arXiv subjects

Li Zhu

Publications and source records attributed to Li Zhu.

At least 91 records · Page 5Linked to original sources

arXiv2023

Landslide Susceptibility Prediction Modeling Based on Self-Screening Deep Learning Model

Landslide susceptibility prediction has always been an important and challenging content. However, there are some uncertain problems to be solved in susceptibility modeling, such as the error of landslide samples and the complex nonlinear relationship between environmental factors. A self-screening graph convolutional network and long short-term memory network (SGCN-LSTM) is proposed int this paper to overcome the above problems in landslide susceptibility prediction. The SGCN-LSTM model has the advantages of wide width and good learning ability. The landslide samples with large errors outside the set threshold interval are eliminated by self-screening network, and the nonlinear relationship between environmental factors can be extracted from both spatial nodes and time series, so as to better simulate the nonlinear relationship between environmental factors. The SGCN-LSTM model was applied to landslide susceptibility prediction in Anyuan County, Jiangxi Province, China, and compared with Cascade-parallel Long Short-Term Memory and Conditional Random Fields (CPLSTM-CRF), Random Forest (RF), Support Vector Machine (SVM), Stochastic Gradient Descent (SGD) and Logistic Regression (LR) models.The landslide prediction experiment in Anyuan County showed that the total accuracy and AUC of SGCN-LSTM model were the highest among the six models, and the total accuracy reached 92.38 %, which was 5.88%, 12.44%, 19.65%, 19.92% and 20.34% higher than those of CPLSTM-CRF, RF, SVM, SGD and LR models, respectively. The AUC value reached 0.9782, which was 0.0305,0.0532,0.1875,0.1909 and 0.1829 higher than the other five models, respectively. In conclusion, compared with some existing traditional machine learning, the SGCN-LSTM model proposed in this paper has higher landslide prediction accuracy and better robustness, and has a good application prospect in the LSP field.

cs.LG↗

arXiv2023

Progressive Text-to-Image Generation

Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space. Although the simple generative process surprisingly works well, is this the best way to generate the image? For instance, human creation is more inclined to the outline-to-fine of an image, while VQ-AR models themselves do not consider any relative importance of image patches. In this paper, we present a progressive model for high-fidelity text-to-image generation. The proposed method takes effect by creating new image tokens from coarse to fine based on the existing context in a parallel manner, and this procedure is recursively applied with the proposed error revision mechanism until an image sequence is completed. The resulting coarse-to-fine hierarchy makes the image generation process intuitive and interpretable. Extensive experiments in MS COCO benchmark demonstrate that the progressive model produces significantly better results compared with the previous VQ-AR method in FID score across a wide variety of categories and aspects. Moreover, the design of parallel generation in each step allows more than $\times 13$ inference acceleration with slight performance loss.

cs.CV↗

arXiv2023

Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark

In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 times larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.96%, +7.68%, and +16.95% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively.

cs.CV↗

arXiv2023

How complex is the microarray dataset? A novel data complexity metric for biological high-dimensional microarray data

Data complexity analysis quantifies the hardness of constructing a predictive model on a given dataset. However, the effectiveness of existing data complexity measures can be challenged by the existence of irrelevant features and feature interactions in biological micro-array data. We propose a novel data complexity measure, depth, that leverages an evolutionary inspired feature selection algorithm to quantify the complexity of micro-array data. By examining feature subsets of varying sizes, the approach offers a novel perspective on data complexity analysis. Unlike traditional metrics, depth is robust to irrelevant features and effectively captures complexity stemming from feature interactions. On synthetic micro-array data, depth outperforms existing methods in robustness to irrelevant features and identifying complexity from feature interactions. Applied to case-control genotype and gene-expression micro-array datasets, the results reveal that a single feature of gene-expression data can account for over 90% of the performance of multi-feature model, confirming the adequacy of the commonly used differentially expressed gene (DEG) feature selection method for the gene expression data. Our study also demonstrates that constructing predictive models for genotype data is harder than gene expression data. The results in this paper provide evidence for the use of interpretable machine learning algorithms on microarray data.

cs.CE↗

arXiv2023

Discounted Thompson Sampling for Non-Stationary Bandit Problems

Non-stationary multi-armed bandit (NS-MAB) problems have recently received significant attention. NS-MAB are typically modelled in two scenarios: abruptly changing, where reward distributions remain constant for a certain period and change at unknown time steps, and smoothly changing, where reward distributions evolve smoothly based on unknown dynamics. In this paper, we propose Discounted Thompson Sampling (DS-TS) with Gaussian priors to address both non-stationary settings. Our algorithm passively adapts to changes by incorporating a discounted factor into Thompson Sampling. DS-TS method has been experimentally validated, but analysis of the regret upper bound is currently lacking. Under mild assumptions, we show that DS-TS with Gaussian priors can achieve nearly optimal regret bound on the order of $\tilde{O}(\sqrt{TB_T})$ for abruptly changing and $\tilde{O}(T^β)$ for smoothly changing, where $T$ is the number of time steps, $B_T$ is the number of breakpoints, $β$ is associated with the smoothly changing environment and $\tilde{O}$ hides the parameters independent of $T$ as well as logarithmic terms. Furthermore, empirical comparisons between DS-TS and other non-stationary bandit algorithms demonstrate its competitive performance. Specifically, when prior knowledge of the maximum expected reward is available, DS-TS has the potential to outperform state-of-the-art algorithms.

cs.LG↗

arXiv2023

ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization

In the realm of machine learning, the study of anomaly detection and localization within image data has gained substantial traction, particularly for practical applications such as industrial defect detection. While the majority of existing methods predominantly use Convolutional Neural Networks (CNN) as their primary network architecture, we introduce a novel approach based on the Transformer backbone network. Our method employs a two-stage incremental learning strategy. During the first stage, we train a Masked Autoencoder (MAE) model solely on normal images. In the subsequent stage, we apply pixel-level data augmentation techniques to generate corrupted normal images and their corresponding pixel labels. This process allows the model to learn how to repair corrupted regions and classify the status of each pixel. Ultimately, the model generates a pixel reconstruction error matrix and a pixel anomaly probability matrix. These matrices are then combined to produce an anomaly scoring matrix that effectively detects abnormal regions. When benchmarked against several state-of-the-art CNN-based methods, our approach exhibits superior performance on the MVTec AD dataset, achieving an impressive 97.6% AUC.

cs.CV↗

arXiv2023

FSDNet-An efficient fire detection network for complex scenarios based on YOLOv3 and DenseNet

Fire is one of the common disasters in daily life. To achieve fast and accurate detection of fires, this paper proposes a detection network called FSDNet (Fire Smoke Detection Network), which consists of a feature extraction module, a fire classification module, and a fire detection module. Firstly, a dense connection structure is introduced in the basic feature extraction module to enhance the feature extraction ability of the backbone network and alleviate the gradient disappearance problem. Secondly, a spatial pyramid pooling structure is introduced in the fire detection module, and the Mosaic data augmentation method and CIoU loss function are used in the training process to comprehensively improve the flame feature extraction ability. Finally, in view of the shortcomings of public fire datasets, a fire dataset called MS-FS (Multi-scene Fire And Smoke) containing 11938 fire images was created through data collection, screening, and object annotation. To prove the effectiveness of the proposed method, the accuracy of the method was evaluated on two benchmark fire datasets and MS-FS. The experimental results show that the accuracy of FSDNet on the two benchmark datasets is 99.82% and 91.15%, respectively, and the average precision on MS-FS is 86.80%, which is better than the mainstream fire detection methods.

cs.CV↗

arXiv2022

On classification of singular matrix difference equations of mixed order

This paper is concerned with singular matrix difference equations of mixed order. The existence and uniqueness of initial value problems for these equations are derived, and then the classification of them is obtained with a similar classical Weyl's method by selecting a suitable quasi-difference. An equivalent characterization of this classification is given in terms of the number of linearly independent square summable solutions of the equation. The influence of off-diagonal coefficients on the classification is illustrated by two examples. In particular, two limit point criteria are established in terms of coefficients of the equation.

math.SP↗

arXiv2022

Conventional high-temperature superconductivity in metallic, covalently bonded, binary-guest C-B clathrates

Inspired by the synthesis of XB3C3 (X= Sr, La) compounds in the bipartite sodalite clathrate structure, density functional theory (DFT) calculations are performed on members of this family containing up to two different metal atoms. A DFT-chemical pressure analysis on systems with X= Mg, Ca, Sr, Ba reveals that the size of the metal cation, which can be tuned to stabilize the B-C framework, is key for their ambient-pressure dynamic stability. High-throughput density functional theory calculations on 105 Pm-3 symmetry XYB6C6 binary-guest compounds (where X, Y are electropositive metal atoms) find 22 that are dynamically stable at 1 atmosphere, expanding the number of potentially synthesizable phases by 19 (18 metals and 1 insulator). The density of states at the Fermi level and superconducting critical temperature, Tc, can be tuned by changing the average oxidation state of the metal atoms, with Tc being highest for an average valence of +1.5. KPbB6C6, with an ambient-pressure Eliashberg Tc of 88 K, is predicted to possess the highest-Tc among the studied Pm-3n XB3C3 or Pm-3 XY B6C6 phases, and calculations suggest it may be synthesized using high-pressure high-temperature techniques then quenched to ambient conditions.

cond-mat.supr-con↗

arXiv2022

Uncertainty-Aware Image Captioning

It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a sentence sequentially and equally. In this paper, we propose an uncertainty-aware image captioning framework, which parallelly and iteratively operates insertion of discontinuous candidate words between existing words from easy to difficult until converged. We hypothesize that high-uncertainty words in a sentence need more prior information to make a correct decision and should be produced at a later stage. The resulting non-autoregressive hierarchy makes the caption generation explainable and intuitive. Specifically, we utilize an image-conditioned bag-of-word model to measure the word uncertainty and apply a dynamic programming algorithm to construct the training pairs. During inference, we devise an uncertainty-adaptive parallel beam search technique that yields an empirically logarithmic time complexity. Extensive experiments on the MS COCO benchmark reveal that our approach outperforms the strong baseline and related methods on both captioning quality as well as decoding speed.

cs.CV↗

arXiv2022

Two Iterative algorithms for the matrix sign function based on the adaptive filtering technology

In this paper, two new efficient algorithms for calculating the sign function of the large-scale sparse matrix are proposed by combining filtering algorithm with Newton method and Newton Schultz method respectively. Through the theoretical analysis of the error diffusion in the iterative process, we designed an adaptive filtering threshold, which can ensure that the filtering has little impact on the iterative process and the calculation result. Numerical experiments are consistent with our theoretical analysis, which shows that the computational efficiency of our method is much better than that of Newton method and Newton Schultz method, and the computational error is of the same order of magnitude as that of the two methods.

math.NA↗

arXiv2022

Progressive Glass Segmentation

Glass is very common in the real world. Influenced by the uncertainty about the glass region and the varying complex scenes behind the glass, the existence of glass poses severe challenges to many computer vision tasks, making glass segmentation as an important computer vision task. Glass does not have its own visual appearances but only transmit/reflect the appearances of its surroundings, making it fundamentally different from other common objects. To address such a challenging task, existing methods typically explore and combine useful cues from different levels of features in the deep network. As there exists a characteristic gap between level-different features, i.e., deep layer features embed more high-level semantics and are better at locating the target objects while shallow layer features have larger spatial sizes and keep richer and more detailed low-level information, fusing these features naively thus would lead to a sub-optimal solution. In this paper, we approach the effective features fusion towards accurate glass segmentation in two steps. First, we attempt to bridge the characteristic gap between different levels of features by developing a Discriminability Enhancement (DE) module which enables level-specific features to be a more discriminative representation, alleviating the features incompatibility for fusion. Second, we design a Focus-and-Exploration Based Fusion (FEBF) module to richly excavate useful information in the fusion process by highlighting the common and exploring the difference between level-different features.

cs.CV↗

arXiv2022

A filtering technique for the matrix power series being near-sparse

This work presents a new algorithm for matrix power series which is near-sparse, that is, there are a large number of near-zero elements in it. The proposed algorithm uses a filtering technique to improve the sparsity of the matrices involved in the calculation process of the Paterson-Stockmeyer (PS) scheme. Based on the error analysis considering the transaction error and the error introduced by filtering, the proposed algorithm can obtain similar accuracy as the original PS scheme but is more efficient than it. For the near-sparse matrix power series, the proposed method is also more efficient than the MATLAB built-in codes.

math.NA↗

arXiv2022

ReGO: Reference-Guided Outpainting for Scenery Image

We aim to tackle the challenging yet practical scenery image outpainting task in this work. Recently, generative adversarial learning has significantly advanced the image outpainting by producing semantic consistent content for the given image. However, the existing methods always suffer from the blurry texture and the artifacts of the generative part, making the overall outpainting results lack authenticity. To overcome the weakness, this work investigates a principle way to synthesize texture-rich results by borrowing pixels from its neighbors (i.e., reference images), named \textbf{Re}ference-\textbf{G}uided \textbf{O}utpainting (ReGO). Particularly, the ReGO designs an Adaptive Content Selection (ACS) module to transfer the pixel of reference images for texture compensating of the target one. To prevent the style of the generated part from being affected by the reference images, a style ranking loss is further proposed to augment the ReGO to synthesize style-consistent results. Extensive experiments on two popular benchmarks, NS6K \cite{yangzx} and NS8K \cite{wang}, well demonstrate the effectiveness of our ReGO. Our code will be made public available.

cs.CV↗

arXiv2022

A new stable and avoiding inversion iteration for computing matrix square root

The objective of this research was to compute the principal matrix square root with sparse approximation. A new stable iterative scheme avoiding fully matrix inversion (SIAI) is provided. The analysis on the sparsity and error of the matrices involved during the iterative process is given. Based on the bandwidth and error analysis, a more efficient algorithm combining the SIAI with the filtering technique is proposed. The high computational efficiency and accuracy of the proposed method are demonstrated by computing the principal square roots of different matrices to reveal its applicability over the existing methods.

math.NA↗

arXiv2021

Superconductivity in SrB3C3 clathrate

We predict superconductivity for the carbon-boron clathrate SrB3C3 at 27-43 K for Coulomb pseudopotential (mu*) values between 0.17 and 0.10 using first-principles calculations with conventional electron-phonon coupling. Electrical transport measurements, facilitated by a novel in situ experimental design compatible with extreme synthesis conditions (>3000 K at 50 GPa), show non-hysteretic resistivity drops that track the calculated magnitude and pressure dependence of superconductivity for mu*=0.15, and transport measurements collected under applied magnetic fields confirm superconductivity with an onset Tc of approximately 20 K at 40 GPa. Carbon-based clathrates thus represent a new class of superconductors similar to other covalent metals like MgB2 and doped fullerenes. Carbon clathrates share structures similar to superconducting superhydrides, but covalent C-B bonds allow metastable persistence at ambient conditions.

cond-mat.mtrl-sci↗

arXiv2021

High-performance computation of the exponential of a large sparse matrix

Computation of the large sparse matrix exponential has been an important topic in many fields, such as network and finite-element analysis. The existing scaling and squaring algorithm (SSA) is not suitable for the computation of the large sparse matrix exponential as it requires greater memories and computational cost than is actually needed. By introducing two novel concepts, i.e., real bandwidth and bandwidth, to measure the sparsity of the matrix, the sparsity of the matrix exponential is analyzed. It is found that for every matrix computed in the squaring phase of the SSA, a corresponding sparse approximate matrix exists. To obtain the sparse approximate matrix, a new filtering technique in terms of forward error analysis is proposed. Combining the filtering technique with the idea of keeping track of the incremental part, a competitive algorithm is developed for the large sparse matrix exponential. The proposed method can primarily alleviate the over-scaling problem due to the filtering technique. Three sets of numerical experiments, including one large matrix with a dimension larger than 2e6 , are conducted. The numerical experiments show that, compared with the expm function in MATLAB, the proposed algorithm can provide higher accuracy at lower computational cost and with less memory.

math.NA↗

arXiv2021

Tuning the intermediate reaction barriers by CuPd catalyst to improve the selectivity of electroreduction CO2 to C2 products

Electrochemical CO2 reduction is a promising strategy for utilization of CO2 and intermittent excess electricity. Cu is the only single-metal catalyst that can electrochemically convert CO2 to multi-carbon products. However, Cu has an undesirable selectivity and activity for C2 products, due to its insufficient amount of CO* for C-C coupling. Considering the strong CO2 adsorption and ultra-fast reaction kinetics of CO* formation on Pd, an intimate CuPd(100) interface was designed to lower the intermediate reaction barriers and then improve the efficiency of C2 products. Density functional theory (DFT) calculations showed that the CuPd(100) interface has enhanced CO2 adsorption and decreased CO2* hydrogenation energy barrier, which are beneficial for C-C coupling. The potential-determining step (PDS) barrier of CO2 to C2 products on CuPd(100) interface is 0.61 eV, which is lower than that on Cu(100) (0.72 eV). Motivated by the DFT calculation, the CuPd(100) interface catalyst was prepared by a facile chemical solution method and demonstrated by transmission electron microscope (TEM). The CO2 temperature programmed desorption (CO2-TPD) and gas sensor experiments proved the enhancements of CO2 adsorption and CO2* hydrogenation abilities on CuPd(100) interface catalyst. As a result, the obtained CuPd(100) interface catalyst exhibits a C2 Faradaic efficiency of 50.3 (+/-) 1.2% at -1.4 VRHE in 0.1 M KHCO3, which is 2.1 times higher than 23.6(+/-) 1.5% of Cu catalyst. This work provides a rational design of Cu-based electrocatalyst for multi-carbon products by fine-tuning the intermediate reaction barriers.

cond-mat.mtrl-sci↗