arXiv subjects

Jingbo Wang

Publications and source records attributed to Jingbo Wang.

At least 163 records · Page 9Linked to original sources

arXiv2023

Certifying the Fairness of KNN in the Presence of Dataset Bias

We propose a method for certifying the fairness of the classification result of a widely used supervised learning algorithm, the k-nearest neighbors (KNN), under the assumption that the training data may have historical bias caused by systematic mislabeling of samples from a protected minority group. To the best of our knowledge, this is the first certification method for KNN based on three variants of the fairness definition: individual fairness, $ε$-fairness, and label-flipping fairness. We first define the fairness certification problem for KNN and then propose sound approximations of the complex arithmetic computations used in the state-of-the-art KNN algorithm. This is meant to lift the computation results from the concrete domain to an abstract domain, to reduce the computational cost. We show effectiveness of this abstract interpretation based technique through experimental evaluation on six datasets widely used in the fairness research literature. We also show that the method is accurate enough to obtain fairness certifications for a large number of test inputs, despite the presence of historical bias in the datasets.

cs.LG↗

arXiv2023

Searching for the nano-Hertz stochastic gravitational wave background with the Chinese Pulsar Timing Array Data Release I

Observing and timing a group of millisecond pulsars (MSPs) with high rotational stability enables the direct detection of gravitational waves (GWs). The GW signals can be identified from the spatial correlations encoded in the times-of-arrival of widely spaced pulsar-pairs. The Chinese Pulsar Timing Array (CPTA) is a collaboration aiming at the direct GW detection with observations carried out using Chinese radio telescopes. This short article serves as a `table of contents' for a forthcoming series of papers related to the CPTA Data Release 1 (CPTA DR1) which uses observations from the Five-hundred-meter Aperture Spherical radio Telescope (FAST). Here, after summarizing the time span and accuracy of CPTA DR1, we report the key results of our statistical inference finding a correlated signal with amplitude $\log A_{\rm c}= -14.4 \,^{+1.0}_{-2.8}$ for spectral index in the range of $α\in [-1.8, 1.5]$ assuming a GW background (GWB) induced quadrupolar correlation. The search for the Hellings-Downs (HD) correlation curve is also presented, where some evidence for the HD correlation has been found that a 4.6-$σ$ statistical significance is achieved using the discrete frequency method around the frequency of 14 nHz. We expect that the future International Pulsar Timing Array data analysis and the next CPTA data release will be more sensitive to the nHz GWB, which could verify the current results.

astro-ph.HE↗

arXiv2023

Interactive Segment Anything NeRF with Feature Imitation

This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world applications like VR and digital creation, the lack of semantics hinders interaction with objects in complex scenes. We propose to imitate the backbone feature of off-the-shelf perception models to achieve zero-shot semantic segmentation with NeRF. Our framework reformulates the segmentation process by directly rendering semantic features and only applying the decoder from perception models. This eliminates the need for expensive backbones and benefits 3D consistency. Furthermore, we can project the learned semantics onto extracted mesh surfaces for real-time interaction. With the state-of-the-art Segment Anything Model (SAM), our framework accelerates segmentation by 16 times with comparable mask quality. The experimental results demonstrate the efficacy and computational advantages of our approach. Project page: \url{https://me.kiui.moe/san/}.

cs.CV↗

arXiv2023

Quantum Phase Recognition via Quantum Kernel Methods

The application of quantum computation to accelerate machine learning algorithms is one of the most promising areas of research in quantum algorithms. In this paper, we explore the power of quantum learning algorithms in solving an important class of Quantum Phase Recognition (QPR) problems, which are crucially important in understanding many-particle quantum systems. We prove that, under widely believed complexity theory assumptions, there exists a wide range of QPR problems that cannot be efficiently solved by classical learning algorithms with classical resources. Whereas using a quantum computer, we prove the efficiency and robustness of quantum kernel methods in solving QPR problems through Linear order parameter Observables. We numerically benchmark our algorithm for a variety of problems, including recognizing symmetry-protected topological phases and symmetry-broken phases. Our results highlight the capability of quantum machine learning in predicting such quantum phase transitions in many-particle systems.

quant-ph↗

arXiv2023

The topological order in loop quantum gravity

Topological order (long-range entanglement) is a new type of order that beyond Landau's symmetry breaking theory. This concept plays important roles in modern condensed matter physics. The topological entanglement entropy provides a universal quantum number to characterize the topological order in a system. The topological entanglement entropy of the BTZ black hole was calculated and found that it coincides with that for fractional quantum Hall states. So the BTZ black hole has the same topological order with the fractional quantum Hall state. We show that the four dimensional black hole can also have topological order, by showing that the topological entanglement entropy of black holes is non-zero in loop quantum gravity. We also consider the Hamiltonian constraint in loop quantum gravity. By comparing with the BF theory, we found that the physical Hilbert space for loop quantum gravity is degenerate on non-trivial manifold, which indicate the existence of topological order in loop quantum gravity. We advise to bring in the methods and results in string-net condensation to loop quantum gravity to solve some difficult problems.

gr-qc↗

arXiv2023

Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective

We revisit Semantic Scene Completion (SSC), a useful task to predict the semantic and occupancy representation of 3D scenes, in this paper. A number of methods for this task are always based on voxelized scene representations for keeping local scene structure. However, due to the existence of visible empty voxels, these methods always suffer from heavy computation redundancy when the network goes deeper, and thus limit the completion quality. To address this dilemma, we propose our novel point-voxel aggregation network for this task. Firstly, we transfer the voxelized scenes to point clouds by removing these visible empty voxels and adopt a deep point stream to capture semantic information from the scene efficiently. Meanwhile, a light-weight voxel stream containing only two 3D convolution layers preserves local structures of the voxelized scenes. Furthermore, we design an anisotropic voxel aggregation operator to fuse the structure details from the voxel stream into the point stream, and a semantic-aware propagation module to enhance the up-sampling process in the point stream by semantic labels. We demonstrate that our model surpasses state-of-the-arts on two benchmarks by a large margin, with only depth images as the input.

cs.CV↗

arXiv2023

Study of pulsar flux density and its variability with Parkes data archive

We present average flux density measurements of 151 radio pulsars at 1.4 GHz with the Parkes 'Murriyang' radio telescope. We recommend our results be included in the next version of the ATNF pulsar catalogue. The large sample of pulsars together with their wide dispersion measure (DM) range make this data set useful for studying variability of flux density, pulsar spectra, and interstellar medium (ISM). We derive the modulation indices and structure-function from the flux density time series for 95 and 54 pulsars, respectively. We suggest the modulation index also be included in the next version of the pulsar catalogue to manifest the variability of pulsar flux density. The modulation index of flow density and DM are negatively correlated. The refractive scintillation (RISS) timescales or its lower bound for a set of 15 pulsars are derived. They are very different from theoretical expectations, implying the complicated properties of the ISM along different lines of sight. The structure-function for other pulsars is flat. The RISS parameters for some of these pulsars possibly could be derived with different observing strategies in the future.

astro-ph.HE↗

arXiv2022

Constraining cosmological phase transitions with the Parkes Pulsar Timing Array

A cosmological first-order phase transition is expected to produce a stochastic gravitational wave background. If the phase transition temperature is on the MeV scale, the power spectrum of the induced stochastic gravitational waves peaks around nanohertz frequencies, and can thus be probed with high-precision pulsar timing observations. We search for such a stochastic gravitational wave background with the latest data set of the Parkes Pulsar Timing Array. We find no evidence for a Hellings-Downs spatial correlation as expected for a stochastic gravitational wave background. Therefore, we present constraints on first-order phase transition model parameters. Our analysis shows that pulsar timing is particularly sensitive to the low-temperature ($T \sim 1 - 100$ MeV) phase transition with a duration $(β/H_*)^{-1}\sim 10^{-2}-10^{-1}$ and therefore can be used to constrain the dark and QCD phase transitions.

astro-ph.CO↗

arXiv2022

Black Hole Membrane Paradigm from Boundary Scalar Field

Black hole membrane paradigm suggests to consider the black hole horizon as a fluid membrane. The membrane has a particular energy-momentum tensor which characterizes the interactions with the falling matter. In this paper, we show that we can construct an action from the scalar field on the horizon which can give the same energy-momentum tensor for the membrane. That is, the membrane can be described effectively by the scalar field on it.

hep-th↗

arXiv2022

Compressible-composable NeRF via Rank-residual Decomposition

Neural Radiance Field (NeRF) has emerged as a compelling method to represent 3D objects and scenes for photo-realistic rendering. However, its implicit representation causes difficulty in manipulating the models like the explicit mesh representation. Several recent advances in NeRF manipulation are usually restricted by a shared renderer network, or suffer from large model size. To circumvent the hurdle, in this paper, we present an explicit neural field representation that enables efficient and convenient manipulation of models. To achieve this goal, we learn a hybrid tensor rank decomposition of the scene without neural networks. Motivated by the low-rank approximation property of the SVD algorithm, we propose a rank-residual learning strategy to encourage the preservation of primary information in lower ranks. The model size can then be dynamically adjusted by rank truncation to control the levels of detail, achieving near-optimal compression without extra optimization. Furthermore, different models can be arbitrarily transformed and composed into one scene by concatenating along the rank dimension. The growth of storage cost can also be mitigated by compressing the unimportant objects in the composed scene. We demonstrate that our method is able to achieve comparable rendering quality to state-of-the-art methods, while enabling extra capability of compression and composition. Code will be made available at https://github.com/ashawkey/CCNeRF.

cs.CV↗

arXiv2022

Optimal Nonparametric Inference with Two-Scale Distributional Nearest Neighbors

The weighted nearest neighbors (WNN) estimator has been popularly used as a flexible and easy-to-implement nonparametric tool for mean regression estimation. The bagging technique is an elegant way to form WNN estimators with weights automatically generated to the nearest neighbors; we name the resulting estimator as the distributional nearest neighbors (DNN) for easy reference. Yet, there is a lack of distributional results for such estimator, limiting its application to statistical inference. Moreover, when the mean regression function has higher-order smoothness, DNN does not achieve the optimal nonparametric convergence rate, mainly because of the bias issue. In this work, we provide an in-depth technical analysis of the DNN, based on which we suggest a bias reduction approach for the DNN estimator by linearly combining two DNN estimators with different subsampling scales, resulting in the novel two-scale DNN (TDNN) estimator. The two-scale DNN estimator has an equivalent representation of WNN with weights admitting explicit forms and some being negative. We prove that, thanks to the use of negative weights, the two-scale DNN estimator enjoys the optimal nonparametric rate of convergence in estimating the regression function under the fourth-order smoothness condition. We further go beyond estimation and establish that the DNN and two-scale DNN are both asymptotically normal as the subsampling scales and sample size diverge to infinity. For the practical implementation, we also provide variance estimators and a distribution estimator using the jackknife and bootstrap techniques for the two-scale DNN. These estimators can be exploited for constructing valid confidence intervals for nonparametric inference of the regression function. The theoretical results and appealing finite-sample performance of the suggested two-scale DNN method are illustrated with several numerical examples.

stat.ML↗

arXiv2022

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

Semantic scene reconstruction from point cloud is an essential and challenging task for 3D scene understanding. This task requires not only to recognize each instance in the scene, but also to recover their geometries based on the partial observed point cloud. Existing methods usually attempt to directly predict occupancy values of the complete object based on incomplete point cloud proposals from a detection-based backbone. However, this framework always fails to reconstruct high fidelity mesh due to the obstruction of various detected false positive object proposals and the ambiguity of incomplete point observations for learning occupancy values of complete objects. To circumvent the hurdle, we propose a Disentangled Instance Mesh Reconstruction (DIMR) framework for effective point scene understanding. A segmentation-based backbone is applied to reduce false positive object proposals, which further benefits our exploration on the relationship between recognition and reconstruction. Based on the accurate proposals, we leverage a mesh-aware latent code space to disentangle the processes of shape completion and mesh generation, relieving the ambiguity caused by the incomplete point observations. Furthermore, with access to the CAD model pool at test time, our model can also be used to improve the reconstruction quality by performing mesh retrieval without extra training. We thoroughly evaluate the reconstructed mesh quality with multiple metrics, and demonstrate the superiority of our method on the challenging ScanNet dataset. Code is available at \url{https://github.com/ashawkey/dimr}.

cs.CV↗

arXiv2022

Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works that separately model each task as a multi-head prediction problem, our insight is to bridge these two tasks with one unified model via vision transformer modeling to benefit each task. In particular, we introduce the object query for segmentation and the attribute query for attribute prediction. Both queries and their corresponding features can be linked via mask prediction. Then we adopt a two-stream query learning framework to learn the decoupled query representations.We design a novel Multi-Layer Rendering module for attribute stream to explore more fine-grained features. The decoder design shares the same spirit as DETR. Thus we name the proposed method \textit{Fahsionformer}. Extensive experiments on three human fashion datasets illustrate the effectiveness of our approach. In particular, our method with the same backbone achieve \textbf{relative 10\% improvements} than previous works in case of \textit{a joint metric (AP$^{\text{mask}}_{\text{IoU+F}_1}$) for both segmentation and attribute recognition}. To the best of our knowledge, we are the first unified end-to-end vision transformer framework for human fashion analysis. We hope this simple yet effective method can serve as a new flexible baseline for fashion analysis. Code is available at https://github.com/xushilin1/FashionFormer.

cs.CV↗

arXiv2022

Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis

The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are constrained by pre-defined target objects or positions and thus limit the diversity of human-scene interactions for synthesized motions. In this paper, we focus on the problem of synthesizing diverse scene-aware human motions under the guidance of target action sequences. To achieve this, we first decompose the diversity of scene-aware human motions into three aspects, namely interaction diversity (e.g. sitting on different objects with different poses in the given scenes), path diversity (e.g. moving to the target locations following different paths), and the motion diversity (e.g. having various body movements during moving). Based on this factorized scheme, a hierarchical framework is proposed, with each sub-module responsible for modeling one aspect. We assess the effectiveness of our framework on two challenging datasets for scene-aware human motion synthesis. The experiment results show that the proposed framework remarkably outperforms previous methods in terms of diversity and naturalness.

cs.CV↗

arXiv2022

Assessing the Performance of Online Students -- New Data, New Approaches, Improved Accuracy

We consider the problem of assessing the changing performance levels of individual students as they go through online courses. This student performance (SP) modeling problem is a critical step for building adaptive online teaching systems. Specifically, we conduct a study of how to utilize various types and large amounts of student log data to train accurate machine learning (ML) models that predict the performance of future students. This study is the first to use four very large sets of student data made available recently from four distinct intelligent tutoring systems. Our results include a new ML approach that defines a new state of the art for logistic regression based SP modeling, improving over earlier methods in several ways: First, we achieve improved accuracy by introducing new features that can be easily computed from conventional question-response logs (e.g., the pattern in the student 's most recent answers). Second, we take advantage of features of the student history that go beyond question-response pairs (e.g., features such as which video segments the student watched, or skipped) as well as information about prerequisite structure in the curriculum. Third, we train multiple specialized SP models for different aspects of the curriculum (e.g., specializing in early versus later segments of the student history), then combine these specialized models to create a group prediction of the SP. Taken together, these innovations yield an average AUC score across these four datasets of 0.808 compared to the previous best logistic regression approach score of 0.767, and also outperforming state-of-the-art deep neural net approaches. Importantly, we observe consistent improvements from each of our three methodological innovations, in each dataset, suggesting that our methods are of general utility and likely to produce improvements for other online tutoring systems as well.

cs.LG↗

arXiv2021

High-precision search for dark photon dark matter with the Parkes Pulsar Timing Array

The nature of dark matter remains obscure in spite of decades of experimental efforts. The mass of dark matter candidates can span a wide range, and its coupling with the Standard Model sector remains uncertain. All these unknowns make the etection of dark matter extremely challenging. Ultralight dark matter, with $m \sim10^{-22}$ eV, is proposed to reconcile the disagreements between observations and predictions from simulations of small-scale structures in the cold dark matter paradigm, while remaining consistent with other observations. Because of its large de Broglie wavelength and large local occupation number within galaxies, ultralight dark matter behaves like a coherently oscillating background field with an oscillating frequency dependent on its mass. If the dark matter particle is a spin-1 dark photon, such as the $U(1)_B$ or $U(1)_{B-L}$ gauge boson, it can induce an external oscillating force and lead to displacements of test masses. Such an effect would be observable in the form of periodic variations in the arrival times of radio pulses from highly stable millisecond pulsars. In this study, we search for evidence of ultralight dark photon dark matter (DPDM) using 14-year high-precision observations of 26 pulsars collected with the Parkes Pulsar Timing Array. While no statistically significant signal is found, we place constraints on coupling constants for the $U(1)_B$ and $U(1)_{B-L}$ DPDM. Compared with other experiments, the limits on the dimensionless coupling constant $ε$ achieved in our study are improved by up to two orders of magnitude when the dark photon mass is smaller than $3\times10^{-22}$~eV ($10^{-22}$~eV) for the $U(1)_{B}$ ($U(1)_{B-L}$) scenario.

hep-ph↗

arXiv2021

Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements

3D interacting hand reconstruction is essential to facilitate human-machine interaction and human behaviors understanding. Previous works in this field either rely on auxiliary inputs such as depth images or they can only handle a single hand if monocular single RGB images are used. Single-hand methods tend to generate collided hand meshes, when applied to closely interacting hands, since they cannot model the interactions between two hands explicitly. In this paper, we make the first attempt to reconstruct 3D interacting hands from monocular single RGB images. Our method can generate 3D hand meshes with both precise 3D poses and minimal collisions. This is made possible via a two-stage framework. Specifically, the first stage adopts a convolutional neural network to generate coarse predictions that tolerate collisions but encourage pose-accurate hand meshes. The second stage progressively ameliorates the collisions through a series of factorized refinements while retaining the preciseness of 3D poses. We carefully investigate potential implementations for the factorized refinement, considering the trade-off between efficiency and accuracy. Extensive quantitative and qualitative results on large-scale datasets such as InterHand2.6M demonstrate the effectiveness of the proposed approach.

cs.CV↗

arXiv2021

Estimating Gibbs partition function with quantumClifford sampling

The partition function is an essential quantity in statistical mechanics, and its accurate computation is a key component of any statistical analysis of quantum system and phenomenon. However, for interacting many-body quantum systems, its calculation generally involves summing over an exponential number of terms and can thus quickly grow to be intractable. Accurately and efficiently estimating the partition function of its corresponding system Hamiltonian then becomes the key in solving quantum many-body problems. In this paper we develop a hybrid quantum-classical algorithm to estimate the partition function, utilising a novel Clifford sampling technique. Note that previous works on quantum estimation of partition functions require $\mathcal{O}(1/ε\sqrtΔ)$-depth quantum circuits~\cite{Arunachalam2020Gibbs, Ashley2015Gibbs}, where $Δ$ is the minimum spectral gap of stochastic matrices and $ε$ is the multiplicative error. Our algorithm requires only a shallow $\mathcal{O}(1)$-depth quantum circuit, repeated $\mathcal{O}(1/ε^2)$ times, to provide a comparable $ε$ approximation. Shallow-depth quantum circuits are considered vitally important for currently available NISQ (Noisy Intermediate-Scale Quantum) devices.

quant-ph↗