arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 703 records · Page 39Linked to original sources

arXiv2022

Learning Granularity-Unified Representations for Text-to-Image Person Re-identification

Text-to-image person re-identification (ReID) aims to search for pedestrian images of an interested identity via textual descriptions. It is challenging due to both rich intra-modal variations and significant inter-modal gaps. Existing works usually ignore the difference in feature granularity between the two modalities, i.e., the visual features are usually fine-grained while textual features are coarse, which is mainly responsible for the large inter-modal gaps. In this paper, we propose an end-to-end framework based on transformers to learn granularity-unified representations for both modalities, denoted as LGUR. LGUR framework contains two modules: a Dictionary-based Granularity Alignment (DGA) module and a Prototype-based Granularity Unification (PGU) module. In DGA, in order to align the granularities of two modalities, we introduce a Multi-modality Shared Dictionary (MSD) to reconstruct both visual and textual features. Besides, DGA has two important factors, i.e., the cross-modality guidance and the foreground-centric reconstruction, to facilitate the optimization of MSD. In PGU, we adopt a set of shared and learnable prototypes as the queries to extract diverse and semantically aligned features for both modalities in the granularity-unified feature space, which further promotes the ReID performance. Comprehensive experiments show that our LGUR consistently outperforms state-of-the-arts by large margins on both CUHK-PEDES and ICFG-PEDES datasets. Code will be released at https://github.com/ZhiyinShao-H/LGUR.

cs.CV↗

arXiv2022

The stochastic nonlinear Schrödinger equations driven by pure jump noise

In this paper, we establish the existence and uniqueness of solutions of stochastic nonlinear Schrödinger equations with additive jump noise in $L^2(\mathbb{R}^d)$. Our results cover all either focusing or defocusing nonlinearity in the full subcritical range of exponents as in the deterministic case.

math.PR↗

arXiv2022

Reply to Comment on "Self-Consistent-Field Method for Correlated Many-Electron Systems with an Entropic Cumulant Energy", arXiv2202.05532v1

Recently we proposed an information entropy based method for electronic structure calculations within the density-matrix functional theory(DMFT) (Phys. Rev. Lett. 128, 013001), dubbed as $i$-DMFT. Comments have been raised regarding the accuracy of the one-particle density-matrix compared to that from the wave function, and the universality of the functional. We address these questions and the problematic case of HeH$^+$.

quant-ph↗

arXiv2022

Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach

Load forecasting is very essential in the analysis and grid planning of power systems. For this reason, we first propose a household load forecasting method based on federated deep learning and non-intrusive load monitoring (NILM). For all we know, this is the first research on federated learning (FL) in household load forecasting based on NILM. In this method, the integrated power is decomposed into individual device power by non-intrusive load monitoring, and the power of individual appliances is predicted separately using a federated deep learning model. Finally, the predicted power values of individual appliances are aggregated to form the total power prediction. Specifically, by separately predicting the electrical equipment to obtain the predicted power, it avoids the error caused by the strong time dependence in the power signal of a single device. And in the federated deep learning prediction model, the household owners with the power data share the parameters of the local model instead of the local power data, guaranteeing the privacy of the household user data. The case results demonstrate that the proposed approach provides a better prediction effect than the traditional methodology that directly predicts the aggregated signal as a whole. In addition, experiments in various federated learning environments are designed and implemented to validate the validity of this methodology.

cs.LG↗

arXiv2022

RACS2: A Framework of Remote Autonomous Control System for Telescope Observation and its application

As the demand of astronomical observation rising, the telescope systems are becoming more and more complex. Thus, the observatory control software needs to be more intelligent, they have to control each instrument inside the observatory, finish the observation tasks autonomously, and report the information to users if needed. We developed a distributed autonomous observatory control framework named Remote Autonomous Control System 2nd, RACS2 to meet these requirements. The RACS2 framework uses decentralized distributed architecture, instrument control software and system service such as observation control service are implemented as different components. The communication between components is implemented based on a high-performance serialization library and a light-weighted messaging library.The interfaces towards python and Experimental Physics and Industrial Control System (EPICS) are implemented, so the RACS2 framework can communicate with EPICS based device control software and python-based software. Several system components including log, executor, scheduler and other modules are developed to help observation. Observation tasks can be programmed with python language, and the plans are scheduled by the scheduler component to achieve autonomous observation.A set of web service is implemented based on the FastAPI framework, with which user can control and manage the framework remotely.Based on the RACS2 framework, we have implemented the DATs telescope's observation system and the space object observation system.We performed remote autonomous observation and received many data with these systems.

astro-ph.IM↗

arXiv2022

MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue

Automatic open-domain dialogue evaluation is a crucial component of dialogue systems. Recently, learning-based evaluation metrics have achieved state-of-the-art performance in open-domain dialogue evaluation. However, these metrics, which only focus on a few qualities, are hard to evaluate dialogue comprehensively. Furthermore, these metrics lack an effective score composition approach for diverse evaluation qualities. To address the above problems, we propose a Multi-Metric Evaluation based on Correlation Re-Scaling (MME-CRS) for evaluating open-domain dialogue. Firstly, we build an evaluation metric composed of 5 groups of parallel sub-metrics called Multi-Metric Evaluation (MME) to evaluate the quality of dialogue comprehensively. Furthermore, we propose a novel score composition method called Correlation Re-Scaling (CRS) to model the relationship between sub-metrics and diverse qualities. Our approach MME-CRS ranks first on the final test data of DSTC10 track5 subtask1 Automatic Open-domain Dialogue Evaluation Challenge with a large margin, which proved the effectiveness of our proposed approach.

cs.CL↗

arXiv2022

Structured Light with Redundancy Codes

Structured light (SL) systems acquire high-fidelity 3D geometry with active illumination projection. Conventional systems exhibit challenges when working in environments with strong ambient illumination, global illumination and cross-device interference. This paper proposes a general-purposed technique to improve the robustness of SL by projecting redundant optical signals in addition to the native SL patterns. In this way, projected signals become more distinguishable from errors. Thus the geometry information can be more easily recovered using simple signal processing and the ``coding gain" in performance is obtained. We propose three applications using our redundancy codes: (1) Self error-correction for SL imaging under strong ambient light, (2) Error detection for adaptive reconstruction under global illumination, and (3) Interference filtering with device-specific projection sequence encoding, especially for event camera-based SL and light curtain devices. We systematically analyze the design rules and signal processing algorithms in these applications. Corresponding hardware prototypes are built for evaluations on real-world complex scenes. Experimental results on the synthetic and real data demonstrate the significant performance improvements in SL systems with our redundancy codes.

cs.CV↗

arXiv2022

ET White Paper: To Find the First Earth 2.0

We propose to develop a wide-field and ultra-high-precision photometric survey mission, temporarily named "Earth 2.0 (ET)". This mission is designed to measure, for the first time, the occurrence rate and the orbital distributions of Earth-sized planets. ET consists of seven 30cm telescopes, to be launched to the Earth-Sun's L2 point. Six of these are transit telescopes with a field of view of 500 square degrees. Staring in the direction that encompasses the original Kepler field for four continuous years, this monitoring will return tens of thousands of transiting planets, including the elusive Earth twins orbiting solar-type stars. The seventh telescope is a 30cm microlensing telescope that will monitor an area of 4 square degrees toward the galactic bulge. This, combined with simultaneous ground-based KMTNet observations, will measure masses for hundreds of long-period and free-floating planets. Together, the transit and the microlensing telescopes will revolutionize our understandings of terrestrial planets across a large swath of orbital distances and free space. In addition, the survey data will also facilitate studies in the fields of asteroseismology, Galactic archeology, time-domain sciences, and black holes in binaries.

astro-ph.IM↗

arXiv2022

One-Bit Matrix Completion with Differential Privacy

As a prevailing collaborative filtering method for recommendation systems, one-bit matrix completion requires data collected by users to provide personalized service. Due to insidious attacks and unexpected inference, the release of users' data often raises serious privacy concerns. To address this issue, differential privacy(DP) has been widely used in standard matrix completion models. To date, however, little has been known about how to apply DP to achieve privacy protection in one-bit matrix completion. In this paper, we propose a unified framework for ensuring a strong privacy guarantee of one-bit matrix completion with DP. In our framework, we develop four different private perturbation mechanisms corresponding to different stages of one-bit matrix completion. For each mechanism, we design a privacy-preserving algorithm and provide a theoretical recovery error bound under the proper conditions. Numerical experiments on synthetic and real-world datasets demonstrate the effectiveness of our proposal. Compared to the one-bit matrix completion without privacy protection, our proposed mechanisms can maintain high-level privacy protection with marginal loss of completion accuracy.

cs.CR↗

arXiv2022

Quantum Support Vector Machine without Iteration

Quantum algorithms can enhance machine learning in different aspects. In 2014, Rebentrost $et~al.$ constructed a least squares quantum support vector machine (LS-QSVM), in which the Swap Test plays a crucial role in realizing the classification. However, as the output states of a previous test cannot be reused for a new test in the Swap Test, the quantum algorithm LS-QSVM has to be repeated in preparing qubits, manipulating operations, and carrying out the measurement. This paper proposes a QSVM based on the generalized quantum amplitude estimation (AE-QSVM) which gets rid of the constraint of repetitive processes and saves the quantum resources. At first, AE-QSVM is trained by using the quantum singular value decomposition. Then, a query sample is classified by using the generalized quantum amplitude estimation in which high accuracy can be achieved by adding auxiliary qubits instead of repeating the algorithm. The complexity of AE-QSVM is reduced to $O(κ^{3}\varepsilon^{-3}(log(mn)+1))$ with an accuracy $\varepsilon$, where $m$ is the number of training vectors, $n$ is the dimension of the feature space, and $κ$ is the condition number. Experiments demonstrate that AE-QSVM is advantageous in terms of training matrix, the number of iterations, space complexity, and time complexity.

quant-ph↗

arXiv2022

Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound

Standard plane recognition plays an important role in prenatal ultrasound (US) screening. Automatically recognizing the standard plane along with the corresponding anatomical structures in US image can not only facilitate US image interpretation but also improve diagnostic efficiency. In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously. Our contribution is three-fold. First, we represent the class correlation by word embeddings to capture the fine-grained semantic and latent statistical concurrency. Second, we equip the MLL with a graph convolutional network to explore the inner and outer relationship among categories. Third, we propose a novel cluster relabel-based contrastive learning algorithm to encourage the divergence among ambiguous classes. Extensive validation was performed on our large in-house dataset. Our approach reports the highest accuracy as 90.25% for standard planes labeling, 85.59% for planes and structures labeling and mAP as 94.63%. The proposed MLL scheme provides a novel perspective for standard plane recognition and can be easily extended to other medical image classification tasks.

cs.CV↗

arXiv2022

Snowmass 2021 White Paper: Resummation for future colliders

Resummation techniques are essential for high-precision phenomenology at current and future high-energy collider experiments. Perturbative computations of cross sections often suffer from large logarithmic corrections, which must be resummed to all orders to restore the reliability of predictions from first principles. The precise understanding of the all-order structure of field theories allows for fundamental tests of the Standard Model and new physics searches. In this white paper, we review recent progress in modern resummation techniques and outline future directions. In particular, we focus on the resummation beyond leading power, the joint resummation of different classes of logarithms relevant for jets and their substructure, small-$x$ resummation in the high-energy regime and the QCD fragmentation process in the small-$z_h$ limit.

hep-ph↗

arXiv2022

Counterexamples to Gerbner's Conjecture on Stability of Maximal $F$-free Graphs

Let $F$ be an $(r+1)$-color critical graph with $r\geq 2$, that is, $χ(F)=r+1$ and there is an edge $e$ in $F$ such that $χ(F-e)=r$. Gerbner recently conjectured that every $n$-vertex maximal $F$-free graph with at least $(1-\frac{1}{r})\frac{n^2}{2}- o(n^{\frac{r+1}{r}})$ edges contains an induced complete $r$-partite graph on $n-o(n)$ vertices. Let $F_{s,k}$ be a graph obtained from $s$ copies of $C_{2k+1}$ by sharing a common edge. In this paper, we show that for all $k\geq 2$ if $G$ is an $n$-vertex maximal $F_{s,k}$-free graph with at least $n^{2}/4 - o(n^{\frac{s+2}{s+1}})$ edges, then $G$ contains an induced complete bipartite graph on $n-o(n)$ vertices. We also show that it is best possible. This disproves Gerbner's conjecture for $r=2$.

math.CO↗

arXiv2022

Intersections and Distinct Intersections in Cross-intersecting Families

Let $\mathcal{F},\mathcal{G}$ be two cross-intersecting families of $k$-subsets of $\{1,2,\ldots,n\}$. Let $\mathcal{F}\wedge \mathcal{G}$, $\mathcal{I}(\mathcal{F},\mathcal{G})$ denote the families of all intersections $F\cap G$ with $F\in \mathcal{F},G\in \mathcal{G}$, and all distinct intersections $F\cap G$ with $F\neq G, F\in \mathcal{F},G\in \mathcal{G}$, respectively. For a fixed $T\subset \{1,2,\ldots,n\}$, let $\mathcal{S}_T$ be the family of all $k$-subsets of $\{1,2,\ldots,n\}$ containing $T$. In the present paper, we show that $|\mathcal{F}\wedge \mathcal{G}|$ is maximized when $\mathcal{F}=\mathcal{G}=\mathcal{S}_{\{1\}}$ for $n\geq 2k^2+8k$, while surprisingly $|\mathcal{I}(\mathcal{F}, \mathcal{G})|$ is maximized when $\mathcal{F}=\mathcal{S}_{\{1,2\}}\cup \mathcal{S}_{\{3,4\}}\cup \mathcal{S}_{\{1,4,5\}}\cup \mathcal{S}_{\{2,3,6\}}$ and $\mathcal{G}=\mathcal{S}_{\{1,3\}}\cup \mathcal{S}_{\{2,4\}}\cup \mathcal{S}_{\{1,4,6\}}\cup \mathcal{S}_{\{2,3,5\}}$ for $n\geq 100k^2$. The maximum number of distinct intersections in a $t$-intersecting family is determined for $n\geq 3(t+2)^3k^2$ as well.

math.CO↗

arXiv2022

Evolution of Electronic and Magnetic Properties in Topological Semimetal SmSbxTe2-x

The ZrSiS-type materials have attracted intensive attention due to the existence of various topological fermions. The magnetic version of the ZrSiS-type materials, LnSbTe (Ln = lanthanides), is an ideal candidate to explore novel exotic states due to the interaction between magnetism and topology. In this work, we report the experimental study on structural, magnetic, thermodynamic, and electronic properties for SmSbxTe2-x with various Sb content. The revealed evolutions of these properties with tuning the compositions would provide useful insights for the fundamental topological physics and the future applications.

cond-mat.mtrl-sci↗

arXiv2022

Human-Object Interaction Detection via Disentangled Transformer

Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus on different regions. To this end, we present Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two sub-tasks. To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder. Extensive experiments show that our method outperforms prior work on two public HOI benchmarks by a sizeable margin. Code will be available.

cs.CV↗

arXiv2022

PP-Matting: High-Accuracy Natural Image Matting

Natural image matting is a fundamental and challenging computer vision task. It has many applications in image editing and composition. Recently, deep learning-based approaches have achieved great improvements in image matting. However, most of them require a user-supplied trimap as an auxiliary input, which limits the matting applications in the real world. Although some trimap-free approaches have been proposed, the matting quality is still unsatisfactory compared to trimap-based ones. Without the trimap guidance, the matting models suffer from foreground-background ambiguity easily, and also generate blurry details in the transition area. In this work, we propose PP-Matting, a trimap-free architecture that can achieve high-accuracy natural image matting. Our method applies a high-resolution detail branch (HRDB) that extracts fine-grained details of the foreground with keeping feature resolution unchanged. Also, we propose a semantic context branch (SCB) that adopts a semantic segmentation subtask. It prevents the detail prediction from local ambiguity caused by semantic context missing. In addition, we conduct extensive experiments on two well-known benchmarks: Composition-1k and Distinctions-646. The results demonstrate the superiority of PP-Matting over previous methods. Furthermore, we provide a qualitative evaluation of our method on human matting which shows its outstanding performance in the practical application. The code and pre-trained models will be available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.

cs.CV↗

arXiv2022

Implicit Sample Extension for Unsupervised Person Re-Identification

Most existing unsupervised person re-identification (Re-ID) methods use clustering to generate pseudo labels for model training. Unfortunately, clustering sometimes mixes different true identities together or splits the same identity into two or more sub clusters. Training on these noisy clusters substantially hampers the Re-ID accuracy. Due to the limited samples in each identity, we suppose there may lack some underlying information to well reveal the accurate clusters. To discover these information, we propose an Implicit Sample Extension (\OurWholeMethod) method to generate what we call support samples around the cluster boundaries. Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy. PLI controls the generation with two critical factors, i.e., 1) the direction from the actual sample towards its K-nearest clusters and 2) the degree for mixing up the context information from the K-nearest clusters. Meanwhile, given the support samples, ISE further uses a label-preserving loss to pull them towards their corresponding actual samples, so as to compact each cluster. Consequently, ISE reduces the "sub and mixed" clustering errors, thus improving the Re-ID performance. Extensive experiments demonstrate that the proposed method is effective and achieves state-of-the-art performance for unsupervised person Re-ID. Code is available at: \url{https://github.com/PaddlePaddle/PaddleClas}.

cs.CV↗