Search arXiv⌕ Search

arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 775 records · Page 43Linked to original sources
arXiv2021

Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition

The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural representation for different motion patterns, which has difficulty in capturing fine-grained action classes given limited training data. To address the aforementioned problems, we propose a novel multi-granular spatio-temporal graph network for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns. To this end, we develop a dual-head graph network consisting of two interleaved branches, which enables us to extract features at two spatio-temporal resolutions in an effective and efficient manner. Moreover, our network utilises a cross-head communication strategy to mutually enhance the representations of both heads. We conducted extensive experiments on three large-scale datasets, namely NTU RGB+D 60, NTU RGB+D 120, and Kinetics-Skeleton, and achieves the state-of-the-art performance on all the benchmarks, which validates the effectiveness of our method.

cs.CV↗
arXiv2021

Two-sided Dirichlet heat estimates of symmetric stable processes on horn-shaped regions

In this paper, we consider symmetric $α$-stable processes on (unbounded) horn-shaped regions which are non-uniformly $C^{1,1}$ near infinity. By using probabilistic approaches extensively, we establish two-sided Dirichlet heat estimates of such processes for all time. The estimates are very sensitive with respect to the reference function corresponding to each horn-shaped region. Our results also cover the case that the associated Dirichlet semigroup is not intrinsically ultracontractive. A striking observation from our estimates is that, even when the associated Dirichlet semigroup is intrinsically ultracontractive, the so-called Varopoulos-type estimates do not hold for symmetric stable processes on horn-shaped regions.

math.PR↗
arXiv2021

Flip Learning: Erase to Segment

Nodule segmentation from breast ultrasound images is challenging yet essential for the diagnosis. Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. Unlike existing weakly-supervised approaches, in this study, we propose a novel and general WSS framework called Flip Learning, which only needs the box annotation. Specifically, the target in the label box will be erased gradually to flip the classification tag, and the erased region will be considered as the segmentation result finally. Our contribution is three-fold. First, our proposed approach erases on superpixel level using a Multi-agent Reinforcement Learning framework to exploit the prior boundary knowledge and accelerate the learning process. Second, we design two rewards: classification score and intensity distribution reward, to avoid under- and over-segmentation, respectively. Third, we adopt a coarse-to-fine learning strategy to reduce the residual errors and improve the segmentation performance. Extensively validated on a large dataset, our proposed approach achieves competitive performance and shows great potential to narrow the gap between fully-supervised and weakly-supervised learning.

cs.CV↗
arXiv2021

Distributed Learning for Time-varying Networks: A Scalable Design

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot topic in both industrial and academic communities. Many frameworks, such as federated learning and federated distillation, have been proposed. However, few of them takes good care of obstacles such as the time-varying topology resulted by the characteristics of wireless networks. In this paper, we propose a distributed learning framework based on a scalable deep neural network (DNN) design. By exploiting the permutation equivalence and invariance properties of the learning tasks, the DNNs with different scales for different clients can be built up based on two basic parameter sub-matrices. Further, model aggregation can also be conducted based on these two sub-matrices to improve the learning convergence and performance. Finally, simulation results verify the benefits of the proposed framework by compared with some baselines.

cs.IT↗
arXiv2021

A Novel Interactive Two-stage Joint Retail Electricity Market for Multiple Microgrids

To accommodate the advent of microgrids (MG) managing distributed energy resources (DER) in distribution systems, an interactive two-stage joint retail electricity market mechanism is proposed to provide an effective platform for these prosumers to proactively join in retail transactions. Day-ahead stochastic energy trading between the distribution system operator (DSO) and MGs is conducted in the first stage of a centralized retail market, where a chance-constrained uncertainty distribution locational marginal price (CC-UDLMP) containing the cost of uncertainty precautions is used to settle transactions. In the second stage, a novel intra-day peer-to-peer-based (P2P) flexibility transaction pattern is implemented between MGs in local flexibility markets under the regulation of DSO to eliminate power imbalances caused by rolling-based estimates whilst considering systematic operations. A fully distributed iterative algorithm is presented to find the equilibrium solution of this two-stage sequential game framework. Moreover, in order to enhance the versatility of this algorithm, an improved Lp-box alternating direction methods of multipliers (ADMM) algorithm is used to efficiently resolve the first-stage stochastic economic dispatch problem with a mixed-integer second-order cone structure. It is verified that the proposed market mechanism can effectively improve the overall market efficiency under uncertainties.

eess.SY↗
arXiv2021

Deep Iterative 2D/3D Registration

Deep Learning-based 2D/3D registration methods are highly robust but often lack the necessary registration accuracy for clinical application. A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy. However, it also increases the runtime. In this work, we propose a novel Deep Learning driven 2D/3D registration framework that can be used end-to-end for iterative registration tasks without relying on any further refinement step. We accomplish this by learning the update step of the 2D/3D registration framework using Point-to-Plane Correspondences. The update step is learned using iterative residual refinement-based optical flow estimation, in combination with the Point-to-Plane correspondence solver embedded as a known operator. Our proposed method achieves an average runtime of around 8s, a mean re-projection distance error of 0.60 $\pm$ 0.40 mm with a success ratio of 97 percent and a capture range of 60 mm. The combination of high registration accuracy, high robustness, and fast runtime makes our solution ideal for clinical applications.

cs.CV↗
arXiv2021

Robust Backdoor Attacks against Deep Neural Networks in Real Physical World

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the malicious behaviors by submitting specific backdoor instance. However, almost all the existing backdoor works focused on the digital domain, while few studies investigate the backdoor attacks in real physical world. Restricted to a variety of physical constraints, the performance of backdoor attacks in the real physical world will be severely degraded. In this paper, we propose a robust physical backdoor attack method, PTB (physical transformations for backdoors), to implement the backdoor attacks against deep learning models in the real physical world. Specifically, in the training phase, we perform a series of physical transformations on these injected backdoor instances at each round of model training, so as to simulate various transformations that a backdoor may experience in real world, thus improves its physical robustness. Experimental results on the state-of-the-art face recognition model show that, compared with the backdoor methods that without PTB, the proposed attack method can significantly improve the performance of backdoor attacks in real physical world. Under various complex physical conditions, by injecting only a very small ratio (0.5%) of backdoor instances, the attack success rate of physical backdoor attacks with the PTB method on VGGFace is 82%, while the attack success rate of backdoor attacks without the proposed PTB method is lower than 11%. Meanwhile, the normal performance of the target DNN model has not been affected.

cs.CR↗
arXiv2021

Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluations

The training and creation of deep learning model is usually costly, thus it can be regarded as an intellectual property (IP) of the model creator. However, malicious users who obtain high-performance models may illegally copy, redistribute, or abuse the models without permission. To deal with such security threats, a few deep neural networks (DNN) IP protection methods have been proposed in recent years. This paper attempts to provide a review of the existing DNN IP protection works and also an outlook. First, we propose the first taxonomy for DNN IP protection methods in terms of six attributes: scenario, mechanism, capacity, type, function, and target models. Then, we present a survey on existing DNN IP protection works in terms of the above six attributes, especially focusing on the challenges these methods face, whether these methods can provide proactive protection, and their resistances to different levels of attacks. After that, we analyze the potential attacks on DNN IP protection methods from the aspects of model modifications, evasion attacks, and active attacks. Besides, a systematic evaluation method for DNN IP protection methods with respect to basic functional metrics, attack-resistance metrics, and customized metrics for different application scenarios is given. Lastly, future research opportunities and challenges on DNN IP protection are presented.

cs.CR↗
arXiv2021

Bayesian Atlas Building with Hierarchical Priors for Subject-specific Regularization

This paper presents a novel hierarchical Bayesian model for unbiased atlas building with subject-specific regularizations of image registration. We develop an atlas construction process that automatically selects parameters to control the smoothness of diffeomorphic transformation according to individual image data. To achieve this, we introduce a hierarchical prior distribution on regularization parameters that allows multiple penalties on images with various degrees of geometric transformations. We then treat the regularization parameters as latent variables and integrate them out from the model by using the Monte Carlo Expectation Maximization (MCEM) algorithm. Another advantage of our algorithm is that it eliminates the need for manual parameter tuning, which can be tedious and infeasible. We demonstrate the effectiveness of our model on 3D brain MR images. Experimental results show that our model provides a sharper atlas compared to the current atlas building algorithms with single-penalty regularizations. Our code is publicly available at https://github.com/jw4hv/HierarchicalBayesianAtlasBuild.

cs.CV↗
arXiv2021

Magnetization-tuned topological quantum phase transition in MnBi2Te4 devices

Recently, the intrinsic magnetic topological insulator MnBi2Te4 has attracted enormous research interest due to the great success in realizing exotic topological quantum states, such as the quantum anomalous Hall effect (QAHE), axion insulator state, high-Chern-number and high-temperature Chern insulator states. One key issue in this field is to effectively manipulate these states and control topological phase transitions. Here, by systematic angle-dependent transport measurements, we reveal a magnetization-tuned topological quantum phase transition from Chern insulator to magnetic insulator with gapped Dirac surface states in MnBi2Te4 devices. Specifically, as the magnetic field is tilted away from the out-of-plane direction by around 40-60 degrees, the Hall resistance deviates from the quantization value and a colossal, anisotropic magnetoresistance is detected. The theoretical analyses based on modified Landauer-Buttiker formalism show that the field-tilt-driven switching from ferromagnetic state to canted antiferromagnetic state induces a topological quantum phase transition from Chern insulator to magnetic insulator with gapped Dirac surface states in MnBi2Te4 devices. Our work provides an efficient means for modulating topological quantum states and topological quantum phase transitions.

cond-mat.mes-hall↗
arXiv2021

Asymptotically Safe Gravity-Fermion systems on curved backgrounds

We set up a consistent background field formalism for studying the renormalization group (RG) flow of gravity coupled to $N_f$ Dirac fermions on maximally symmetric backgrounds. Based on Wetterich's equation we perform a detailed study of the resulting fixed point structure in a projection including the Einstein-Hilbert action, the fermion anomalous dimension, and a specific coupling of the fermion bilinears to the spacetime curvature. The latter constitutes a mass-type term which breaks chiral symmetry explicitly. Our analysis identifies two infinite families of interacting RG fixed points which are viable candidates to provide a high-energy completion through the asymptotic safety mechanism. The fixed points exist for all values of $N_f$ outside of a small window situated at low values $N_f$ and become weakly coupled in the large $N_f$-limit. Symmetry-wise, they correspond to "quasi-chiral" and "non-chiral" fixed points. The former come with enhanced predictive power, fixing one of the couplings via the asymptotic safety condition. Moreover, the interplay of the fixed points allows for cross-overs from the non-chiral to the chiral fixed point, giving a dynamical mechanism for restoring the symmetry approximately at intermediate scales. Our discussion of chiral symmetry breaking effects provides strong indications that the topology of spacetime plays a crucial role when analyzing whether quantum gravity admits light chiral fermions.

hep-th↗
arXiv2021

Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack information such as the trigger size, which is difficult to satisfy in realistic scenarios. In this paper, a novel backdoor detection method based on adversarial examples is proposed. The proposed method leverages intentional adversarial perturbations to detect whether an image contains a trigger, which can be applied in both the training stage and the inference stage (sanitize the training set in training stage and detect the backdoor instances in inference stage). Specifically, given an untrusted image, the adversarial perturbation is added to the image intentionally. If the prediction of the model on the perturbed image is consistent with that on the unperturbed image, the input image will be considered as a backdoor instance. Compared with most existing defense works, the proposed adversarial perturbation based method requires low computational resources and maintains the visual quality of the images. Experimental results show that, the backdoor detection rate of the proposed defense method is 99.63%, 99.76% and 99.91% on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively. Besides, the proposed method maintains the visual quality of the image as the l2 norm of the added perturbation are as low as 2.8715, 3.0513 and 2.4362 on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively. In addition, it is also demonstrated that the proposed method can achieve high defense performance against backdoor attacks under different attack settings (trigger transparency, trigger size and trigger pattern). Compared with the existing defense work (STRIP), the proposed method has better detection performance on all the three datasets, and is more efficient than STRIP.

cs.CV↗
arXiv2021

Detect and remove watermark in deep neural networks via generative adversarial networks

Deep neural networks (DNN) have achieved remarkable performance in various fields. However, training a DNN model from scratch requires a lot of computing resources and training data. It is difficult for most individual users to obtain such computing resources and training data. Model copyright infringement is an emerging problem in recent years. For instance, pre-trained models may be stolen or abuse by illegal users without the authorization of the model owner. Recently, many works on protecting the intellectual property of DNN models have been proposed. In these works, embedding watermarks into DNN based on backdoor is one of the widely used methods. However, when the DNN model is stolen, the backdoor-based watermark may face the risk of being detected and removed by an adversary. In this paper, we propose a scheme to detect and remove watermark in deep neural networks via generative adversarial networks (GAN). We demonstrate that the backdoor-based DNN watermarks are vulnerable to the proposed GAN-based watermark removal attack. The proposed attack method includes two phases. In the first phase, we use the GAN and few clean images to detect and reverse the watermark in the DNN model. In the second phase, we fine-tune the watermarked DNN based on the reversed backdoor images. Experimental evaluations on the MNIST and CIFAR10 datasets demonstrate that, the proposed method can effectively remove about 98% of the watermark in DNN models, as the watermark retention rate reduces from 100% to less than 2% after applying the proposed attack. In the meantime, the proposed attack hardly affects the model's performance. The test accuracy of the watermarked DNN on the MNIST and the CIFAR10 datasets drops by less than 1% and 3%, respectively.

cs.MM↗
arXiv2021

XCloud-pFISTA: A Medical Intelligence Cloud for Accelerated MRI

Machine learning and artificial intelligence have shown remarkable performance in accelerated magnetic resonance imaging (MRI). Cloud computing technologies have great advantages in building an easily accessible platform to deploy advanced algorithms. In this work, we develop an open-access, easy-to-use and high-performance medical intelligence cloud computing platform (XCloud-pFISTA) to reconstruct MRI images from undersampled k-space data. Two state-of-the-art approaches of the Projected Fast Iterative Soft-Thresholding Algorithm (pFISTA) family have been successfully implemented on the cloud. This work can be considered as a good example of cloud-based medical image reconstruction and may benefit the future development of integrated reconstruction and online diagnosis system.

eess.IV↗
arXiv2021

A Stability Theorem for Maximal $C_{2k+1}$-free Graphs

For any positive integer $k$, we show that every maximal $C_{2k+1}$-free graph with at least $n^2/4-o(n^{3/2})$ edges contains an induced complete bipartite subgraph on $(1-o(1))n$ vertices. We also show that this is best possible.

math.CO↗
arXiv2021

The Generalized Turán Problem of Two Intersecting Cliques

For $s<r$, let $B_{r,s}$ be the graph consisting of two copies of $K_r$, which share exactly $s$ vertices. Denote by $ex(n, K_r, B_{r,s})$ the maximum number of copies of $K_r$ in a $B_{r,s}$-free graph on $n$ vertices. In 1976, Erdős and Sós determined $ex(n,K_3,B_{3,1})$. Recently, Gowers and Janzer showed that $ex(n,K_r,B_{r,r-1})=n^{r-1-o(1)}$. It is a natural question to ask for $ex(n,K_r,B_{r,s})$ for general $r$ and $s$. In this paper, we mainly consider the problem for $s=1$. Utilizing the Zykov's symmetrization, we show that $ex(n,K_4, B_{4,1})=\lfloor (n-2)^2/4\rfloor$ for $n\geq 45$. For $r\geq 5$ and $n$ sufficiently large, by the Füredi's structure theorem we show that $ex(n,K_r,B_{r,1}) =\mathcal{N}(K_{r-2},T_{r-2}(n-2))$, where $\mathcal{N}(K_{r-2},T_{r-2}(n-2))$ represents the number of copies of $K_{r-2}$ in the $(r-2)$-partite Turán graph on $n-2$ vertices.

math.CO↗
arXiv2021

AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption

A well-trained DNN model can be regarded as an intellectual property (IP) of the model owner. To date, many DNN IP protection methods have been proposed, but most of them are watermarking based verification methods where model owners can only verify their ownership passively after the copyright of DNN models has been infringed. In this paper, we propose an effective framework to actively protect the DNN IP from infringement. Specifically, we encrypt the DNN model's parameters by perturbing them with well-crafted adversarial perturbations. With the encrypted parameters, the accuracy of the DNN model drops significantly, which can prevent malicious infringers from using the model. After the encryption, the positions of encrypted parameters and the values of the added adversarial perturbations form a secret key. Authorized user can use the secret key to decrypt the model. Compared with the watermarking methods which only passively verify the ownership after the infringement occurs, the proposed method can prevent infringement in advance. Moreover, compared with most of the existing active DNN IP protection methods, the proposed method does not require additional training process of the model, which introduces low computational overhead. Experimental results show that, after the encryption, the test accuracy of the model drops by 80.65%, 81.16%, and 87.91% on Fashion-MNIST, CIFAR-10, and GTSRB, respectively. Moreover, the proposed method only needs to encrypt an extremely low number of parameters, and the proportion of the encrypted parameters of all the model's parameters is as low as 0.000205%. The experimental results also indicate that, the proposed method is robust against model fine-tuning attack and model pruning attack. Moreover, for the adaptive attack where attackers know the detailed steps of the proposed method, the proposed method is also demonstrated to be robust.

cs.CR↗