arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 577 records · Page 32Linked to original sources

arXiv2020

Field-wise Learning for Multi-field Categorical Data

We propose a new method for learning with multi-field categorical data. Multi-field categorical data are usually collected over many heterogeneous groups. These groups can reflect in the categories under a field. The existing methods try to learn a universal model that fits all data, which is challenging and inevitably results in learning a complex model. In contrast, we propose a field-wise learning method leveraging the natural structure of data to learn simple yet efficient one-to-one field-focused models with appropriate constraints. In doing this, the models can be fitted to each category and thus can better capture the underlying differences in data. We present a model that utilizes linear models with variance and low-rank constraints, to help it generalize better and reduce the number of parameters. The model is also interpretable in a field-wise manner. As the dimensionality of multi-field categorical data can be very high, the models applied to such data are mostly over-parameterized. Our theoretical analysis can potentially explain the effect of over-parametrization on the generalization of our model. It also supports the variance constraints in the learning objective. The experiment results on two large-scale datasets show the superior performance of our model, the trend of the generalization error bound, and the interpretability of learning outcomes. Our code is available at https://github.com/lzb5600/Field-wise-Learning.

cs.LG↗

arXiv2020

Beamforming Design for Multiuser uRLLC with Finite Blocklength Transmission

Driven by the explosive growth of Internet of Things (IoT) devices with stringent requirements on latency and reliability, ultra-reliability and low latency communication (uRLLC) has become one of the three key communication scenarios for the fifth generation (5G) and beyond 5G communication systems. In this paper, we focus on the beamforming design problem for the downlink multiuser uRLLC systems. Since the strict demand on the reliability and latency, in general, short packet transmission is a favorable form for uRLLC systems, which indicates the literature Shannon's capacity formula is no longer applicable. With the finite blocklength transmission, the achievable delivery rate is greatly influenced by the reliability and latency. Using the developed achievable delivery rate formula for finite blocklength transmission, we respectively formulate the problems of interest as the weighted sum rate maximization, energy efficiency maximization, and user fairness optimization by considering the maximum allowable transmission power and minimum rate requirement. It's worthy pointing out that this is the first work to design the beamforming vectors for the downlink multiuser uRLLC systems. To address these non-convex problems, some important insights have been discovered by analyzing the function of achievable delivery rate. For example, the minimum rate requirement can be realized by low bounded the signal-to-interference-plus-noise ratio. Based on the discovered results, we provide algorithms to optimize the beamforming vectors and power allocation, which are guaranteed to converge to a local optimum solution of the formulated problems with low computational complexity. Our simulation results reveal that our proposed beamforming algorithms outperform the zero-forcing beamforming algorithm with equal power allocation widely used in the existing literatures.

cs.IT↗

arXiv2020

Distance-based Data Cleaning: A Survey (Technical Report)

With the rapid development of the internet technology, dirty data are commonly observed in various real scenarios, e.g., owing to unreliable sensor reading, transmission and collection from heterogeneous sources. To deal with their negative effects on downstream applications, data cleaning approaches are designed to preprocess the dirty data before conducting applications. The idea of most data cleaning methods is to identify or correct dirty data, referring to the values of their neighbors which share the same information. Unfortunately, owing to data sparsity and heterogeneity, the number of neighbors based on equality relationship is rather limited, especially in the presence of data values with variances. To tackle this problem, distance-based data cleaning approaches propose to consider similarity neighbors based on value distance. By tolerance of small variants, the enriched similarity neighbors can be identified and used for data cleaning tasks. At the same time, distance relationship between tuples is also helpful to guide the data cleaning, which contains more information and includes the equality relationship. Therefore, distance-based technology plays an important role in the data cleaning area, and we also have reason to believe that distance-based data cleaning technology will attract more attention in data preprocessing research in the future. Hence this survey provides a classification of four main data cleaning tasks, i.e., rule profiling, error detection, data repair and data imputation, and comprehensively reviews the state of the art for each class.

cs.DB↗

arXiv2020

Multi-layer Feature Aggregation for Deep Scene Parsing Models

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of adjacent image patches. So the challenge for this learning task is to simultaneously describe the geometric and semantic properties of objects or a scene. In this paper, we explore the effective use of multi-layer feature outputs of the deep parsing networks for spatial-semantic consistency by designing a novel feature aggregation module to generate the appropriate global representation prior, to improve the discriminative power of features. The proposed module can auto-select the intermediate visual features to correlate the spatial and semantic information. At the same time, the multiple skip connections form a strong supervision, making the deep parsing network easy to train. Extensive experiments on four public scene parsing datasets prove that the deep parsing network equipped with the proposed feature aggregation module can achieve very promising results.

cs.CV↗

arXiv2020

Distribution-aware Margin Calibration for Medical Image Segmentation

The Jaccard index, also known as Intersection-over-Union (IoU score), is one of the most critical evaluation metrics in medical image segmentation. However, directly optimizing the mean IoU (mIoU) score over multiple objective classes is an open problem. Although some algorithms have been proposed to optimize its surrogates, there is no guarantee provided for their generalization ability. In this paper, we present a novel data-distribution-aware margin calibration method for a better generalization of the mIoU over the whole data-distribution, underpinned by a rigid lower bound. This scheme ensures a better segmentation performance in terms of IoU scores in practice. We evaluate the effectiveness of the proposed margin calibration method on two medical image segmentation datasets, showing substantial improvements of IoU scores over other learning schemes using deep segmentation models.

cs.CV↗

arXiv2020

Parameter Efficient Deep Neural Networks with Bilinear Projections

Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy. Given a proper deep learning framework, it is generally possible to increase the depth or layer width to achieve a higher level of accuracy. However, the huge number of model parameters imposes more computational and memory usage overhead and leads to the parameter redundancy. In this paper, we address the parameter redundancy problem in DNNs by replacing conventional full projections with bilinear projections. For a fully-connected layer with $D$ input nodes and $D$ output nodes, applying bilinear projection can reduce the model space complexity from $\mathcal{O}(D^2)$ to $\mathcal{O}(2D)$, achieving a deep model with a sub-linear layer size. However, structured projection has a lower freedom of degree compared to the full projection, causing the under-fitting problem. So we simply scale up the mapping size by increasing the number of output channels, which can keep and even boosts the model accuracy. This makes it very parameter-efficient and handy to deploy such deep models on mobile systems with memory limitations. Experiments on four benchmark datasets show that applying the proposed bilinear projection to deep neural networks can achieve even higher accuracies than conventional full DNNs, while significantly reduces the model size.

cs.CV↗

arXiv2020

Identification of deep breath while moving forward based on multiple body regions and graph signal analysis

This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera. Existing non-contact breath assessments achieve satisfactory results under restricted conditions when human body stays relatively still. When someone moves forward, the breath signals detected by depth camera are hidden within signals of trunk displacement and deformation, and the signal length is short due to the short stay time, posing great challenges for us to establish models. To overcome these challenges, multiple region of interests (ROIs) based signal extraction and selection method is proposed to automatically obtain the signal informative to breath from depth video. Subsequently, graph signal analysis (GSA) is adopted as a spatial-temporal filter to wipe the components unrelated to breath. Finally, a classifier for identifying deep breath is established based on the selected breath-informative signal. In validation experiments, the proposed approach outperforms the comparative methods with the accuracy, precision, recall and F1 of 75.5%, 76.2%, 75.0% and 75.2%, respectively. This system can be extended to public places to provide timely and ubiquitous help for those who may have or are going through physical or mental trouble.

cs.CV↗

arXiv2020

Stage Lookup: Accelerating Path Lookup using Directory Shortcuts

The lookup procedure in Linux costs a significant portion of file accessing time as the virtual file system (VFS) traverses the file path components one after another. The lookup procedure becomes more time consuming when applications frequently access files, especially those with small sizes. We propose Stage Lookup, which dynamically caches popular directories to speed up lookup procedures and further reduce file accessing latency. The core of Stage Lookup is to cache popular dentries as shortcuts, so that path walks do not bother to traverse directory trees from the root. Furthermore, Stage Lookup enriches backward path walks as it treats the directory tree in a VFS as an undirected map. We implement a Stage Lookup prototype and integrate it into Linux Kernel v3.14. Our extensive performance evaluation studies show that Stage Lookup offers up to 46.9% performance gain compared to ordinary path lookup schemes. Furthermore, Stage Lookup shows smaller performance overheads in rename and chmod operations compared to the original method of the kernel.

cs.OS↗

arXiv2020

Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone

Coronavirus Disease 2019 (COVID-19) has spread all over the world since it broke out massively in December 2019, which has caused a large loss to the whole world. Both the confirmed cases and death cases have reached a relatively frightening number. Syndrome coronaviruses 2 (SARS-CoV-2), the cause of COVID-19, can be transmitted by small respiratory droplets. To curb its spread at the source, wearing masks is a convenient and effective measure. In most cases, people use face masks in a high-frequent but short-time way. Aimed at solving the problem that we don't know which service stage of the mask belongs to, we propose a detection system based on the mobile phone. We first extract four features from the GLCMs of the face mask's micro-photos. Next, a three-result detection system is accomplished by using KNN algorithm. The results of validation experiments show that our system can reach a precision of 82.87% (standard deviation=8.5%) on the testing dataset. In future work, we plan to expand the detection objects to more mask types. This work demonstrates that the proposed mobile microscope system can be used as an assistant for face mask being used, which may play a positive role in fighting against COVID-19.

cs.CV↗

arXiv2020

ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution

Deep convolutional neural networks have significantly improved the peak signal-to-noise ratio of SuperResolution (SR). However, image viewer applications commonly allow users to zoom the images to arbitrary magnification scales, thus far imposing a large number of required training scales at a tremendous computational cost. To obtain a more computationally efficient model for arbitrary scale SR, this paper employs a Laplacian pyramid method to reconstruct any-scale high-resolution (HR) images using the high-frequency image details in a Laplacian Frequency Representation. For SR of small-scales (between 1 and 2), images are constructed by interpolation from a sparse set of precalculated Laplacian pyramid levels. SR of larger scales is computed by recursion from small scales, which significantly reduces the computational cost. For a full comparison, fixed- and any-scale experiments are conducted using various benchmarks. At fixed scales, ASDN outperforms predefined upsampling methods (e.g., SRCNN, VDSR, DRRN) by about 1 dB in PSNR. At any-scale, ASDN generally exceeds Meta-SR on many scales.

eess.IV↗

arXiv2020

Imprint of a new light particle at KOTO?

Recently, the KOTO experiment reported their new preliminary result of searching for the decay $K_L\toπ^0ν\barν$. Three candidate events were observed in the signal region, which exceed significantly the expectation based on the standard model. On the other hand, the new NA62 and previous BNL-E949 experiments yielded a consistent result and confirmed the standard model prediction in the charged meson decay $K^+\toπ^+ν\barν$. Furthermore, the two decays are bound by a well-motivated relation from an analysis of isospin symmetry that is hard to break by the new physics of heavy particles. In this work, we study the issue by a systematic effective field theory approach with three of the simplest scenarios, in which the $K_L$ may decay into a new light neutral particle $X$, i.e., $K_L\toπ^0X$, $K_L\to γγX$, or $K_L\toπ^0XX$. We assess the feasibility of the scenarios by simulations and by incorporating constraints coming from NA62 and other relevant experiments. Our main conclusion is that the scenario $K\toπXX$ for a long lived scalar $X$ seems more credible than the other two when combining distributions and other experimental constraints while the region below the KOTO's blind box provides a good detection environment to search for all three scenarios for a relatively heavy $X$.

hep-ph↗

arXiv2020

Scalar Coupling Constant Prediction Using Graph Embedding Local Attention Encoder

Scalar coupling constant (SCC) plays a key role in the analysis of three-dimensional structure of organic matter, however, the traditional SCC prediction using quantum mechanical calculations is very time-consuming. To calculate SCC efficiently and accurately, we proposed a graph embedding local self-attention encoder (GELAE) model, in which, a novel invariant structure representation of the coupling system in terms of bond length, bond angle and dihedral angle was presented firstly, and then a local self-attention module embedded with the adjacent matrix of a graph was designed to extract effectively the features of coupling systems, finally, with a modified classification loss function, the SCC was predicted. To validate the superiority of the proposed method, we conducted a series of comparison experiments using different structure representations, different attention modules, and different losses. The experimental results demonstrate that, compared to the traditional chemical bond structure representations, the rotation and translation invariant structure representations proposed in this work can improve the SCC prediction accuracy; with the graph embedded local self-attention, the mean absolute error (MAE) of the prediction model in the validation set decreases from 0.1603 Hz to 0.1067 Hz; using the classification based loss function instead of the scaled regression loss, the MAE of the predicted SCC can be decreased to 0.0963 HZ, which is close to the quantum chemistry standard on CHAMPS dataset.

cs.LG↗

arXiv2020

Computational prediction of RNA tertiary structures using machine learning methods

RNAs play crucial and versatile roles in biological processes. Computational prediction approaches can help to understand RNA structures and their stabilizing factors, thus providing information on their functions, and facilitating the design of new RNAs. Machine learning (ML) techniques have made tremendous progress in many fields in the past few years. Although their usage in protein-related fields has a long history, the use of ML methods in predicting RNA tertiary structures is new and rare. Here, we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation, the difficulties and potentials of these approaches when applied in the field.

physics.bio-ph↗

arXiv2020

Face Anti-Spoofing Via Disentangled Representation Learning

Face anti-spoofing is crucial to security of face recognition systems. Previous approaches focus on developing discriminative models based on the features extracted from images, which may be still entangled between spoof patterns and real persons. In this paper, motivated by the disentangled representation learning, we propose a novel perspective of face anti-spoofing that disentangles the liveness features and content features from images, and the liveness features is further used for classification. We also put forward a Convolutional Neural Network (CNN) architecture with the process of disentanglement and combination of low-level and high-level supervision to improve the generalization capabilities. We evaluate our method on public benchmark datasets and extensive experimental results demonstrate the effectiveness of our method against the state-of-the-art competitors. Finally, we further visualize some results to help understand the effect and advantage of disentanglement.

cs.CV↗

arXiv2020

Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features

TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical co-localization or weakly-supervised localization tasks. To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained convolutional neural networks (CNNs). Specifically, we first convert the feature maps from a pre-trained CNN model into a set of transactions, and then discovers frequent patterns from transaction database through pattern mining techniques. We observe that those discovered patterns, i.e., co-occurrence highlighted regions, typically hold appearance and spatial consistency. Motivated by this observation, we can easily discover and localize possible objects by merging relevant meaningful patterns. Extensive experiments on a variety of benchmarks demonstrate that OLM achieves competitive localization performance compared with the state-of-the-art methods. We also evaluate our approach compared with unsupervised saliency detection methods and achieves competitive results on seven benchmark datasets. Moreover, we conduct experiments on fine-grained classification to show that our proposed method can locate the entire object and parts accurately, which can benefit to improving the classification results significantly.

cs.CV↗

arXiv2020

Salvage Reusable Samples from Noisy Data for Robust Learning

Due to the existence of label noise in web images and the high memorization capacity of deep neural networks, training deep fine-grained (FG) models directly through web images tends to have an inferior recognition ability. In the literature, to alleviate this issue, loss correction methods try to estimate the noise transition matrix, but the inevitable false correction would cause severe accumulated errors. Sample selection methods identify clean ("easy") samples based on the fact that small losses can alleviate the accumulated errors. However, "hard" and mislabeled examples that can both boost the robustness of FG models are also dropped. To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images. Our key idea is to additionally identify and correct reusable samples, and then leverage them together with clean examples to update the networks. We demonstrate the superiority of the proposed approach from both theoretical and experimental perspectives.

cs.CV↗

arXiv2020

Max-min Fairness of K-user Cooperative Rate-Splitting in MISO Broadcast Channel with User Relaying

Cooperative Rate-Splitting (CRS) strategy, relying on linearly precoded rate-splitting at the transmitter and opportunistic transmission of the common message by the relaying user, has recently been shown to outperform typical Non-cooperative Rate-Splitting (NRS), Cooperative Non-Orthogonal Multiple Access (C-NOMA) and Space Division Multiple Access (SDMA) in a two-user Multiple Input Single Output (MISO) Broadcast Channel (BC) with user relaying. In this work, the existing two-user CRS transmission strategy is generalized to the K-user case. We study the problem of jointly optimizing the precoders, message split, time slot allocation, and relaying user scheduling with the objective of maximizing the minimum rate among users. An efficient self-organizing relaying protocol is first proposed followed by a Successive Convex Approximation (SCA)-based algorithm to jointly optimize time slot, precoders and message split. Numerical results show that the worst-case achievable rate achieved by CRS is significantly increased over that of NRS and SDMA in a wide range of network loads and user deployments. Importantly, the proposed SCA-based algorithm dramatically reduces the computational complexity without any rate loss compared with the conventional algorithm in the literature of CRS. Therefore, we conclude that the proposed K-user CRS is more powerful than the existing transmission schemes.

eess.SP↗

arXiv2020

Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks

Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs. A class of adversarial attack network algorithms has been proposed to generate robust physical perturbations under different circumstances. These algorithms are the first efforts to move forward secure deep learning by providing an avenue to train future defense networks, however, the intrinsic complexity of them prevents their broader usage. In this paper, we propose the first hardware accelerator for adversarial attacks based on memristor crossbar arrays. Our design significantly improves the throughput of a visual adversarial perturbation system, which can further improve the robustness and security of future deep learning systems. Based on the algorithm uniqueness, we propose four implementations for the adversarial attack accelerator ($A^3$) to improve the throughput, energy efficiency, and computational efficiency.

eess.SP↗