arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 559 records · Page 31Linked to original sources

arXiv2021

Thousand to One: Semantic Prior Modeling for Conceptual Coding

Conceptual coding has been an emerging research topic recently, which encodes natural images into disentangled conceptual representations for compression. However, the compression performance of the existing methods is still sub-optimal due to the lack of comprehensive consideration of rate constraint and reconstruction quality. To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis. Specifically, we employ semantic segmentation maps as structural guidance for extracting deep semantic prior, which provides fine-grained texture distribution modeling for better detail construction and higher flexibility in subsequent high-level vision tasks. Moreover, a cross-channel entropy model is proposed to further exploit the inter-channel correlation of the spatially independent semantic prior, leading to more accurate entropy estimation for rate-constrained training. The proposed scheme achieves an ultra-high 1000x compression ratio, while still enjoying high visual reconstruction quality and versatility towards visual processing and analysis tasks.

cs.CV↗

arXiv2021

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS). High-order features are usually developed to uncover subtle differences between sub-categories in FGFS, but they are less effective in handling the high intra-class variance. In this paper, we propose a Target-Oriented Alignment Network (TOAN) to investigate the fine-grained relation between the target query image and support classes. The feature of each support image is transformed to match the query ones in the embedding feature space, which reduces the disparity explicitly within each category. Moreover, different from existing FGFS approaches devise the high-order features over the global image with less explicit consideration of discriminative parts, we generate discriminative fine-grained features by integrating compositional concept representations to global second-order pooling. Extensive experiments are conducted on four fine-grained benchmarks to demonstrate the effectiveness of TOAN compared with the state-of-the-art models.

cs.CV↗

arXiv2021

COLA-Net: Collaborative Attention Network for Image Restoration

Local and non-local attention-based methods have been well studied in various image restoration tasks while leading to promising performance. However, most of the existing methods solely focus on one type of attention mechanism (local or non-local). Furthermore, by exploiting the self-similarity of natural images, existing pixel-wise non-local attention operations tend to give rise to deviations in the process of characterizing long-range dependence due to image degeneration. To overcome these problems, in this paper we propose a novel collaborative attention network (COLA-Net) for image restoration, as the first attempt to combine local and non-local attention mechanisms to restore image content in the areas with complex textures and with highly repetitive details respectively. In addition, an effective and robust patch-wise non-local attention model is developed to capture long-range feature correspondences through 3D patches. Extensive experiments on synthetic image denoising, real image denoising and compression artifact reduction tasks demonstrate that our proposed COLA-Net is able to achieve state-of-the-art performance in both peak signal-to-noise ratio and visual perception, while maintaining an attractive computational complexity. The source code is available on https://github.com/MC-E/COLA-Net.

cs.CV↗

arXiv2021

Revisiting BFloat16 Training

State-of-the-art generic low-precision training algorithms use a mix of 16-bit and 32-bit precision, creating the folklore that 16-bit hardware compute units alone are not enough to maximize model accuracy. As a result, deep learning accelerators are forced to support both 16-bit and 32-bit floating-point units (FPUs), which is more costly than only using 16-bit FPUs for hardware design. We ask: can we train deep learning models only with 16-bit floating-point units, while still matching the model accuracy attained by 32-bit training? Towards this end, we study 16-bit-FPU training on the widely adopted BFloat16 unit. While these units conventionally use nearest rounding to cast output to 16-bit precision, we show that nearest rounding for model weight updates often cancels small updates, which degrades the convergence and model accuracy. Motivated by this, we study two simple techniques well-established in numerical analysis, stochastic rounding and Kahan summation, to remedy the model accuracy degradation in 16-bit-FPU training. We demonstrate that these two techniques can enable up to 7% absolute validation accuracy gain in 16-bit-FPU training. This leads to 0.1% lower to 0.2% higher validation accuracy compared to 32-bit training across seven deep learning applications.

cs.LG↗

arXiv2021

A comprehensive survey on point cloud registration

Registration is a transformation estimation problem between two point clouds, which has a unique and critical role in numerous computer vision applications. The developments of optimization-based methods and deep learning methods have improved registration robustness and efficiency. Recently, the combinations of optimization-based and deep learning methods have further improved performance. However, the connections between optimization-based and deep learning methods are still unclear. Moreover, with the recent development of 3D sensors and 3D reconstruction techniques, a new research direction emerges to align cross-source point clouds. This survey conducts a comprehensive survey, including both same-source and cross-source registration methods, and summarize the connections between optimization-based and deep learning methods, to provide further research insight. This survey also builds a new benchmark to evaluate the state-of-the-art registration algorithms in solving cross-source challenges. Besides, this survey summarizes the benchmark data sets and discusses point cloud registration applications across various domains. Finally, this survey proposes potential research directions in this rapidly growing field.

cs.CV↗

arXiv2021

Temperature dependent coherence properties of NV ensemble in diamond up to 600K

Nitrogen-vacancy (NV) center in diamond is an ideal candidate for quantum sensors because of its excellent optical and coherence property. However, previous studies are usually conducted at low or room temperature. The lack of full knowledge of coherence properties of the NV center at high temperature limits NV's further applications. Here, we systematically explore the coherence properties of the NV center ensemble at temperatures from 300 K to 600 K. Coherence time $T_2$ decreases rapidly from $184 μs$ at 300 K to $30 μs$ at 600 K, which is attributed to the interaction with paramagnetic impurities. Single-quantum and double-quantum relaxation rates show an obvious temperature-dependent behavior as well, and both of them are dominated by the two phonon Raman process. While the inhomogeneous dephasing time $T_2^*$ and thermal echo decoherence time $T_{TE}$ remain almost unchanged as temperature rises. Since $T_{TE}$ changed slightly as temperature rises, a thermal-echo-based thermometer is demonstrated to have a sensitivity of $41 mK/\sqrt{Hz}$ at 450 K. These findings will help to pave the way toward NV-based high-temperature sensing, as well as to have a more comprehensive understanding of the origin of decoherence in the solid-state qubit.

quant-ph↗

arXiv2021

Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these existing approaches simulate the test conditions too strictly during the training process, and thus cannot make full use of the given label information. Besides, these approaches mainly focus on the foreground-background target class segmentation setting. They only utilize binary mask labels for training. In this paper, we propose to leverage the multi-class label information during the episodic training. It will encourage the network to generate more semantically meaningful features for each category. After integrating the target class cues into the query features, we then propose a pyramid feature fusion module to mine the fused features for the final classifier. Furthermore, to take more advantage of the support image-mask pair, we propose a self-prototype guidance branch to support image segmentation. It can constrain the network for generating more compact features and a robust prototype for each semantic class. For inference, we propose a fused prototype guidance branch for the segmentation of the query image. Specifically, we leverage the prediction of the query image to extract the pseudo-prototype and combine it with the initial prototype. Then we utilize the fused prototype to guide the final segmentation of the query image. Extensive experiments demonstrate the superiority of our proposed approach.

cs.CV↗

arXiv2021

Feasibility study of TPC detector at high luminosity $Z$ pole on the circular collider

With the development of the circular collider, it is necessary to make accurate physics experimental measurements of particle properties at higher luminosity $Z$ pole. Micro-pattern gaseous detectors (MPGDs), which contain Gaseous Electron Multiplier (GEM) and Micro-mesh gaseous structures (Micromegas), have excellent potential for development as the readout devices of the time projection chamber (TPC) tracker detector. To meet the updated physics requirements of the high luminosity $Z$ from the preliminary concept design report (preCDR) to concept design report (CDR) at the circular electron positron collider (CEPC), In this paper, the space charge distortion of the TPC detector is simulated with the CEPC beam structure. Using the multi-physics simulation software package, the distribution of ion estimated by Geant4 is used as the input for the differential equation, and the relationship between the ion density distribution and electric field in the detector chamber is simulated. These simulation results show that the maximum deviation for Higgs $\mathcal{O}$(25 $μ$m) meets the performance requirements in CEPC TPC detector at the high luminosity $Z$ pole, while it is still a considerable challenge for $Z$ pole, with the maximum deviation $\mathcal{O}$($>100~μ$m). According to the previous developments, the cascaded structure of GEM and Micromegas detector has been measured. The new considerations of the detector's requirements were given, the gain needs to be reached to about 2000 with IBF$\times$Gain under 0.1, and IBF means the ions back flow ratio of the detector. The pixel TPC is a potential option to replace the traditional MPGDs with the low gain, low occupancy, and outstanding pattern recognition. Finally, some update parameters and experiments results were compared.

physics.ins-det↗

arXiv2021

Temporal-Amount Snapshot MultiGraph for Ethereum Transaction Tracking

With the wide application of blockchain in the financial field, the rise of various types of cybercrimes has brought great challenges to the security of blockchain. In order to better understand this emerging market and explore more efficient countermeasures for effective supervision, it is imperative to track transactions on blockchain-based systems. Due to the openness of Ethereum, we can easily access the publicly available transaction records, model them as a complex network, and further study the problem of transaction tracking via link prediction, which provides a deeper understanding of Ethereum transactions from a network perspective. Specifically, we introduce an embedding based link prediction framework that is composed of temporal-amount snapshot multigraph (TASMG) and present temporal-amount walk (TAW). By taking the realistic rules and features of transaction networks into consideration, we propose TASMG to model Ethereum transaction records as a temporal-amount network and then present TAW to effectively embed accounts via their transaction records, which integrates temporal and amount information of the proposed network. Experimental results demonstrate the superiority of the proposed framework in learning more informative representations and could be an effective method for transaction tracking.

cs.CR↗

arXiv2021

Time-Series Snapshot Network for Partner Recommendation: A Case Study on OSS

The last decade has witnessed the rapid growth of open source software (OSS). Still, all contributors may find it difficult to assimilate into OSS community even they are enthusiastic to make contributions. We thus suggest that partner recommendation across different roles may benefit both the users and developers, i.e., once we are able to make successful recommendation for those in need, it may dramatically contribute to the productivity of developers and the enthusiasm of users, thus further boosting OSS projects' development. Motivated by this potential, we model the partner recommendation as link prediction task from email data via network embedding methods. In this paper, we introduce time-series snapshot network (TSSN) which is a mixture network to model the interactions among users and developers. Based on the established TSSN, we perform temporal biased walk (TBW) to automatically capture both temporal and structural information of the email network, i.e., the behavioral similarity between individuals in the OSS email network. Experiments on ten Apache datasets demonstrate that the proposed TBW significantly outperforms a number of advanced random walk based embedding methods, leading to the state-of-the-art recommendation performance.

cs.SI↗

arXiv2021

Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System

Face authentication on mobile end has been widely applied in various scenarios. Despite the increasing reliability of cutting-edge face authentication/verification systems to variations like blinking eye and subtle facial expression, anti-spoofing against high-resolution rendering replay of paper photos or digital videos retains as an open problem. In this paper, we propose a simple yet effective face anti-spoofing system, termed Aurora Guard (AG). Our system firstly extracts the normal cues via light reflection analysis, and then adopts an end-to-end trainable multi-task Convolutional Neural Network (CNN) to accurately recover subjects' intrinsic depth and material map to assist liveness classification, along with the light CAPTCHA checking mechanism in the regression branch to further improve the system reliability. Experiments on public Replay-Attack and CASIA datasets demonstrate the merits of our proposed method over the state-of-the-arts. We also conduct extensive experiments on a large-scale dataset containing 12,000 live and diverse spoofing samples, which further validates the generalization ability of our method in the wild.

cs.CV↗

arXiv2021

An approximate dynamic programming approach to the admission control of elective patients

In this paper, we propose an approximate dynamic programming (ADP) algorithm to solve a Markov decision process (MDP) formulation for the admission control of elective patients. To manage the elective patients from multiple specialties equitably and efficiently, we establish a waiting list and assign each patient a time-dependent dynamic priority score. Then, taking the random arrivals of patients into account, sequential decisions are made on a weekly basis. At the end of each week, we select the patients to be treated in the following week from the waiting list. By minimizing the cost function of the MDP over an infinite horizon, we seek to achieve the best trade-off between the patients' waiting times and the over-utilization of surgical resources. Considering the curses of dimensionality resulting from the large scale of realistically sized problems, we first analyze the structural properties of the MDP and propose an algorithm that facilitates the search for best actions. We then develop a novel reinforcement-learning-based ADP algorithm as the solution technique. Experimental results reveal that the proposed algorithms consume much less computation time in comparison with that required by conventional dynamic programming methods. Additionally, the algorithms are shown to be capable of computing high-quality near-optimal policies for realistically sized problems.

math.OC↗

arXiv2021

Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, the presence of label noise and hard examples in web images are two obstacles for training robust fine-grained recognition models. Therefore, in this paper, we propose a novel approach for removing irrelevant samples from real-world web images during training, while employing useful hard examples to update the network. Thus, our approach can alleviate the harmful effects of irrelevant noisy web images and hard examples to achieve better performance. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is far superior to current state-of-the-art web-supervised methods.

cs.CV↗

arXiv2020

Counting the Number of Solutions to Constraints

Compared with constraint satisfaction problems, counting problems have received less attention. In this paper, we survey research works on the problems of counting the number of solutions to constraints. The constraints may take various forms, including, formulas in the propositional logic, linear inequalities over the reals or integers, Boolean combination of linear constraints. We describe some techniques and tools for solving the counting problems, as well as some applications (e.g., applications to automated reasoning, program analysis, formal verification and information security).

cs.AI↗

arXiv2020

Electrically Tunable Multifunctional All-Dielectric Metasurfaces Integrated with Liquid Crystals in the Visible

As two-dimensional metamaterials, metasurfaces open up new avenues for designing static planar optics. However, the dynamic modulation of metasurfaces in the optical band is required for practical applications. The existing dynamic devices rarely utilized the polarization manipulation capability of metasurfaces. Here, we demonstrate an electrically tunable multifunctional metasurface in the visible range by integrating birefringent liquid crystals (LCs) with all-dielectric metasurfaces based on a novel packaging scheme. By combining the helicity-dependent geometric phase of the metasurface and the polarization control ability of LC molecules, continuous intensity tuning and switching of two helicity channels are realized. Electrically tunable single-channel switchable metaholograms, multicolor multiplexed metaholograms, and dynamic varifocal metalenses are designed to verify the concept. The exploration of polarization control in dynamic tuning can pave the way for dynamic metasurface devices in various applications, such as space light modulators, light detection and ranging systems, and holographic displays.

physics.optics↗

arXiv2020

Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet

The identification of nerve is difficult as structures of nerves are challenging to image and to detect in ultrasound images. Nevertheless, the nerve identification in ultrasound images is a crucial step to improve performance of regional anesthesia. In this paper, a network called Brachial Plexus Multi-instance Segmentation Network (BPMSegNet) is proposed to identify different tissues (nerves, arteries, veins, muscles) in ultrasound images. The BPMSegNet has three novel modules. The first is the spatial local contrast feature, which computes contrast features at different scales. The second one is the self-attention gate, which reweighs the channels in feature maps by their importance. The third is the addition of a skip concatenation with transposed convolution within a feature pyramid network. The proposed BPMSegNet is evaluated by conducting experiments on our constructed Ultrasound Brachial Plexus Dataset (UBPD). Quantitative experimental results show the proposed network can segment multiple tissues from the ultrasound images with a good performance.

cs.CV↗

arXiv2020

Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation

We present a self-supervised learning approach for the semantic segmentation of lidar frames. Our method is used to train a deep point cloud segmentation architecture without any human annotation. The annotation process is automated with the combination of simultaneous localization and mapping (SLAM) and ray-tracing algorithms. By performing multiple navigation sessions in the same environment, we are able to identify permanent structures, such as walls, and disentangle short-term and long-term movable objects, such as people and tables, respectively. New sessions can then be performed using a network trained to predict these semantic labels. We demonstrate the ability of our approach to improve itself over time, from one session to the next. With semantically filtered point clouds, our robot can navigate through more complex scenarios, which, when added to the training pool, help to improve our network predictions. We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.

cs.RO↗

arXiv2020

Rigid and Articulated Point Registration with Expectation Conditional Maximization

This paper addresses the issue of matching rigid and articulated shapes through probabilistic point registration. The problem is recast into a missing data framework where unknown correspondences are handled via mixture models. Adopting a maximum likelihood principle, we introduce an innovative EM-like algorithm, namely the Expectation Conditional Maximization for Point Registration (ECMPR) algorithm. The algorithm allows the use of general covariance matrices for the mixture model components and improves over the isotropic covariance case. We analyse in detail the associated consequences in terms of estimation of the registration parameters, and we propose an optimal method for estimating the rotational and translational parameters based on semi-definite positive relaxation. We extend rigid registration to articulated registration. Robustness is ensured by detecting and rejecting outliers through the addition of a uniform component to the Gaussian mixture model at hand. We provide an in-depth analysis of our method and we compare it both theoretically and experimentally with other robust methods for point registration.

cs.CV↗