matter mass of 30 GeV/$c^2$.

hep-ex↗

arXiv2021

Excited-state spectroscopy of spin defects in hexagonal boron nitride

We used optically detected magnetic resonance (ODMR) technique to directly probe electron-spin resonance transitions in the excited state of negatively-charged boron vacancy (VB-) defects in hexagonal boron nitride (hBN) at room temperature. The data showed that the excited state has a zero-field splitting of ~ 2.1 GHz, a g factor similar to the ground state and two types of hyperfine splitting ~ 90 MHz and ~ 18.8 MHz respectively. Pulsed ODMR experiments were conducted to further verify observed resonant peaks corresponding to spin transitions in the excited state. In addition, negative peaks in photoluminescence and ODMR contrast as a function of magnetic field magnitude and angle at level anti-crossing were observed and explained by coherent spin precession and anisotropic relaxation. This work provided significant insights for studying the structure of VB- excited states, which might be used for quantum information processing and nanoscale quantum sensing.

quant-ph↗

arXiv2021

Light yield and field dependence measurement in PandaX-II dual-phase xenon detector

The dual-phase xenon time projection chamber (TPC) is one of the most sensitive detector technology for dark matter direct search, where the energy deposition of incoming particle can be converted into photons and electrons through xenon excitation and ionization. The detector response to signal energy deposition varies significantly with the electric field in liquid xenon. We study the detector's light yield and its dependence on the electric field in the PandaX-II dual-phase detector containing 580~kg liquid xenon in the sensitive volume. From our measurements, the light yield at electric fields from 0~V/cm to 317~V/cm is obtained for energy depositions up to 236~keV.

physics.ins-det↗

arXiv2021

MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack

Deep neural networks are discovered to be non-robust when attacked by imperceptible adversarial examples, which is dangerous for it applied into medical diagnostic system that requires high reliability. However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks. The preprocessing methods (e.g., random resizing, compression) may lead to the loss of the small lesions feature in the medical image. Retraining the network on the augmented data set is also not practical for medical models that have already been deployed online. Accordingly, it is necessary to design an easy-to-deploy and effective defense framework for medical diagnostic tasks. In this paper, we propose a Robust and Retrain-Less Diagnostic Framework for Medical pretrained models against adversarial attack (i.e., MedRDF). It acts on the inference time of the pertained medical model. Specifically, for each test image, MedRDF firstly creates a large number of noisy copies of it, and obtains the output labels of these copies from the pretrained medical diagnostic model. Then, based on the labels of these copies, MedRDF outputs the final robust diagnostic result by majority voting. In addition to the diagnostic result, MedRDF produces the Robust Metric (RM) as the confidence of the result. Therefore, it is convenient and reliable to utilize MedRDF to convert pre-trained non-robust diagnostic models into robust ones. The experimental results on COVID-19 and DermaMNIST datasets verify the effectiveness of our MedRDF in improving the robustness of medical diagnostic models.

cs.CV↗

arXiv2021

A search for solar axions and anomalous neutrino magnetic moment with the complete PandaX-II data

We report a search for new physics signals using the low energy electron recoil events in the complete data set from PandaX-II, in light of the recent event excess reported by XENON1T. The data correspond to a total exposure of 100.7 ton-day with liquid xenon. With robust estimates of the dominant background spectra, we perform sensitive searches on solar axions and neutrinos with enhanced magnetic moment. We find that the axion-electron coupling $g_{Ae}<4.6\times 10^{-12}$ for an axion mass less than $\rm 0.1~keV/c^2$ and the neutrino magnetic moment $μ_ν<4.9\times 10^{-11}μ_{B}$ at 90% confidence level. The observed excess from XENON1T is within our experimental constraints.

hep-ex↗

arXiv2021

Pre-training Graph Neural Network for Cross Domain Recommendation

A recommender system predicts users' potential interests in items, where the core is to learn user/item embeddings. Nevertheless, it suffers from the data-sparsity issue, which the cross-domain recommendation can alleviate. However, most prior works either jointly learn the source domain and target domain models, or require side-features. However, jointly training and side features would affect the prediction on the target domain as the learned embedding is dominated by the source domain containing bias information. Inspired by the contemporary arts in pre-training from graph representation learning, we propose a pre-training and fine-tuning diagram for cross-domain recommendation. We devise a novel Pre-training Graph Neural Network for Cross-Domain Recommendation (PCRec), which adopts the contrastive self-supervised pre-training of a graph encoder. Then, we transfer the pre-trained graph encoder to initialize the node embeddings on the target domain, which benefits the fine-tuning of the single domain recommender system on the target domain. The experimental results demonstrate the superiority of PCRec. Detailed analyses verify the superiority of PCRec in transferring information while avoiding biases from source domains.

cs.IR↗