Searcharxiv⌕ Search

arXiv subjects

Yu Xiang

Publications and source records attributed to Yu Xiang.

At least 73 records · Page 4Linked to original sources
arXiv2024

Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification

We present a unified framework called deep dependency networks (DDNs) that combines dependency networks and deep learning architectures for multi-label classification, with a particular emphasis on image and video data. The primary advantage of dependency networks is their ease of training, in contrast to other probabilistic graphical models like Markov networks. In particular, when combined with deep learning architectures, they provide an intuitive, easy-to-use loss function for multi-label classification. A drawback of DDNs compared to Markov networks is their lack of advanced inference schemes, necessitating the use of Gibbs sampling. To address this challenge, we propose novel inference schemes based on local search and integer linear programming for computing the most likely assignment to the labels given observations. We evaluate our novel methods on three video datasets (Charades, TACoS, Wetlab) and three image datasets (MS-COCO, PASCAL VOC, NUS-WIDE), comparing their performance with (a) basic neural architectures and (b) neural architectures combined with Markov networks equipped with advanced inference and learning techniques. Our results demonstrate the superiority of our new DDN methods over the two competing approaches.

cs.LG↗
arXiv2024

Segment Every Out-of-Distribution Object

Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safety-critical applications. Existing methods rely on anomaly scores, but choosing a suitable threshold for generating masks presents difficulties and can lead to fragmentation and inaccuracy. This paper introduces a method to convert anomaly \textbf{S}core \textbf{T}o segmentation \textbf{M}ask, called S2M, a simple and effective framework for OoD detection in semantic segmentation. Unlike assigning anomaly scores to pixels, S2M directly segments the entire OoD object. By transforming anomaly scores into prompts for a promptable segmentation model, S2M eliminates the need for threshold selection. Extensive experiments demonstrate that S2M outperforms the state-of-the-art by approximately 20% in IoU and 40% in mean F1 score, on average, across various benchmarks including Fishyscapes, Segment-Me-If-You-Can, and RoadAnomaly datasets.

cs.CV↗
arXiv2024

Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis

Count data naturally arise in many fields, such as finance, neuroscience, and epidemiology, and discovering causal structure among count data is a crucial task in various scientific and industrial scenarios. One of the most common characteristics of count data is the inherent branching structure described by a binomial thinning operator and an independent Poisson distribution that captures both branching and noise. For instance, in a population count scenario, mortality and immigration contribute to the count, where survival follows a Bernoulli distribution, and immigration follows a Poisson distribution. However, causal discovery from such data is challenging due to the non-identifiability issue: a single causal pair is Markov equivalent, i.e., $X\rightarrow Y$ and $Y\rightarrow X$ are distributed equivalent. Fortunately, in this work, we found that the causal order from $X$ to its child $Y$ is identifiable if $X$ is a root vertex and has at least two directed paths to $Y$, or the ancestor of $X$ with the most directed path to $X$ has a directed path to $Y$ without passing $X$. Specifically, we propose a Poisson Branching Structure Causal Model (PB-SCM) and perform a path analysis on PB-SCM using high-order cumulants. Theoretical results establish the connection between the path and cumulant and demonstrate that the path information can be obtained from the cumulant. With the path information, causal order is identifiable under some graphical conditions. A practical algorithm for learning causal structure under PB-SCM is proposed and the experiments demonstrate and verify the effectiveness of the proposed method.

stat.ML↗
arXiv2024

On Large-Scale Multiple Testing Over Networks: An Asymptotic Approach

This work concerns developing communication- and computation-efficient methods for large-scale multiple testing over networks, which is of interest to many practical applications. We take an asymptotic approach and propose two methods, proportion-matching and greedy aggregation, tailored to distributed settings. The proportion-matching method achieves the global BH performance yet only requires a one-shot communication of the (estimated) proportion of true null hypotheses as well as the number of p-values at each node. By focusing on the asymptotic optimal power, we go beyond the BH procedure by providing an explicit characterization of the asymptotic optimal solution. This leads to the greedy aggregation method that effectively approximates the optimal rejection regions at each node, while computation efficiency comes from the greedy-type approach naturally. Moreover, for both methods, we provide the rate of convergence for both the FDR and power. Extensive numerical results over a variety of challenging settings are provided to support our theoretical findings.

stat.ME↗
arXiv2024

SCENEREPLICA: Benchmarking Real-World Robot Manipulation by Creating Replicable Scenes

We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on pick-and-place. Our benchmark uses the YCB objects, a commonly used dataset in the robotics community, to ensure that our results are comparable to other studies. Additionally, the benchmark is designed to be easily reproducible in the real world, making it accessible to researchers and practitioners. We also provide our experimental results and analyzes for model-based and model-free 6D robotic grasping on the benchmark, where representative algorithms are evaluated for object perception, grasping planning, and motion planning. We believe that our benchmark will be a valuable tool for advancing the field of robot manipulation. By providing a standardized evaluation framework, researchers can more easily compare different techniques and algorithms, leading to faster progress in developing robot manipulation methods.

cs.RO↗
arXiv2024

RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features

In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects. Previous works perform unseen object instance segmentation (UOIS) by training deep neural networks on large-scale data to learn RGB/RGB-D feature embeddings, where cluttered environments often result in inaccurate segmentations. We build upon these methods and introduce a novel approach to correct inaccurate segmentation, such as under-segmentation, of static image-based UOIS masks by using robot interaction and a designed body frame-invariant feature. We demonstrate that the relative linear and rotational velocities of frames randomly attached to rigid bodies due to robot interactions can be used to identify objects and accumulate corrected object-level segmentation masks. By introducing motion to regions of segmentation uncertainty, we are able to drastically improve segmentation accuracy in an uncertainty-driven manner with minimal, non-disruptive interactions (ca. 2-3 per scene). We demonstrate the effectiveness of our proposed interactive perception pipeline in accurately segmenting cluttered scenes by achieving an average object segmentation accuracy rate of 80.7%, an increase of 28.2% when compared with other state-of-the-art UOIS methods.

cs.CV↗
arXiv2024

Experimentally ruling out joint reality based on operational completeness

Whether the observables of a physical system admit real values is of fundamental importance to a deep understanding of nature. In this work, we report a device-independent experiment to confirm that the joint reality of two observables on a single two-level system is incompatible with the assumption of operational completeness, which is strictly weaker than that of preparation noncontextuality. We implement two observables on a trapped $^{171}{\rm Yb}^{+}$ ion to test this incompatibility via violation of certain inequalities derived from both linear and nonlinear criteria. Moreover, by introducing a highly controllable dephasing channel, we show that the nonlinear criterion is more robust against noise. Our results push the fundamental limit to delineate the quantum-classical boundary and pave the way for exploring relevant problems in other scenarios.

quant-ph↗
arXiv2024

Filtering one-way Einstein-Podolsky-Rosen steering

Einstein-Podolsky-Rosen (EPR) steering, a fundamental concept of quantum nonlocality, describes one observer's capability to remotely affect another distant observer's state by local measurements. Unlike quantum entanglement and Bell nonlocality, both associated with the symmetric quantum correlation, EPR steering depicts the unique asymmetric property of quantum nonlocality. With the local filter operation in which some system components are discarded, quantum nonlocality can be distilled to enhance the nonlocal correlation, and even the hidden nonlocality can be activated. However, asymmetric quantum nonlocality in the filter operation still lacks a well-rounded investigation, especially considering the discarded parts where quantum nonlocal correlations may still exist with probabilities. Here, in both theory and experiment, we investigate the effect of reusing the discarded particles from local filter. We observe all configurations of EPR steering simultaneously and other intriguing evolution of asymmetric quantum nonlocality, such as reversing the direction of one-way EPR steering. This work provides a perspective to answer "What is the essential role of utilizing quantum steering as a resource?", and demonstrates a practical toolbox for manipulating asymmetric quantum systems with significant potential applications in quantum information tasks.

quant-ph↗
arXiv2023

Communication-Efficient Distribution-Free Inference Over Networks

Consider a star network where each local node possesses a set of test statistics that exhibit a symmetric distribution around zero when their corresponding null hypothesis is true. This paper investigates statistical inference problems in networks concerning the aggregation of this general type of statistics and global error rate control under communication constraints in various scenarios. The study proposes communication-efficient algorithms that are built on established non-parametric methods, such as the Wilcoxon and sign tests, as well as modern inference methods such as the Benjamini-Hochberg (BH) and Barber-Candes (BC) procedures, coupled with sampling and quantization operations. The proposed methods are evaluated through extensive simulation studies.

stat.ME↗
arXiv2023

Variable Selection with the Knockoffs: Composite Null Hypotheses

The fixed-X knockoff filter is a flexible framework for variable selection with false discovery rate (FDR) control in linear models with arbitrary design matrices (of full column rank) and it allows for finite-sample selective inference via the Lasso estimates. In this paper, we extend the theory of the knockoff procedure to tests with composite null hypotheses, which are usually more relevant to real-world problems. The main technical challenge lies in handling composite nulls in tandem with dependent features from arbitrary designs. We develop two methods for composite inference with the knockoffs, namely, shifted ordinary least-squares (S-OLS) and feature-response product perturbation (FRPP), building on new structural properties of test statistics under composite nulls. We also propose two heuristic variants of S-OLS method that outperform the celebrated Benjamini-Hochberg (BH) procedure for composite nulls, which serves as a heuristic baseline under dependent test statistics. Finally, we analyze the loss in FDR when the original knockoff procedure is naively applied on composite tests.

math.ST↗
arXiv2023

Correlation-pattern-based Continuous-variable Entanglement Detection through Neural Networks

Entanglement in continuous-variable non-Gaussian states provides irreplaceable advantages in many quantum information tasks. However, the sheer amount of information in such states grows exponentially and makes a full characterization impossible. Here, we develop a neural network that allows us to use correlation patterns to effectively detect continuous-variable entanglement through homodyne detection. Using a recently defined stellar hierarchy to rank the states used for training, our algorithm works not only on any kind of Gaussian state but also on a whole class of experimentally achievable non-Gaussian states, including photon-subtracted states. With the same limited amount of data, our method provides higher accuracy than usual methods to detect entanglement based on maximum-likelihood tomography. Moreover, in order to visualize the effect of the neural network, we employ a dimension reduction algorithm on the patterns. This shows that a clear boundary appears between the entangled states and others after the neural network processing. In addition, these techniques allow us to compare different entanglement witnesses and understand their working. Our findings provide a new approach for experimental detection of continuous-variable quantum correlations without resorting to a full tomography of the state and confirm the exciting potential of neural networks in quantum information processing.

quant-ph↗
arXiv2023

Learning Invariant Representations under General Interventions on the Response

It has become increasingly common nowadays to collect observations of feature and response pairs from different environments. As a consequence, one has to apply learned predictors to data with a different distribution due to distribution shifts. One principled approach is to adopt the structural causal models to describe training and test models, following the invariance principle which says that the conditional distribution of the response given its predictors remains the same across environments. However, this principle might be violated in practical settings when the response is intervened. A natural question is whether it is still possible to identify other forms of invariance to facilitate prediction in unseen environments. To shed light on this challenging scenario, we focus on linear structural causal models (SCMs) and introduce invariant matching property (IMP), an explicit relation to capture interventions through an additional feature, leading to an alternative form of invariance that enables a unified treatment of general interventions on the response as well as the predictors. We analyze the asymptotic generalization errors of our method under both the discrete and continuous environment settings, where the continuous case is handled by relating it to the semiparametric varying coefficient models. We present algorithms that show competitive performance compared to existing methods over various experimental settings including a COVID dataset.

stat.ME↗
arXiv2023

Mean Shift Mask Transformer for Unseen Object Instance Segmentation

Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for image segmentation tasks. However, the traditional mean shift clustering algorithm is not differentiable, making it difficult to integrate it into an end-to-end neural network training framework. In this work, we propose the Mean Shift Mask Transformer (MSMFormer), a new transformer architecture that simulates the von Mises-Fisher (vMF) mean shift clustering algorithm, allowing for the joint training and inference of both the feature extractor and the clustering. Its central component is a hypersphere attention mechanism, which updates object queries on a hypersphere. To illustrate the effectiveness of our method, we apply MSMFormer to unseen object instance segmentation. Our experiments show that MSMFormer achieves competitive performance compared to state-of-the-art methods for unseen object instance segmentation. The project page, appendix, video, and code are available at https://irvlutd.github.io/MSMFormer

cs.CV↗
arXiv2023

Certification of non-Gaussian Einstein-Podolsky-Rosen Steering

Non-Gaussian quantum states are a known necessary resource for reaching a quantum advantage and for violating Bell inequalities in continuous variable systems. As one kind of manifestation of quantum correlations, Einstein-Podolsky-Rosen (EPR) steering enables verification of shared entanglement even when one of the subsystems is not characterized. However, how to detect and classify such an effect for non-Gaussian states is far from being well understood. Here, we present an efficient non-Gaussian steering criterion based on the high-order observables and conduct a systematic investigation into the hierarchy of non-Gaussian steering criteria. Moreover, we apply our criterion to three experimentally-relevant non-Gaussian states under realistic conditions and, in particular, propose a feasible scheme to create multi-component cat states with tunable size by performing a suitable high-order quadrature measurement on the steering party. Our work reveals the fundamental characteristics of non-Gaussianity and quantum correlations, and offers new insights to explore their applications in quantum information processing.

quant-ph↗
arXiv2023

Error Probability Bounds for Invariant Causal Prediction via Multiple Access Channels

We consider the problem of lower bounding the error probability under the invariant causal prediction (ICP) framework. To this end, we examine and draw connections between ICP and the zero-rate Gaussian multiple access channel by first proposing a variant of the original invariant prediction assumption, and then considering a special case of the Gaussian multiple access channel where a codebook is shared between an unknown number of senders. This connection allows us to develop three types of lower bounds on the error probability, each with different assumptions and constraints, leveraging techniques for multiple access channels. The proposed bounds are evaluated with respect to existing causal discovery methods as well as a proposed heuristic method based on minimum distance decoding.

cs.IT↗
arXiv2023

Identifying Direct Causes using Intervened Target Variable

Identifying the direct causes or causal parents of a target variable is crucial for scientific discovery. Focusing on linear models, the invariant prediction framework was built upon the invariance principle, namely, the conditional distribution of the target variable given its causal parents is invariant across multiple environments or experimental conditions. However, their identifiability results for causal parents can be restrictive with respect to the underlying graph structure and the experimental conditions for generating interventional data. Motivated by a recent alternative formulation of invariance, called the invariant matching property, we establish identifiability results under relatively mild assumptions, which leads to a simple yet effective procedure for identifying causal parents. We demonstrate the performance of the proposed method over various synthetic and real datasets.

stat.ME↗
arXiv2023

Randomness Certification from Multipartite Quantum Steering for Arbitrary Dimensional Systems

Entanglement in bipartite systems has been applied for the generation of secure random numbers, which are playing an important role in cryptography or scientific numerical simulations. Here, we propose to use multipartite entanglement distributed between trusted and untrusted parties for generating randomness of arbitrary dimensional systems. We show that the distributed structure of several parties leads to additional protection against possible attacks by an eavesdropper, resulting in more secure randomness generated than in the corresponding bipartite scenario. Especially, randomness can be certified in the group of untrusted parties, even there is no randomness exists in either of them individually. We prove that the necessary and sufficient resource for quantum randomness in this scenario is multipartite quantum steering when two measurement settings are performed on the untrusted parties. However, the sufficiency no longer holds with more measurement settings. Finally, we apply our analysis to some experimentally realized states and show that more randomness can be extracted in comparison to the existing analysis.

quant-ph↗
arXiv2023

Novel deep learning methods for 3D flow field segmentation and classification

Flow field segmentation and classification help researchers to understand vortex structure and thus turbulent flow. Existing deep learning methods mainly based on global information and focused on 2D circumstance. Based on flow field theory, we propose novel flow field segmentation and classification deep learning methods in three-dimensional space. We construct segmentation criterion based on local velocity information and classification criterion based on the relationship between local vorticity and vortex wake, to identify vortex structure in 3D flow field, and further classify the type of vortex wakes accurately and rapidly. Simulation experiment results showed that, compared with existing methods, our segmentation method can identify the vortex area more accurately, while the time consumption is reduced more than 50%; our classification method can reduce the time consumption by more than 90% while maintaining the same classification accuracy level.

cs.CV↗