arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 721 records · Page 40Linked to original sources

arXiv2022

MixFormer: Mixing Features across Windows and Dimensions

While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at \url{https://github.com/PaddlePaddle/PaddleClas}.

cs.CV↗

arXiv2022

Exponential ergodicity for damping Hamiltonian dynamics with state-dependent and non-local collisions

In this paper, we investigate the exponential ergodicity in a Wasserstein-type distance for a damping Hamiltonian dynamics with state-dependent and non-local collisions, which indeed is a special case of piecewise deterministic Markov processes while is very popular in numerous modelling situations including stochastic algorithms. The approach adopted in this work is based on a combination of the refined basic coupling and the refined reflection coupling for non-local operators. In a certain sense, the main result developed in the present paper is a continuation of the counterpart in \cite{BW2022} on exponential ergodicity of stochastic Hamiltonian systems with Lévy noises and a complement of \cite{BA} upon exponential ergodicity for Andersen dynamics with constant jump rate functions.

math.PR↗

arXiv2022

NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks

Deep learning has recently been widely applied to many applications across different domains, e.g., image classification and audio recognition. However, the quality of Deep Neural Networks (DNNs) still raises concerns in the practical operational environment, which calls for systematic testing, especially in safety-critical scenarios. Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs. However, due to the blackbox nature of DNN, the existing structural coverage criteria are difficult to interpret, making it hard to understand the underlying principles of these criteria. The relationship between the structural coverage and the decision logic of DNNs is unknown. Moreover, recent studies have further revealed the non-existence of correlation between the structural coverage and DNN defect detection, which further posts concerns on what a suitable DNN testing criterion should be. In this paper, we propose the interpretable coverage criteria through constructing the decision structure of a DNN. Mirroring the control flow graph of the traditional program, we first extract a decision graph from a DNN based on its interpretation, where a path of the decision graph represents a decision logic of the DNN. Based on the control flow and data flow of the decision graph, we propose two variants of path coverage to measure the adequacy of the test cases in exercising the decision logic. The higher the path coverage, the more diverse decision logic the DNN is expected to be explored. Our large-scale evaluation results demonstrate that: the path in the decision graph is effective in characterizing the decision of the DNN, and the proposed coverage criteria are also sensitive with errors including natural errors and adversarial examples, and strongly correlated with the output impartiality.

cs.LG↗

arXiv2022

One Shot Face Swapping on Megapixels

Face swapping has both positive applications such as entertainment, human-computer interaction, etc., and negative applications such as DeepFake threats to politics, economics, etc. Nevertheless, it is necessary to understand the scheme of advanced methods for high-quality face swapping and generate enough and representative face swapping images to train DeepFake detection algorithms. This paper proposes the first Megapixel level method for one shot Face Swapping (or MegaFS for short). Firstly, MegaFS organizes face representation hierarchically by the proposed Hierarchical Representation Face Encoder (HieRFE) in an extended latent space to maintain more facial details, rather than compressed representation in previous face swapping methods. Secondly, a carefully designed Face Transfer Module (FTM) is proposed to transfer the identity from a source image to the target by a non-linear trajectory without explicit feature disentanglement. Finally, the swapped faces can be synthesized by StyleGAN2 with the benefits of its training stability and powerful generative capability. Each part of MegaFS can be trained separately so the requirement of our model for GPU memory can be satisfied for megapixel face swapping. In summary, complete face representation, stable training, and limited memory usage are the three novel contributions to the success of our method. Extensive experiments demonstrate the superiority of MegaFS and the first megapixel level face swapping database is released for research on DeepFake detection and face image editing in the public domain. The dataset is at this link.

cs.CV↗

arXiv2022

Nonlinear Hall effect induced by internal Coulomb interaction and phase relaxation process in a four-terminal system with time-reversal symmetry

We numerically investigate the second-order nonlinear Hall transport properties of a four-terminal system with time-reversal symmetry and broken inversion symmetry. Within the nonequilibrium Green's function formalism, the second-order nonlinear conductances are derived, where the internal Coulomb potential in response to external voltages is explicitly included to guarantee the gauge invariance. For the system with single mirror symmetry Mx, nonlinear Hall properties are only observable in the y direction and contributed solely from the second-order nonlinear effect. From the symmetry point of view, the observed nonlinear Hall transport phenomena have one-to-one correspondence with the Berry curvature dipole induced nonlinear Hall effect semiclassically obtained for the same Hamiltonian. In addition to the nonlinear Hall effect originated from symmetries of the system, it is found that the internal Coulomb potential has the same symmetry of the four-terminal system, which gives rise to an extra nonlinear Hall response. Moreover, the phase relaxation mechanism modeled by virtual probes leads to the dephasing-induced nonlinear Hall effect.

cond-mat.mes-hall↗

arXiv2022

Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacy

Recent years, local differential privacy (LDP) has been adopted by many web service providers like Google \cite{erlingsson2014rappor}, Apple \cite{apple2017privacy} and Microsoft \cite{bolin2017telemetry} to collect and analyse users' data privately. In this paper, we consider the problem of discrete distribution estimation under local differential privacy constraints. Distribution estimation is one of the most fundamental estimation problems, which is widely studied in both non-private and private settings. In the local model, private mechanisms with provably optimal sample complexity are known. However, they are optimal only in the worst-case sense; their sample complexity is proportional to the size of the entire universe, which could be huge in practice. In this paper, we consider sparse or approximately sparse (e.g.\ highly skewed) distribution, and show that the number of samples needed could be significantly reduced. This problem has been studied recently \cite{acharya2021estimating}, but they only consider strict sparse distributions and the high privacy regime. We propose new privatization mechanisms based on compressive sensing. Our methods work for approximately sparse distributions and medium privacy, and have optimal sample and communication complexity.

cs.IT↗

arXiv2022

Image Steganography based on Style Transfer

Image steganography is the art and science of using images as cover for covert communications. With the development of neural networks, traditional image steganography is more likely to be detected by deep learning-based steganalysis. To improve upon this, we propose image steganography network based on style transfer, and the embedding of secret messages can be disguised as image stylization. We embed secret information while transforming the content image style. In latent space, the secret information is integrated into the latent representation of the cover image to generate the stego images, which are indistinguishable from normal stylized images. It is an end-to-end unsupervised model without pre-training. Extensive experiments on the benchmark dataset demonstrate the reliability, quality and security of stego images generated by our steganographic network.

cs.CV↗

arXiv2022

Thermal Modelling and Controller Design of an Alkaline Electrolysis System under Dynamic Operating Conditions

Thermal management is vital for the efficient and safe operation of alkaline electrolysis systems. Traditional alkaline electrolysis systems use simple proportional-integral-differentiation (PID) controllers to maintain the stack temperature near the rated value. However, in renewable-to-hydrogen scenarios, the stack temperature is disturbed by load fluctuations, and the temperature overshoot phenomenon occurs which can exceed the upper limit and harm the stack. This paper focuses on the thermal modelling and controller design of an alkaline electrolysis system under dynamic operating conditions. A control-oriented thermal model is established in the form of a third-order time-delay process, which is used for simulation and controller design. Based on this model, we propose two novel controllers to reduce temperature overshoot: one is a current feed-forward PID controller (PID-I), the other is a model predictive controller (MPC). Their performances are tested on a lab-scale system and the experimental results are satisfying: the temperature overshoot is reduced by 2.2 degree with the PID-I controller, and no obvious overshoot is observed with the MPC controller. Furthermore, the thermal dynamic performance of an MW-scale alkaline electrolysis system is analyzed by simulation, which shows that the temperature overshoot phenomenon is more general in large systems. The proposed method allows for higher temperature set points which can improve system efficiency by 1%.

eess.SY↗

arXiv2022

Explore-Bench: Data Sets, Metrics and Evaluations for Frontier-based and Deep-reinforcement-learning-based Autonomous Exploration

Autonomous exploration and mapping of unknown terrains employing single or multiple robots is an essential task in mobile robotics and has therefore been widely investigated. Nevertheless, given the lack of unified data sets, metrics, and platforms to evaluate the exploration approaches, we develop an autonomous robot exploration benchmark entitled Explore-Bench. The benchmark involves various exploration scenarios and presents two types of quantitative metrics to evaluate exploration efficiency and multi-robot cooperation. Explore-Bench is extremely useful as, recently, deep reinforcement learning (DRL) has been widely used for robot exploration tasks and achieved promising results. However, training DRL-based approaches requires large data sets, and additionally, current benchmarks rely on realistic simulators with a slow simulation speed, which is not appropriate for training exploration strategies. Hence, to support efficient DRL training and comprehensive evaluation, the suggested Explore-Bench designs a 3-level platform with a unified data flow and $12 \times$ speed-up that includes a grid-based simulator for fast evaluation and efficient training, a realistic Gazebo simulator, and a remotely accessible robot testbed for high-accuracy tests in physical environments. The practicality of the proposed benchmark is highlighted with the application of one DRL-based and three frontier-based exploration approaches. Furthermore, we analyze the performance differences and provide some insights about the selection and design of exploration methods. Our benchmark is available at https://github.com/efc-robot/Explore-Bench.

cs.RO↗

arXiv2022

Refinements of Franks' theorem and applications in Reeb dynamics

In this article, we give two refinements of Franks' theorem: For orientation and area preserving homeomorphisms of the closed or open annulus, the existence of $k$-periodic orbits ($(k,n_0)=1$) forces the existence of infinitely many periodic orbits with periods prime to $n_0$. Moreover, if $f$ is reversible, the periodic orbits above could be symmetric. Our improvements of Franks' theorem can be applied to Reeb dynamics and celestial mechanics, for example, we give some precise information about the symmetries of periodic orbits found in Hofer, Wysocki and Zehnder's dichotomy theorem when the tight 3-sphere is equipped with some additional symmetries, and also the symmetries of periodic orbits on the energy level of H$\acute{e}$non-Heiles system in celestial mechanics.

math.DS↗

arXiv2022

Applying Differential Privacy to Tensor Completion

Tensor completion aims at filling the missing or unobserved entries based on partially observed tensors. However, utilization of the observed tensors often raises serious privacy concerns in many practical scenarios. To address this issue, we propose a solid and unified framework that contains several approaches for applying differential privacy to the two most widely used tensor decomposition methods: i) CANDECOMP/PARAFAC~(CP) and ii) Tucker decompositions. For each approach, we establish a rigorous privacy guarantee and meanwhile evaluate the privacy-accuracy trade-off. Experiments on synthetic and real-world datasets demonstrate that our proposal achieves high accuracy for tensor completion while ensuring strong privacy protections.

cs.LG↗

arXiv2022

Hybrid Atlas Building with Deep Registration Priors

Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much reduced computational cost. In contrast to previous approaches that iteratively perform registration tasks between an estimated atlas and individual images, we propose to use learned priors of registration from pre-trained neural networks. This newly developed hybrid framework features several advantages of (i) providing an efficient way of atlas building without losing the quality of results, and (ii) offering flexibility in utilizing a wide variety of deep learning based registration methods. We demonstrate the effectiveness of this proposed model on 3D brain magnetic resonance imaging (MRI) scans.

cs.CV↗

arXiv2022

Deep Learning for Regularization Prediction in Diffeomorphic Image Registration

This paper presents a predictive model for estimating regularization parameters of diffeomorphic image registration. We introduce a novel framework that automatically determines the parameters controlling the smoothness of diffeomorphic transformations. Our method significantly reduces the effort of parameter tuning, which is time and labor-consuming. To achieve the goal, we develop a predictive model based on deep convolutional neural networks (CNN) that learns the mapping between pairwise images and the regularization parameter of image registration. In contrast to previous methods that estimate such parameters in a high-dimensional image space, our model is built in an efficient bandlimited space with much lower dimensions. We demonstrate the effectiveness of our model on both 2D synthetic data and 3D real brain images. Experimental results show that our model not only predicts appropriate regularization parameters for image registration, but also improving the network training in terms of time and memory efficiency.

eess.IV↗

arXiv2022

Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks

Recent researches demonstrate that Deep Neural Networks (DNN) models are vulnerable to backdoor attacks. The backdoored DNN model will behave maliciously when images containing backdoor triggers arrive. To date, existing backdoor attacks are single-trigger and single-target attacks, and the triggers of most existing backdoor attacks are obvious thus are easy to be detected or noticed. In this paper, we propose a novel imperceptible and multi-channel backdoor attack against Deep Neural Networks by exploiting Discrete Cosine Transform (DCT) steganography. Based on the proposed backdoor attack method, we implement two variants of backdoor attacks, i.e., N-to-N backdoor attack and N-to-One backdoor attack. Specifically, for a colored image, we utilize DCT steganography to construct the trigger on different channels of the image. As a result, the trigger is stealthy and natural. Based on the proposed method, we implement multi-target and multi-trigger backdoor attacks. Experimental results demonstrate that the average attack success rate of the N-to-N backdoor attack is 93.95% on CIFAR-10 dataset and 91.55% on TinyImageNet dataset, respectively. The average attack success rate of N-to-One attack is 90.22% and 89.53% on CIFAR-10 and TinyImageNet datasets, respectively. Meanwhile, the proposed backdoor attack does not affect the classification accuracy of the DNN model. Moreover, the proposed attack is demonstrated to be robust to the state-of-the-art backdoor defense (Neural Cleanse).

cs.CV↗

arXiv2022

Spectral broadening of a single Er$^{3+}$ ion in a Si nano-transistor

Single rare-earth ions in solids show great potential for quantum applications, including single photon emission, quantum computing, and high-precision sensing. However, homogeneous linewidths observed for single rare-earth ions are orders of magnitude larger than the sub-kilohertz linewidths observed for ensembles in bulk crystals. The spectral broadening creates a significant challenge for achieving entanglement generation and qubit operation with single rare-earth ions, so it is critical to investigate the broadening mechanisms. We report a spectral broadening study on a single Er$^{3+}$ ion in a Si nano-transistor. The Er-induced photoionisation rate is found to be an appropriate quantity to represent the optical transition probability for spectroscopic studies, and the single ion spectra display a Lorentzian lineshape at all optical powers in use. Spectral broadening is observed at relatively high optical powers and is caused by spectral diffusion on a fast time scale.

quant-ph↗

arXiv2022

Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision

Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.

cs.CV↗

arXiv2022

A Sparse Model-inspired Deep Thresholding Network for Exponential Signal Reconstruction -- Application in Fast Biological Spectroscopy

The non-uniform sampling is a powerful approach to enable fast acquisition but requires sophisticated reconstruction algorithms. Faithful reconstruction from partial sampled exponentials is highly expected in general signal processing and many applications. Deep learning has shown astonishing potential in this field but many existing problems, such as lack of robustness and explainability, greatly limit its applications. In this work, by combining merits of the sparse model-based optimization method and data-driven deep learning, we propose a deep learning architecture for spectra reconstruction from undersampled data, called MoDern. It follows the iterative reconstruction in solving a sparse model to build the neural network and we elaborately design a learnable soft-thresholding to adaptively eliminate the spectrum artifacts introduced by undersampling. Extensive results on both synthetic and biological data show that MoDern enables more robust, high-fidelity, and ultra-fast reconstruction than the state-of-the-art methods. Remarkably, MoDern has a small number of network parameters and is trained on solely synthetic data while generalizing well to biological data in various scenarios. Furthermore, we extend it to an open-access and easy-to-use cloud computing platform (XCloud-MoDern), contributing a promising strategy for further development of biological applications.

cs.LG↗

arXiv2022

An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

A major limitation of fuzzy or neuro-fuzzy systems is their failure to deal with high-dimensional datasets. This happens primarily due to the use of T-norm, particularly, product or minimum (or a softer version of it). Thus, there are hardly any work dealing with datasets with dimensions more than hundred or so. Here, we propose a neuro-fuzzy framework that can handle datasets with dimensions even more than 7000! In this context, we propose an adaptive softmin (Ada-softmin) which effectively overcomes the drawbacks of ``numeric underflow" and ``fake minimum" that arise for existing fuzzy systems while dealing with high-dimensional problems. We call it an Adaptive Takagi-Sugeno-Kang (AdaTSK) fuzzy system. We then equip the AdaTSK system to perform feature selection and rule extraction in an integrated manner. In this context, a novel gate function is introduced and embedded only in the consequent parts, which can determine the useful features and rules, in two successive phases of learning. Unlike conventional fuzzy rule bases, we design an enhanced fuzzy rule base (En-FRB), which maintains adequate rules but does not grow the number of rules exponentially with dimension that typically happens for fuzzy neural networks. The integrated Feature Selection and Rule Extraction AdaTSK (FSRE-AdaTSK) system consists of three sequential phases: (i) feature selection, (ii) rule extraction, and (iii) fine tuning. The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with dimension greater than 7000. This may be the first time fuzzy systems are realized for classification involving more than 7000 input features.

cs.LG↗