arXiv subjects

Chuang Wang

Publications and source records attributed to Chuang Wang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Faster Projected GAN: Towards Faster Few-Shot Image Generation

In order to solve the problems of long training time, large consumption of computing resources and huge parameter amount of GAN network in image generation, this paper proposes an improved GAN network model, which is named Faster Projected GAN, based on Projected GAN. The proposed network is mainly focuses on the improvement of generator of Projected GAN. By introducing depth separable convolution (DSC), the number of parameters of the Projected GAN is reduced, the training speed is accelerated, and memory is saved. Experimental results show that on ffhq-1k, art-painting, Landscape and other few-shot image datasets, a 20% speed increase and a 15% memory saving are achieved. At the same time, FID loss is less or no loss, and the amount of model parameters is better controlled. At the same time, significant training speed improvement has been achieved in the small sample image generation task of special scenes such as earthquake scenes with few public datasets.

cs.CV↗

arXiv2024

Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training

Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance on image generation tasks, enabling highly-flexible control through text-driven generation or energy functions. However, generating photo-realistic images with color and texture from sketch images remains challenging for diffusion models. Sketches typically consist of only a few strokes, with most regions left blank, making it difficult for diffusion-based methods to produce photo-realistic images. In this work, we propose a two-stage method named ``Inversion-by-Inversion" for exemplar-based sketch-to-photo synthesis. This approach includes shape-enhancing inversion and full-control inversion. During the shape-enhancing inversion process, an uncolored photo is generated with the guidance of a shape-energy function. This step is essential to ensure control over the shape of the generated photo. In the full-control inversion process, we propose an appearance-energy function to control the color and texture of the final generated photo.Importantly, our Inversion-by-Inversion pipeline is training-free and can accept different types of exemplars for color and texture control. We conducted extensive experiments to evaluate our proposed method, and the results demonstrate its effectiveness. The code and project can be found at https://ximinng.github.io/inversion-by-inversion-project/.

cs.CV↗

arXiv2023

Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning

Deep Neural Network (DNN) has achieved great success on datasets of closed class set. However, new classes, like new categories of social media topics, are continuously added to the real world, making it necessary to incrementally learn. This is hard for DNN because it tends to focus on fitting to new classes while ignoring old classes, a phenomenon known as catastrophic forgetting. State-of-the-art methods rely on knowledge distillation and data replay techniques but still have limitations. In this work, we analyze the causes of catastrophic forgetting in class incremental learning, which owes to three factors: representation drift, representation confusion, and classifier distortion. Based on this view, we propose a two-stage learning framework with a fixed encoder and an incrementally updated prototype classifier. The encoder is trained with self-supervised learning to generate a feature space with high intrinsic dimensionality, thus improving its transferability and generality. The classifier incrementally learns new prototypes while retaining the prototypes of previously learned data, which is crucial in preserving the decision boundary.Our method does not rely on preserved samples of old classes, is thus a non-exemplar based CIL method. Experiments on public datasets show that our method can significantly outperform state-of-the-art exemplar-based methods when they reserved 5 examplers per class, under the incremental setting of 10 phases, by 18.24% on CIFAR-100 and 9.37% on ImageNet100.

cs.CV↗

arXiv2020

Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation

In recent studies, Generative Adversarial Network (GAN) is one of the popular schemes to augment the image dataset. However, in our study we find the generator G in the GAN fails to generate numerical data in lower-dimensional spaces, and we address overfitting in the generation. By analyzing the Directed Graphical Model (DGM), we propose a theoretical restraint, independence on the loss function, to suppress the overfitting. Practically, as the Statically Restrained GAN (SRGAN) and Dynamically Restrained GAN (DRGAN), two frameworks are proposed to employ the theoretical restraint to the network structure. In the static structure, we predefined a pair of particular network topologies of G and D as the restraint, and quantify such restraint by the interpretable metric Similarity of the Restraint (SR). While for DRGAN we design an adjustable dropout module for the restraint function. In the widely carried out 20 group experiments, on four public numerical class imbalance datasets and five classifiers, the static and dynamic methods together produce the best augmentation results of 19 from 20; and both two methods simultaneously generate 14 of 20 groups of the top-2 best, proving the effectiveness and feasibility of the theoretical restraints.

cs.LG↗

arXiv2020

FISHING Net: Future Inference of Semantic Heatmaps In Grids

For autonomous robots to navigate a complex environment, it is crucial to understand the surrounding scene both geometrically and semantically. Modern autonomous robots employ multiple sets of sensors, including lidars, radars, and cameras. Managing the different reference frames and characteristics of the sensors, and merging their observations into a single representation complicates perception. Choosing a single unified representation for all sensors simplifies the task of perception and fusion. In this work, we present an end-to-end pipeline that performs semantic segmentation and short term prediction using a top-down representation. Our approach consists of an ensemble of neural networks which take in sensor data from different sensor modalities and transform them into a single common top-down semantic grid representation. We find this representation favorable as it is agnostic to sensor-specific reference frames and captures both the semantic and geometric information for the surrounding scene. Because the modalities share a single output representation, they can be easily aggregated to produce a fused output. In this work we predict short-term semantic grids but the framework can be extended to other tasks. This approach offers a simple, extensible, end-to-end approach for multi-modal perception and prediction.

cs.CV↗

arXiv2020

Lossless Attention in Convolutional Networks for Facial Expression Recognition in the Wild

Unlike the constraint frontal face condition, faces in the wild have various unconstrained interference factors, such as complex illumination, changing perspective and various occlusions. Facial expressions recognition (FER) in the wild is a challenging task and existing methods can't perform well. However, for occluded faces (containing occlusion caused by other objects and self-occlusion caused by head posture changes), the attention mechanism has the ability to focus on the non-occluded regions automatically. In this paper, we propose a Lossless Attention Model (LLAM) for convolutional neural networks (CNN) to extract attention-aware features from faces. Our module avoids decay information in the process of generating attention maps by using the information of the previous layer and not reducing the dimensionality. Sequentially, we adaptively refine the feature responses by fusing the attention map with the feature map. We participate in the seven basic expression classification sub-challenges of FG-2020 Affective Behavior Analysis in-the-wild Challenge. And we validate our method on the Aff-Wild2 datasets released by the Challenge. The total accuracy (Accuracy) and the unweighted mean (F1) of our method on the validation set are 0.49 and 0.38 respectively, and the final result is 0.42 (0.67 F1-Score + 0.33 Accuracy).

cs.CV↗

arXiv2019

Theoretical study of structure and magnetism of Ga$_{1-x}$V$_x$Sb compounds for spintronic applications

In this paper, the structural, electronic and magnetic properties of Zinc-blende Ga1-xVxSb compounds, with x from dilute doping situation to extreme doping limiting, were systematically investigated by first-principles calculations. V atoms prefer to substitute the Ga atoms and the formation energy is lower in Sb-rich than Ga-rich growth condition. Meantime, the SbGa antisite defects can effectively decrease the energy barrier of substitution process, from 0.85 eV to 0.53 eV. The diffusion of V atom in GaSb lattice is through meta-stable interstitial sites with an energy barrier of 0.6 eV. At a low V concentration x = 0.0625, V atoms prefer a homogeneous distribution and an antiferromagnetic coupling among them. However, starting from x = 0.5, the magnetic coupling among V atoms changes to be ferromagnetic, due to enhanced superexchange interaction between eg and t2g states of neighbouring V atoms. At the extreme limiting of x = 1.00, we found that Zinc-blende VSb as well as its analogs VAs and VP are intrinsic ferromagneitc semiconductors, with a large change of light absorption at the curie temperature. These results indicate that Ga1-xVxSb compounds can provide a platform to design the new electronic, spintronic and optoelectronic devices.

cond-mat.mtrl-sci↗

arXiv2019

Study of Constrained Network Structures for WGANs on Numeric Data Generation

Some recent studies have suggested using GANs for numeric data generation such as to generate data for completing the imbalanced numeric data. Considering the significant difference between the dimensions of the numeric data and images, as well as the strong correlations between features of numeric data, the conventional GANs normally face an overfitting problem, consequently leads to an ill-conditioning problem in generating numeric and structured data. This paper studies the constrained network structures between generator G and discriminator D in WGAN, designs several structures including isomorphic, mirror and self-symmetric structures. We evaluates the performances of the constrained WGANs in data augmentations, taking the non-constrained GANs and WGANs as the baselines. Experiments prove the constrained structures have been improved in 17/20 groups of experiments. In twenty experiments on four UCI Machine Learning Repository datasets, Australian Credit Approval data, German Credit data, Pima Indians Diabetes data and SPECT heart data facing five conventional classifiers. Especially, Isomorphic WGAN is the best in 15/20 experiments. Finally, we theoretically proves that the effectiveness of constrained structures by the directed graphic model (DGM) analysis.

cs.LG↗

arXiv2019

A Solvable High-Dimensional Model of GAN

We present a theoretical analysis of the training process for a single-layer GAN fed by high-dimensional input data. The training dynamics of the proposed model at both microscopic and macroscopic scales can be exactly analyzed in the high-dimensional limit. In particular, we prove that the macroscopic quantities measuring the quality of the training process converge to a deterministic process characterized by an ordinary differential equation (ODE), whereas the microscopic states containing all the detailed weights remain stochastic, whose dynamics can be described by a stochastic differential equation (SDE). This analysis provides a new perspective different from recent analyses in the limit of small learning rate, where the microscopic state is always considered deterministic, and the contribution of noise is ignored. From our analysis, we show that the level of the background noise is essential to the convergence of the training process: setting the noise level too strong leads to failure of feature recovery, whereas setting the noise too weak causes oscillation. Although this work focuses on a simple copy model of GAN, we believe the analysis methods and insights developed here would prove useful in the theoretical understanding of other variants of GANs with more advanced training algorithms.

cs.LG↗

arXiv2019

Electronic, magnetic, and optical properties of Mn-doped GaSb: a first-principles study

Half-metallic ferromagnets can produce fully spin-polarized conduction electrons and can be applied to fabricate spintronic devices. Thus, in this study, the electronic structure, magnetic properties, and optical properties of GaSb, which has exhibited half-metallicity, doped with Mn, a 3d transition metal, are calculated using the generalized gradient approximation and Heyd-Scuseria-Ernzerhof (HSE) functional. Ga$_{1-x}$Mn$_x$Sb ($x = 0.25, 0.5, 0.75$) materials exhibit ferromagnetic half-metallic properties and a high Curie temperature, indicating that this series can applied in spintronic devices. Meanwhile, they absorb strongly in the infrared band, suggesting that Ga$_{1-x}$Mn$_{x}$Sb also has potential applications in infrared photoelectric devices.

cond-mat.mtrl-sci↗

arXiv2019

Hexagonal MASnI$_3$ exhibiting strong absorption of ultraviolet photons

MASnI$_3$, an organometallic halide, has great potential in the field of lead-free perovskite solar cells. Ultraviolet photons have been shown to generate deep trapping electronic defects in mesoporous TiO$_2$-based perovskite, affecting its performance and stability. In this study, the structure, electronic properties, and optical properties of the cubic, tetragonal, and hexagonal phases of MASnI$_3$ were studied using first-principles calculations. The results indicate that the hexagonal phase of MASnI$_3$ possesses a larger indirect band gap and larger carrier effective mass along the \emph{c}-axis compared with the cubic and tetragonal phases. These findings were attributed to the enhanced electronic coupling and localization in the hexagonal phase. Moreover, the hexagonal phase exhibited high absorption of ultraviolet photons and high transmission of visible photons, particularly along the \emph{c}-axis. These characteristics demonstrate the potential of hexagonal MASnI$_3$ for application in multijunction perovskite tandem solar cells or as coatings in mesoporous TiO$_2$-based perovskite solar cells to enhance ultraviolet stability and photon utilization.

cond-mat.mtrl-sci↗

arXiv2018

Subspace Estimation from Incomplete Observations: A High-Dimensional Analysis

We present a high-dimensional analysis of three popular algorithms, namely, Oja's method, GROUSE and PETRELS, for subspace estimation from streaming and highly incomplete observations. We show that, with proper time scaling, the time-varying principal angles between the true subspace and its estimates given by the algorithms converge weakly to deterministic processes when the ambient dimension $n$ tends to infinity. Moreover, the limiting processes can be exactly characterized as the unique solutions of certain ordinary differential equations (ODEs). A finite sample bound is also given, showing that the rate of convergence towards such limits is $\mathcal{O}(1/\sqrt{n})$. In addition to providing asymptotically exact predictions of the dynamic performance of the algorithms, our high-dimensional analysis yields several insights, including an asymptotic equivalence between Oja's method and GROUSE, and a precise scaling relationship linking the amount of missing data to the signal-to-noise ratio. By analyzing the solutions of the limiting ODEs, we also establish phase transition phenomena associated with the steady-state performance of these techniques.

cs.LG↗

arXiv2018

An experiment in distributed Internet address management using blockchains

The current system to manage the global pool of IP addresses is centralized in five transnational organizations, the Regional Internet Registries (RIRs). Each of these RIRs manage the address pool for a large number of countries. Because the RIRs are private organizations, they are subject to the legal framework of the country where they are based. This configuration results in a jurisdictional overflow from the legal framework of the countries where the RIR is based to all the countries that the RIRs are serving (the countries served by the RIRs de facto become subjects of the legal system of the country where the RIR is hosted). The situation is aggravated by the deployment of new security techniques such as the RPKI and BGPsec, that enable enforcement of allocations by the RIRs. In this paper we present InBlock, a blockchain-based distributed governance body aimed to provide de-centralized management of IP addresses. InBlock also aims to fulfil the same objectives as the current IP address allocation system, namely, uniqueness, fairness, conservation, aggregation, registration and minimized overhead. InBlock is implemented as a Decentralized Autonomous Organization, i.e., as a set of blockchain's smart contracts in Ethereum. Any entity may request an allocation of addresses to the InBlock registry by solely performing a (crypto)currency transfer to the InBlock. The fee required, along with the annual renewal fee, serves as a mechanism to deter stockpiling and other wasteful practices. As with any novel technology, there are many open questions about the usage of blockchains to build an IP address registry. For this reason, we believe that practical experimentation is required in order to have hands-on experiences about such a system. We propose to conduct an experiment on distributed address management using InBlock as a starting point to inform future directions in this area.

cs.NI↗

arXiv2017

Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA

We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal component analysis. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measures of the target feature vector and its estimates provided by the algorithms will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numerical solutions of this PDE can be efficiently obtained. These solutions lead to precise predictions of the performance of the algorithms, as many practical performance metrics are linear functionals of the joint empirical measures. In addition to characterizing the dynamic performance of online learning algorithms, our asymptotic analysis also provides useful insights. In particular, in the high-dimensional limit, and due to exchangeability, the original coupled dynamics associated with the algorithms will be asymptotically "decoupled", with each coordinate independently solving a 1-D effective minimization problem via stochastic gradient descent. Exploiting this insight for nonconvex optimization problems may prove an interesting line of future research.

cs.LG↗

arXiv2017

The Scaling Limit of High-Dimensional Online Independent Component Analysis

We analyze the dynamics of an online algorithm for independent component analysis in the high-dimensional scaling limit. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measure of the target feature vector and the estimates provided by the algorithm will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numerical solutions of this PDE, which involves two spatial variables and one time variable, can be efficiently obtained. These solutions provide detailed information about the performance of the ICA algorithm, as many practical performance metrics are functionals of the joint empirical measures. Numerical simulations show that our asymptotic analysis is accurate even for moderate dimensions. In addition to providing a tool for understanding the performance of the algorithm, our PDE analysis also provides useful insight. In particular, in the high-dimensional limit, the original coupled dynamics associated with the algorithm will be asymptotically "decoupled", with each coordinate independently solving a 1-D effective minimization problem via stochastic gradient descent. Exploiting this insight to design new algorithms for achieving optimal trade-offs between computational and statistical efficiency may prove an interesting line of future research.

cs.LG↗

arXiv2016

Online Learning for Sparse PCA in High Dimensions: Exact Dynamics and Phase Transitions

We study the dynamics of an online algorithm for learning a sparse leading eigenvector from samples generated from a spiked covariance model. This algorithm combines the classical Oja's method for online PCA with an element-wise nonlinearity at each iteration to promote sparsity. In the high-dimensional limit, the joint empirical measure of the underlying sparse eigenvector and its estimate provided by the algorithm is shown to converge weakly to a deterministic, measure-valued process. This scaling limit is characterized as the unique solution of a nonlinear PDE, and it provides exact information regarding the asymptotic performance of the algorithm. For example, performance metrics such as the cosine similarity and the misclassification rate in sparse support recovery can be obtained by examining the limiting dynamics. A steady-state analysis of the nonlinear PDE also reveals an interesting phase transition phenomenon. Although our analysis is asymptotic in nature, numerical simulations show that the theoretical predictions are accurate for moderate signal dimensions.

cs.IT↗

arXiv2016

On one-step replica symmetry breaking in the Edwards-Anderson spin glass model

We consider a one-step replica symmetry breaking description of the Edwards-Anderson spin glass model in 2D. The ingredients of this description are a Kikuchi approximation to the free energy and a second-level statistical model built on the extremal points of the Kikuchi approximation, which are also fixed points of a Generalized Belief Propagation (GBP) scheme. We show that a generalized free energy can be constructed where these extremal points are exponentially weighted by their Kikuchi free energy and a Parisi parameter $y$, and that the Kikuchi approximation of this generalized free energy leads to second-level, one-step replica symmetry breaking (1RSB), GBP equations. We then proceed analogously to Bethe approximation case for tree-like graphs, where it has been shown that 1RSB Belief Propagation equations admit a Survey Propagation solution. We discuss when and how the one-step-replica symmetry breaking GBP equations that we obtain also allow a simpler class of solutions which can be interpreted as a class of Generalized Survey Propagation equations for the single instance graph case.

cond-mat.dis-nn↗

arXiv2015

Randomized Kaczmarz Algorithm for Inconsistent Linear Systems: An Exact MSE Analysis

We provide a complete characterization of the randomized Kaczmarz algorithm (RKA) for inconsistent linear systems. The Kaczmarz algorithm, known in some fields as the algebraic reconstruction technique, is a classical method for solving large-scale overdetermined linear systems through a sequence of projection operators; the randomized Kaczmarz algorithm is a recent proposal by Strohmer and Vershynin to randomize the sequence of projections in order to guarantee exponential convergence (in mean square) to the solutions. A flurry of work followed this development, with renewed interest in the algorithm, its extensions, and various bounds on their performance. Earlier, we studied the special case of consistent linear systems and provided an exact formula for the mean squared error (MSE) in the value reconstructed by RKA, as well as a simple way to compute the exact decay rate of the error. In this work, we consider the case of inconsistent linear systems, which is a more relevant scenario for most applications. First, by using a "lifting trick", we derive an exact formula for the MSE given a fixed noise vector added to the measurements. Then we show how to average over the noise when it is drawn from a distribution with known first and second-order statistics. Finally, we demonstrate the accuracy of our exact MSE formulas through numerical simulations, which also illustrate that previous upper bounds in the literature may be several orders of magnitude too high.

math.NA↗