arXiv subjects

Yang Jiao

Publications and source records attributed to Yang Jiao.

At least 73 records · Page 4Linked to original sources

arXiv2024

Methodology and Real-World Applications of Dynamic Uncertain Causality Graph for Clinical Diagnosis with Explainability and Invariance

AI-aided clinical diagnosis is desired in medical care. Existing deep learning models lack explainability and mainly focus on image analysis. The recently developed Dynamic Uncertain Causality Graph (DUCG) approach is causality-driven, explainable, and invariant across different application scenarios, without problems of data collection, labeling, fitting, privacy, bias, generalization, high cost and high energy consumption. Through close collaboration between clinical experts and DUCG technicians, 46 DUCG models covering 54 chief complaints were constructed. Over 1,000 diseases can be diagnosed without triage. Before being applied in real-world, the 46 DUCG models were retrospectively verified by third-party hospitals. The verified diagnostic precisions were no less than 95%, in which the diagnostic precision for every disease including uncommon ones was no less than 80%. After verifications, the 46 DUCG models were applied in the real-world in China. Over one million real diagnosis cases have been performed, with only 17 incorrect diagnoses identified. Due to DUCG's transparency, the mistakes causing the incorrect diagnoses were found and corrected. The diagnostic abilities of the clinicians who applied DUCG frequently were improved significantly. Following the introduction to the earlier presented DUCG methodology, the recommendation algorithm for potential medical checks is presented and the key idea of DUCG is extracted.

cs.AI↗

arXiv2024

Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models

Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend is to further extend and enhance the perception capabilities of LMMs. The current methods follow the paradigm of adapting the visual task outputs to the format of the language model, which is the main component of a LMM. This adaptation leads to convenient development of such LMMs with minimal modifications, however, it overlooks the intrinsic characteristics of diverse visual tasks and hinders the learning of perception capabilities. To address this issue, we propose a novel LMM architecture named Lumen, a Large multimodal model with versatile vision-centric capability enhancement. We decouple the LMM's learning of perception capabilities into task-agnostic and task-specific stages. Lumen first promotes fine-grained vision-language concept alignment, which is the fundamental capability for various visual tasks. Thus the output of the task-agnostic stage is a shared representation for all the tasks we address in this paper. Then the task-specific decoding is carried out by flexibly routing the shared representation to lightweight task decoders with negligible training efforts. Comprehensive experimental results on a series of vision-centric and VQA benchmarks indicate that our Lumen model not only achieves or surpasses the performance of existing LMM-based approaches in a range of vision-centric tasks while maintaining general visual understanding and instruction following capabilities. The code will be released at https://github.com/SxJyJay/Lumen.

cs.CV↗

arXiv2024

The Pogorelov estimates for degenerate curvature equations

We establish the Pogorelov type estimates for degenerate prescribed k-curvature equations as well as k-Hessian equations. Furthermore,we investigate the interior C1,1 regularity of the solutions for Dirichlet problems. These techniques also enable us to improve the existence theorem for an asymptotic Plateau type problem in hyperbolic space.

math.AP↗

arXiv2024

Detection of Problem Gambling with Less Features Using Machine Learning Methods

Analytic features in gambling study are performed based on the amount of data monitoring on user daily actions. While performing the detection of problem gambling, existing datasets provide relatively rich analytic features for building machine learning based model. However, considering the complexity and cost of collecting the analytic features in real applications, conducting precise detection with less features will tremendously reduce the cost of data collection. In this study, we propose a deep neural networks PGN4 that performs well when using limited analytic features. Through the experiment on two datasets, we discover that PGN4 only experiences a mere performance drop when cutting 102 features to 5 features. Besides, we find the commonality within the top 5 features from two datasets.

cs.LG↗

arXiv2024

Parallel Self-assembly for a Multi-USV System on Water Surface with Obstacles

Parallel self-assembly is an efficient approach to accelerate the assembly process for modular robots. However, these approaches cannot accommodate complicated environments with obstacles, which restricts their applications. This paper considers the surrounding stationary obstacles and proposes a parallel self-assembly planning algorithm named SAPOA. With this algorithm, modular robots can avoid immovable obstacles when performing docking actions, which adapts the parallel self-assembly process to complex scenes. To validate the efficiency and scalability, we have designed 25 distinct grid maps with different obstacle configurations to simulate the algorithm. From the results compared to the existing parallel self-assembly algorithms, our algorithm shows a significantly higher success rate, which is more than 80%. For verification in real-world applications, a multi-agent hardware testbed system is developed. The algorithm is successfully deployed on four omnidirectional unmanned surface vehicles, CuBoats. The navigation strategy that translates the discrete planner, SAPOA, to the continuous controller on the CuBoats is presented. The algorithm's feasibility and flexibility were demonstrated through successful self-assembly experiments on 5 maps with varying obstacle configurations.

cs.RO↗

arXiv2024

From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios

The precise recognition of food categories plays a pivotal role for intelligent health management, attracting significant research attention in recent years. Prominent benchmarks, such as Food-101 and VIREO Food-172, provide abundant food image resources that catalyze the prosperity of research in this field. Nevertheless, these datasets are well-curated from canteen scenarios and thus deviate from food appearances in daily life. This discrepancy poses great challenges in effectively transferring classifiers trained on these canteen datasets to broader daily-life scenarios encountered by humans. Toward this end, we present two new benchmarks, namely DailyFood-172 and DailyFood-16, specifically designed to curate food images from everyday meals. These two datasets are used to evaluate the transferability of approaches from the well-curated food image domain to the everyday-life food image domain. In addition, we also propose a simple yet effective baseline method named Multi-Cluster Reference Learning (MCRL) to tackle the aforementioned domain gap. MCRL is motivated by the observation that food images in daily-life scenarios exhibit greater intra-class appearance variance compared with those in well-curated benchmarks. Notably, MCRL can be seamlessly coupled with existing approaches, yielding non-trivial performance enhancements. We hope our new benchmarks can inspire the community to explore the transferability of food recognition models trained on well-curated datasets toward practical real-life applications.

cs.CV↗

arXiv2024

NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario

We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. Compared to traditional VQA tasks, VQA in autonomous driving scenario presents more challenges. Firstly, the raw visual data are multi-modal, including images and point clouds captured by camera and LiDAR, respectively. Secondly, the data are multi-frame due to the continuous, real-time acquisition. Thirdly, the outdoor scenes exhibit both moving foreground and static background. Existing VQA benchmarks fail to adequately address these complexities. To bridge this gap, we propose NuScenes-QA, the first benchmark for VQA in the autonomous driving scenario, encompassing 34K visual scenes and 460K question-answer pairs. Specifically, we leverage existing 3D detection annotations to generate scene graphs and design question templates manually. Subsequently, the question-answer pairs are generated programmatically based on these templates. Comprehensive statistics prove that our NuScenes-QA is a balanced large-scale benchmark with diverse question formats. Built upon it, we develop a series of baselines that employ advanced 3D detection and VQA techniques. Our extensive experiments highlight the challenges posed by this new task. Codes and dataset are available at https://github.com/qiantianwen/NuScenes-QA.

cs.CV↗

arXiv2024

Parallel Self-assembly for Modular USVs with Diverse Docking Mechanism Layouts

Self-assembly enables multi-robot systems to merge diverse capabilities and accomplish tasks beyond the reach of individual robots. Incorporating varied docking mechanisms layouts (DMLs) can enhance robot versatility or reduce costs. However, assembling multiple heterogeneous robots with diverse DMLs is still a research gap. This paper addresses this problem by introducing CuBoat, an omnidirectional unmanned surface vehicle (USV). CuBoat can be equipped with or without docking systems on its four sides to emulate heterogeneous robots. We implement a multi-robot system based on multiple CuBoats. To enhance maneuverability, a linear active disturbance rejection control (LADRC) scheme is proposed. Additionally, we present a generalized parallel self-assembly planning algorithm for efficient assembly among CuBoats with different DMLs. Validation is conducted through simulation within 2 scenarios across 4 distinct maps, demonstrating the performance of the self-assembly planning algorithm. Moreover, trajectory tracking tests confirm the effectiveness of the LADRC controller. Self-assembly experiments on 5 maps with different target structures affirm the algorithm's feasibility and generality. This study advances robotic self-assembly, enabling multi-robot systems to collaboratively tackle complex tasks beyond the capabilities of individual robots.

cs.RO↗

arXiv2024

Provably Convergent Federated Trilevel Learning

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach; 2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes $μ$-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed $μ$-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the $μ$-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain $ε$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{ε^2})$. Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80$\%$.

cs.LG↗

arXiv2023

Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization

While providing machine learning model as a service to process users' inference requests, online applications can periodically upgrade the model utilizing newly collected data. Federated learning (FL) is beneficial for enabling the training of models across distributed clients while keeping the data locally. However, existing work has overlooked the coexistence of model training and inference under clients' limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients. Such an optimization faces several challenges. The first challenge is to characterize the clients' inference performance when clients may partially participate in FL. To resolve this challenge, we introduce a new notion of age of model (AoM) to quantify client-side model freshness, based on which we use FL's global model convergence error as an approximate measure of inference performance. The second challenge is the tight coupling among clients' decisions, including participation probability in FL, model download probability, and service rates. Toward the challenges, we propose an online problem approximation to reduce the problem complexity and optimize the resources to balance the needs of model training and inference. Experimental results demonstrate that the proposed algorithm improves the average inference accuracy by up to 12%.

cs.DC↗

arXiv2023

Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning

Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images. However, existing approaches exhaustively predict depths for every pixel without prioritizing objects, which are precisely the entities requiring detection in the 3D space. To this end, we propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector. First, a category-specific structural priors mining approach is proposed for enhancing the efficacy of monocular depth generation. Besides, a self-boosting learning strategy is further proposed to encourage the model to place more emphasis on challenging objects in computation-expensive temporal stereo matching. Together they provide advanced depth estimation results for high-quality BEV features construction, benefiting the ultimate 3D detection. The proposed method achieves state-of-the-art performances on the challenging nuScenes benchmark, and extensive experimental results demonstrate the effectiveness of our designs.

cs.CV↗

arXiv2023

Hyperuniformity of Maximally Random Jammed Packings of Hyperspheres Across Spatial Dimensions

The maximally random jammed (MRJ) state is the most random configuration of strictly jammed (mechanically rigid) nonoverlapping objects. MRJ packings are hyperuniform, meaning their long-wavelength density fluctuations are anomalously suppressed compared to typical disordered systems, i.e., their structure factors $S(\mathbf{k})$ tend to zero as the wavenumber $|\mathbf{k}|$ tends to zero. Here, we show that generating high-quality strictly jammed states for space dimensions $d = 3,4,$ and $5$ is of paramount importance in ensuring hyperuniformity and extracting precise values of the hyperuniformity exponent $α> 0$ for MRJ states, defined by the power-law behavior of $S(\mathbf{k})\sim|\mathbf{k}|^α$ in the limit $|\mathbf{k}|\rightarrow0$. Moreover, we show that for fixed $d$ it is more difficult to ensure jamming as the particle number $N$ increases, which results in packings that are nonhyperuniform. Free-volume theory arguments suggest that the ideal MRJ state does not contain rattlers, which act as defects in numerically generated packings. As $d$ increases, we find that the fraction of rattlers decreases substantially. Our analysis of the largest truly jammed packings suggests that the ideal MRJ packings for all dimensions $d\geq3$ are hyperuniform with $α= d - 2$, implying the packings become more hyperuniform as $d$ increases. The differences in $α$ between MRJ packings and recently proposed Manna-class random close packed (RCP) states, which were reported to have $α= 0.25$ in $d=3$ and be nonhyperuniform ($α= 0$) for $d = 4$ and $d = 5$, demonstrate the vivid distinctions between the large-scale structure of RCP and MRJ states in these dimensions. Our work clarifies the importance of the link between true jamming and hyperuniformity and motivates the development of an algorithm to produce rattler-free three-dimensional MRJ packings.

cond-mat.soft↗

arXiv2023

Vibrational Properties of One-Dimensional Disordered Hyperuniform Atomic Chains

Disorder hyperuniformity (DHU) is a recently discovered exotic state of many-body systems that possess a hidden order in between that of a perfect crystal and a completely disordered system. Recently, this novel DHU state has been observed in a number of quantum materials including amorphous 2D graphene and silica, which are endowed with unexpected electronic transport properties. Here, we numerically investigate 1D atomic chain models, including perfect crystalline, disordered hyperuniform as well as randomly perturbed atom packing configurations to obtain a quantitative understanding of how the unique DHU disorder affects the vibrational properties of these low-dimensional materials. We find that the DHU chains possess lower cohesive energies compared to the randomly perturbed chains, implying their potential reliability in experiments. Our inverse partition ratio (IPR) calculations indicate that the DHU chains can support fully delocalized states just like perfect crystalline chains over a wide range of frequencies, i.e., $ω\in (0, 100)$ cm$^{-1}$, suggesting superior phonon transport behaviors within these frequencies, which was traditionally considered impossible in disordered systems. Interestingly, we observe the emergence of a group of highly localized states associated with $ω\sim 200$ cm$^{-1}$, which is characterized by a significant peak in the IPR and a peak in phonon density of states at the corresponding frequency, and is potentially useful for decoupling electron and phonon degrees of freedom. These unique properties of DHU chains have implications in the design and engineering of novel DHU quantum materials for thermal and phononic applications.

cond-mat.mtrl-sci↗

arXiv2023

Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments

Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years. Among the existing approaches for ONL2R, a natural modeling architecture is the multi-armed bandit framework coupled with the position-based click model. However, developing efficient online learning policies for MAB-based ONL2R with position-based click models is highly challenging due to the combinatorial nature of the problem, and partial observability in the position-based click model. To date, results in MAB-based ONL2R with position-based click models remain rather limited, which motivates us to fill this gap in this work. Our main contributions in this work are threefold: i) We propose the first general MAB framework that captures all key ingredients of ONL2R with position-based click models. Our model considers personalized and equal treatments in ONL2R ranking recommendations, both of which are widely used in practice; ii) Based on the above analytical framework, we develop two unified greed- and UCB-based policies called GreedyRank and UCBRank, each of which can be applied to personalized and equal ranking treatments; and iii) We show that both GreedyRank and UCBRank enjoy $O(\sqrt{t}\ln t)$ and $O(\sqrt{t\ln t})$ anytime sublinear regret for personalized and equal treatment, respectively. For the fundamentally hard equal ranking treatment, we identify classes of collective utility functions and their associated sufficient conditions under which $O(\sqrt{t}\ln t)$ and $O(\sqrt{t\ln t})$ anytime sublinear regrets are still achievable for GreedyRank and UCBRank, respectively. Our numerical experiments also verify our theoretical results and demonstrate the efficiency of GreedyRank and UCBRank in seeking the optimal action under various problem settings.

cs.LG↗

arXiv2023

Sweeping process approach to stress analysis in elastoplastic Lattice Springs Models with applications to Hyperuniform Network Materials

Disordered network materials abound in both nature and synthetic situations while rigorous analysis of their nonlinear mechanical behaviors still is very challenging. The purpose of this paper is to connect the mathematical framework of sweeping process originally proposed by Moreau to a generic class of Lattice Spring Models with plasticity phenomenon. We explicitly construct a sweeping process and provide numerical schemes to find the evolution of stresses in a Lattice Spring Model with infinitesimal strains and perfect plasticity. In particular, we develop a highly efficient "leapfrog" computational framework that allow ones to rigorously track the progression of plastic events in the system based on the sweeping process theory. The utility of our framework is demonstrated by analyzing the elastoplastic stresses in a novel class of disordered network materials exhibiting the property of hyperuniformity, in which the infinite wave-length density fluctuations associated with the distribution of network nodes are completely suppressed. We find enhanced mechanical properties such as increasing stiffness, yield strength and tensile strength as the degree of hyperuniformity of the material system increases. Our results have implications for optimal network material design and our event-based framework can be readily generalized for nonlinear stress analysis of other heterogeneous material systems. We also include some insights to the model from the viewpoint of the rigidity theory.

math.OC↗

arXiv2023

"Can You Move It?": The Design and Evaluation of Moving VR Shots in Sport Broadcast

Virtual Reality (VR) broadcasting has seen widespread adoption in major sports events, attributed to its ability to generate a sense of presence, curiosity, and excitement among viewers. However, we have noticed that still shots reveal a limitation in the movement of VR cameras and hinder the VR viewing experience in current VR sports broadcasts. This paper aims to bridge this gap by engaging in a quantitative user analysis to explore the design and impact of dynamic VR shots on viewing experiences. We conducted two user studies in a digital hockey game twin environment and asked participants to evaluate their viewing experience through two questionnaires. Our findings suggested that the viewing experiences demonstrated no notable disparity between still and moving shots for single clips. However, when considering entire events, moving shots improved the viewer's immersive experience, with no notable increase in sickness compared to still shots. We further discuss the benefits of integrating moving shots into VR sports broadcasts and present a set of design considerations and potential improvements for future VR sports broadcasting.

cs.HC↗

arXiv2023

Morphological entropy encodes cellular migration strategies on multiple length scales

Cell migration is crucial to many physiological and pathological processes. During migration, a cell adapts its morphology, including the overall morphology and nucleus morphology, in response to various cues in complex microenvironments, e.g. topotaxis and chemotaxis. Thus, cellular morphology dynamics can encode migration strategies based on which various migration mechanisms can be inferred. However, how to decipher cell migration mechanisms encoded in the morphology dynamics remains a challenging problem. Here we introduce a novel universal metric, namely cell morphological entropy (CME), by combining parametric morphological analysis with Shannon entropy. The utility of CME, which accurately quantifies the complex cellular morphology on multiple length scales through the deviation from the perfect circular shape, is demonstrated using a variety of normal and tumorous cell lines in distinct in vitro microenvironments. Our results reveal that 1) the effects of geometric constraints on cell nucleus, 2) the emerging interplays of MCF-10A cells migrating on collagen gel, and 3) the critical transition of tumor spheroid from proliferation to invasion. The analysis indicates that the CME offers a physically interpretable and efficient tool to quantify morphology on multiple length scales in real-time, which provides more insights into cell migration, and further contributing to the understanding of the diverse behavioral modes as well as collective cell motility in more complex microenvironment.

physics.bio-ph↗

arXiv2023

Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding

Recently, one-stage visual grounders attract high attention due to their comparable accuracy but significantly higher efficiency than two-stage grounders. However, inter-object relation modeling has not been well studied for one-stage grounders. Inter-object relationship modeling, though important, is not necessarily performed among all objects, as only part of them are related to the text query and may confuse the model. We call these objects suspected objects. However, exploring their relationships in the one-stage paradigm is non-trivial because: First, no object proposals are available as the basis on which to select suspected objects and perform relationship modeling. Second, suspected objects are more confusing than others, as they may share similar semantics, be entangled with certain relationships, etc, and thereby more easily mislead the model prediction. Toward this end, we propose a Suspected Object Transformation mechanism (SOT), which can be seamlessly integrated into existing CNN and Transformer-based one-stage visual grounders to encourage the target object selection among the suspected ones. Suspected objects are dynamically discovered from a learned activation map adapted to the model current discrimination ability during training. Afterward, on top of suspected objects, a Keyword-Aware Discrimination module (KAD) and an Exploration by Random Connection strategy (ERC) are concurrently proposed to help the model rethink its initial prediction. On the one hand, KAD leverages keywords contributing high to suspected object discrimination. On the other hand, ERC allows the model to seek the correct object instead of being trapped in a situation that always exploits the current false prediction. Extensive experiments demonstrate the effectiveness of our proposed method.

cs.CV↗