arXiv subjects

Jing Zhao

Publications and source records attributed to Jing Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2023

A Framework of Full-Process Generation Design for Park Green Spaces Based on Remote Sensing Segmentation-GAN-Diffusion

The development of generative design driven by artificial intelligence algorithms is speedy. There are two research gaps in the current research: 1) Most studies only focus on the relationship between design elements and pay little attention to the external information of the site; 2) GAN and other traditional generative algorithms generate results with low resolution and insufficient details. To address these two problems, we integrate GAN, Stable diffusion multimodal large-scale image pre-training model to construct a full-process park generative design method: 1) First, construct a high-precision remote sensing object extraction system for automated extraction of urban environmental information; 2) Secondly, use GAN to construct a park design generation system based on the external environment, which can quickly infer and generate design schemes from urban environmental information; 3) Finally, introduce Stable Diffusion to optimize the design plan, fill in details, and expand the resolution of the plan by 64 times. This method can achieve a fully unmanned design automation workflow. The research results show that: 1) The relationship between the inside and outside of the site will affect the algorithm generation results. 2) Compared with traditional GAN algorithms, Stable diffusion significantly improve the information richness of the generated results.

cs.CV↗

arXiv2023

Rethinking the Cloudonomics of Efficient I/O for Data-Intensive Analytics Applications

This paper explores a prevailing trend in the industry: migrating data-intensive analytics applications from on-premises to cloud-native environments. We find that the unique cost models associated with cloud-based storage necessitate a more nuanced understanding of optimizing performance. Specifically, based on traces collected from Uber's Presto fleet in production, we argue that common I/O optimizations, such as table scan and filter, and broadcast join, may lead to unexpected costs when naively applied in the cloud. This is because traditional I/O optimizations mainly focus on improving throughput or latency in on-premises settings, without taking into account the monetary costs associated with storage API calls. In cloud environments, these costs can be significant, potentially involving billions of API calls per day just for Presto workloads at Uber scale. Presented as a case study, this paper serves as a starting point for further research to design efficient I/O strategies specifically tailored for data-intensive applications in cloud settings.

cs.DC↗

arXiv2023

MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection

Multimodal time series (MTS) anomaly detection is crucial for maintaining the safety and stability of working devices (e.g., water treatment system and spacecraft), whose data are characterized by multivariate time series with diverse modalities. Although recent deep learning methods show great potential in anomaly detection, they do not explicitly capture spatial-temporal relationships between univariate time series of different modalities, resulting in more false negatives and false positives. In this paper, we propose a multimodal spatial-temporal graph attention network (MST-GAT) to tackle this problem. MST-GAT first employs a multimodal graph attention network (M-GAT) and a temporal convolution network to capture the spatial-temporal correlation in multimodal time series. Specifically, M-GAT uses a multi-head attention module and two relational attention modules (i.e., intra- and inter-modal attention) to model modal correlations explicitly. Furthermore, MST-GAT optimizes the reconstruction and prediction modules simultaneously. Experimental results on four multimodal benchmarks demonstrate that MST-GAT outperforms the state-of-the-art baselines. Further analysis indicates that MST-GAT strengthens the interpretability of detected anomalies by locating the most anomalous univariate time series.

cs.LG↗

arXiv2023

A generalized Stokes system with a nonsmooth slip boundary condition

A class of quasi-variational-hemivariational inequalities in reflexive Banach spaces is studied. The inequalities contain a convex potential, a locally Lipschitz superpotential, and an implicit obstacle set of constraints. Results on the well posedness are established including existence, uniqueness, dependence of solution on the data, and the compactness of the solution set in the strong topology. The applicability of the results is illustrated by the steady-state Stokes model of a generalized Newtonian incompressible fluid with a nonmonotone slip boundary condition.

math.AP↗

arXiv2023

Null-text Guidance in Diffusion Models is Secretly a Cartoon-style Creator

Classifier-free guidance is an effective sampling technique in diffusion models that has been widely adopted. The main idea is to extrapolate the model in the direction of text guidance and away from null-text guidance. In this paper, we demonstrate that null-text guidance in diffusion models is secretly a cartoon-style creator, i.e., the generated images can be efficiently transformed into cartoons by simply perturbing the null-text guidance. Specifically, we proposed two disturbance methods, i.e., Rollback disturbance (Back-D) and Image disturbance (Image-D), to construct misalignment between the noisy images used for predicting null-text guidance and text guidance (subsequently referred to as \textbf{null-text noisy image} and \textbf{text noisy image} respectively) in the sampling process. Back-D achieves cartoonization by altering the noise level of null-text noisy image via replacing $x_t$ with $x_{t+Δt}$. Image-D, alternatively, produces high-fidelity, diverse cartoons by defining $x_t$ as a clean input image, which further improves the incorporation of finer image details. Through comprehensive experiments, we delved into the principle of noise disturbing for null-text and uncovered that the efficacy of disturbance depends on the correlation between the null-text noisy image and the source image. Moreover, our proposed techniques, which can generate cartoon images and cartoonize specific ones, are training-free and easily integrated as a plug-and-play component in any classifier-free guided diffusion model. Project page is available at \url{https://nulltextforcartoon.github.io/}.

cs.CV↗

arXiv2023

Verifiable Data Sharing Scheme for Dynamic Multi-Owner Setting

One of scenarios in data-sharing applications is that files are managed by multiple owners, and the list of file owners may change dynamically. However, most existing solutions to this problem rely on trusted third parties and have complicated signature permission processes, resulting in additional overhead. Therefore, we propose a verifiable data-sharing scheme (VDS-DM) that can support dynamic multi-owner scenarios. We introduce a management entity that combines linear secret-sharing technology, multi-owner signature generation, and an aggregation technique to allow multi-owner file sharing. Without the help of trusted third parties, VDS-DM can update file signatures for dynamically changing file owners, which helps save communication overhead. Moreover, users independently verify the integrity of files without resorting to a third party. We analyse the security of VDS-DM through a security game. Finally, we conduct enough simulation experiments and the outcomes of experimental demonstrate the feasibility of VDS-DM.

cs.CR↗

arXiv2023

RecursiveDet: End-to-End Region-based Recursive Object Detection

End-to-end region-based object detectors like Sparse R-CNN usually have multiple cascade bounding box decoding stages, which refine the current predictions according to their previous results. Model parameters within each stage are independent, evolving a huge cost. In this paper, we find the general setting of decoding stages is actually redundant. By simply sharing parameters and making a recursive decoder, the detector already obtains a significant improvement. The recursive decoder can be further enhanced by positional encoding (PE) of the proposal box, which makes it aware of the exact locations and sizes of input bounding boxes, thus becoming adaptive to proposals from different stages during the recursion. Moreover, we also design centerness-based PE to distinguish the RoI feature element and dynamic convolution kernels at different positions within the bounding box. To validate the effectiveness of the proposed method, we conduct intensive ablations and build the full model on three recent mainstream region-based detectors. The RecusiveDet is able to achieve obvious performance boosts with even fewer model parameters and slightly increased computation cost. Codes are available at https://github.com/bravezzzzzz/RecursiveDet.

cs.CV↗

arXiv2023

MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models

The advent of open-source AI communities has produced a cornucopia of powerful text-guided diffusion models that are trained on various datasets. While few explorations have been conducted on ensembling such models to combine their strengths. In this work, we propose a simple yet effective method called Saliency-aware Noise Blending (SNB) that can empower the fused text-guided diffusion models to achieve more controllable generation. Specifically, we experimentally find that the responses of classifier-free guidance are highly related to the saliency of generated images. Thus we propose to trust different models in their areas of expertise by blending the predicted noises of two diffusion models in a saliency-aware manner. SNB is training-free and can be completed within a DDIM sampling process. Additionally, it can automatically align the semantics of two noise spaces without requiring additional annotations such as masks. Extensive experiments show the impressive effectiveness of SNB in various applications. Project page is available at https://magicfusion.github.io/.

cs.CV↗

arXiv2023

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

cs.CL↗

arXiv2023

A stochastic two-step inertial Bregman proximal alternating linearized minimization algorithm for nonconvex and nonsmooth problems

In this paper, for solving a broad class of large-scale nonconvex and nonsmooth optimization problems, we propose a stochastic two step inertial Bregman proximal alternating linearized minimization (STiBPALM) algorithm with variance-reduced stochastic gradient estimators. And we show that SAGA and SARAH are variance-reduced gradient estimators. Under expectation conditions with the Kurdyka-Lojasiewicz property and some suitable conditions on the parameters, we obtain that the sequence generated by the proposed algorithm converges to a critical point. And the general convergence rate is also provided. Numerical experiments on sparse nonnegative matrix factorization and blind image-deblurring are presented to demonstrate the performance of the proposed algorithm.

math.OC↗

arXiv2023

Enhanced Population on Ionic Excited States by Synchronized Ionization and Multiphoton Resonance

We study population distributions and lasing actions of N_2^+ driven by femtosecond lasers with various wavelengths, and uncover an efficient ionic excitation mechanism induced by synchronized ionization and multiphoton resonance. Our results show that the strongest N_2^+ lasing appears around 1000 nm pump wavelength. At the optimal wavelength, the pump-energy threshold for air lasing generation is reduced by five folds compared with that required by the previous 800 nm pump laser. Simulations based on the ionization-coupling model indicate that although the Stark-assisted three-photon resonance can be satisfied within a broad pump wavelength range, the optimal pump wavelength arises when the dynamic three-photon resonance temporally synchronizes with the ionization injection. In this case, the ionic dipoles created at each half optical cycle have the same phase. The dipole phase locking promotes the continuous population transfer from ionic ground state to the excited state, giving rise to a dramatic increase of excited-state population. This work provides new insight on the photoexcitation mechanism of ions in strong laser fields, and opens up a route for optimizing ionic radiations.

physics.atom-ph↗

arXiv2023

Two-step inertial Bregman proximal alternating linearized minimization algorithm for nonconvex and nonsmooth problems

In this paper, we study an algorithm for solving a class of nonconvex and nonsmooth nonseparable optimization problems. Based on proximal alternating linearized minimization (PALM), we propose a new iterative algorithm which combines two-step inertial extrapolation and Bregman distance. By constructing appropriate benefit function, with the help of Kurdyka--Łojasiewicz property we establish the convergence of the whole sequence generated by proposed algorithm. We apply the algorithm to signal recovery, quadratic fractional programming problem and show the effectiveness of proposed algorithm.

math.OC↗

arXiv2023

Two-step inertial Bregman alternating structure-adapted proximal gradient descent algorithm for nonconvex and nonsmooth problems

In the paper, we introduce several accelerate iterative algorithms for solving the multiple-set split common fixed-point problem of quasi-nonexpansive operators in real Hilbert space. Based on primal-dual method, we construct several iterative algorithms in a way that combines inertial technology and the self-adaptive stepsize such that the implementation of the algorithms doesn't need any prior information about bounded linear operator norm. Under suitable assumptions, weak convergence of the proposed algorithms is established. As applications, we obtain relative iterative algorithms to solve the multiple-set split feasibility problem. Finally, the performance of the proposed algorithms is illustrated by numerical experiments.

math.OC↗

arXiv2022

Inclusive and semi-inclusive production of spin-3/2 hadrons in $e^+e^-$ annihilation

We investigate the inclusive and semi-inclusive productions of spin-3/2 hadrons, such as $Ω$, in unpolarized $e^+ e^-$ annihilation. The general differential cross sections are expressed in terms of structure functions in accordance to the polarization of the hadron and the azimuthal modulations. We derive a complete definition of quark transverse momentum dependent (TMD) fragmentation functions (FFs) to spin-3/2 hadrons for the first time from the decomposition of the quark-quark correlation matrix at leading twist, 14 of which are newly defined corresponding to rank-3 tensor polarized hadron. The collinear FFs are obtained from the $k_T$-integrated correlation matrix, and only two TMD FFs with rank-3 tensor polarization have nonvanishing collinear counterparts. Then we perform a leading order calculation of the unpolarized differential cross sections. In the single-hadron inclusive production, only two structure functions are found nonzero and none of the rank-3 tensor polarized FFs contributes. For the nearly back-to-back two-hadron production, half of the 48 structure functions are found nonzero even if the spin of the second hadron is not analyzed, and ten of the rank-3 tensor polarized TMD FFs contribute. Therefore, one can study the rank-3 tensor polarized FFs via the production of a spin-3/2 hadron and an unpolarized hadron in unpolarized $e^+ e^-$ collision experiments. These newly defined FFs can be further applied in semi-inclusive deep inelastic scattering processes for the study of nucleon structures.

hep-ph↗

arXiv2022

P$^3$LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training

Conventional autoregressive left-to-right (L2R) sequence generation faces two issues during decoding: limited to unidirectional target sequence modeling, and constrained on strong local dependencies. To address the aforementioned problem, we propose P$^3$LM, a probabilistically permuted prophet language model, which strengthens the modeling of bidirectional information and long token dependencies for sequence generation. Specifically, P$^3$LM learns to generate tokens in permuted order upon an order-aware transformer decoder, as well as to generate the corresponding future $N$ tokens with a multi-stream attention mechanism. Extensive experiments are conducted on the GLGE benchmark, which includes four datasets for summarization, two for question generation, one for conversational question answering, and one for dialog response generation, where P$^3$LM achieves state-of-the-art results compared with strong publicly available generative pre-training methods.

cs.CL↗

arXiv2022

IoU-Enhanced Attention for End-to-End Task Specific Object Detection

Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the one-to-one relation between the query and its attending region, it heavily depends on the self attention, which is usually inaccurate in the early training stage. Moreover, in a scene of dense objects, the object query interacts with many irrelevant ones, reducing its uniqueness and harming the performance. This paper proposes to use IoU between different boxes as a prior for the value routing in self attention. The original attention matrix multiplies the same size matrix computed from the IoU of proposal boxes, and they determine the routing scheme so that the irrelevant features can be suppressed. Furthermore, to accurately extract features for both classification and regression, we add two lightweight projection heads to provide the dynamic channel masks based on object query, and they multiply with the output from dynamic convs, making the results suitable for the two different tasks. We validate the proposed scheme on different datasets, including MS-COCO and CrowdHuman, showing that it significantly improves the performance and increases the model convergence speed.

cs.CV↗

arXiv2022

A Safe Semi-supervised Graph Convolution Network

In the semi-supervised learning field, Graph Convolution Network (GCN), as a variant model of GNN, has achieved promising results for non-Euclidean data by introducing convolution into GNN. However, GCN and its variant models fail to safely use the information of risk unlabeled data, which will degrade the performance of semi-supervised learning. Therefore, we propose a Safe GCN framework (Safe-GCN) to improve the learning performance. In the Safe-GCN, we design an iterative process to label the unlabeled data. In each iteration, a GCN and its supervised version(S-GCN) are learned to find the unlabeled data with high confidence. The high-confidence unlabeled data and their pseudo labels are then added to the label set. Finally, both added unlabeled data and labeled ones are used to train a S-GCN which can achieve the safe exploration of the risk unlabeled data and enable safe use of large numbers of unlabeled data. The performance of Safe-GCN is evaluated on three well-known citation network datasets and the obtained results demonstrate the effectiveness of the proposed framework over several graph-based semi-supervised learning methods.

cs.LG↗

arXiv2022

The THUEE System Description for the IARPA OpenASR21 Challenge

This paper describes the THUEE team's speech recognition system for the IARPA Open Automatic Speech Recognition Challenge (OpenASR21), with further experiment explorations. We achieve outstanding results under both the Constrained and Constrained-plus training conditions. For the Constrained training condition, we construct our basic ASR system based on the standard hybrid architecture. To alleviate the Out-Of-Vocabulary (OOV) problem, we extend the pronunciation lexicon using Grapheme-to-Phoneme (G2P) techniques for both OOV and potential new words. Standard acoustic model structures such as CNN-TDNN-F and CNN-TDNN-F-A are adopted. In addition, multiple data augmentation techniques are applied. For the Constrained-plus training condition, we use the self-supervised learning framework wav2vec2.0. We experiment with various fine-tuning techniques with the Connectionist Temporal Classification (CTC) criterion on top of the publicly available pre-trained model XLSR-53. We find that the frontend feature extractor plays an important role when applying the wav2vec2.0 pre-trained model to the encoder-decoder based CTC/Attention ASR architecture. Extra improvements can be achieved by using the CTC model finetuned in the target language as the frontend feature extractor.

cs.CL↗