arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 577 records · Page 32Linked to original sources

arXiv2022

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

Objectives: To develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN. Methods: A total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was built on the attention-based multiple instance-learning (AMIL) framework to predict ALN status utilizing the DL features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) were analyzed to evaluate our model. Results: The best-performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nucleus features including density ($p$ = 0.015), circumference ($p$ = 0.009), circularity ($p$ = 0.010), and orientation ($p$ = 0.012). Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC. The codes and dataset are available at https://github.com/bupt-ai-cz/BALNMP

eess.IV↗

arXiv2022

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks, and also limited variations in environmental conditions and viewpoints. To address these limitations, we create a large and diverse dataset, Animal Kingdom, that provides multiple annotated tasks to enable a more thorough understanding of natural animal behaviors. The wild animal footages used in our dataset record different times of the day in extensive range of environments containing variations in backgrounds, viewpoints, illumination and weather conditions. More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes. Such a challenging and comprehensive dataset shall be able to facilitate the community to develop, adapt, and evaluate various types of advanced methods for animal behavior analysis. Moreover, we propose a Collaborative Action Recognition (CARe) model that learns general and specific features for action recognition with unseen new animals. This method achieves promising performance in our experiments. Our dataset can be found at https://sutdcv.github.io/Animal-Kingdom.

cs.CV↗

arXiv2022

Sufficient Conditions for Robust Probabilistic Reach-Avoid-Stay Specifications using Stochastic Lyapunov-Barrier Functions

Stability and safety are crucial in safety-critical control of dynamical systems. The reach-avoid-stay objectives for deterministic dynamical systems can be effectively handled by formal methods as well as Lyapunov methods with soundness and approximate completeness guarantees. However, for continuous-time stochastic dynamical systems, probabilistic reach-avoid-stay problems are viewed as challenging tasks. Motivated by the recent surge of applications in characterizing safety-critical properties using Lyapunov-barrier functions, we aim to provide a stochastic version for the probabilistic reach-avoid-stay problems in consideration of robustness. To this end, we first establish a connection between stochastic stability with safety constraints and reach-avoid-stay specifications. We then prove that stochastic Lyapunov-barrier functions provide sufficient conditions for the target objectives. We apply Lyapunovbarrier conditions in control synthesis for reach-avoid-stay specifications, and show its effectiveness in a case study.

math.DS↗

arXiv2022

Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach

Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) is a key technology component in the evolution towards cognitive radio (CR) in next-generation communication in which the accuracy of timing and frequency synchronization significantly impacts the overall system performance. In this paper, we propose a novel scheme leveraging extreme learning machine (ELM) to achieve high-precision synchronization. Specifically, exploiting the preamble signals with synchronization offsets, two ELMs are incorporated into a traditional MIMO-OFDM system to estimate both the residual symbol timing offset (RSTO) and the residual carrier frequency offset (RCFO). The simulation results show that the performance of the proposed ELM-based synchronization scheme is superior to the traditional method under both additive white Gaussian noise (AWGN) and frequency selective fading channels. Furthermore, comparing with the existing machine learning based techniques, the proposed method shows outstanding performance without the requirement of perfect channel state information (CSI) and prohibitive computational complexity. Finally, the proposed method is robust in terms of the choice of channel parameters (e.g., number of paths) and also in terms of "generalization ability" from a machine learning standpoint.

eess.SP↗

arXiv2022

Data-Driven Learning of Safety-Critical Control with Stochastic Control Barrier Functions

Control barrier functions are widely used to synthesize safety-critical controls. The existence of Gaussian-type noise may lead to unsafe actions and result in severe consequences. While studies are widely done in safety-critical control for stochastic systems, in many real-world applications, we do not have the knowledge of the stochastic component of the dynamics. In this paper, we study safety-critical control of stochastic systems with an unknown diffusion part and propose a data-driven method to handle these scenarios. More specifically, we propose a data-driven stochastic control barrier function (DDSCBF) framework and use supervised learning to learn the unknown stochastic dynamics via the DDSCBF scheme. Under some reasonable assumptions, we provide guarantees that the DDSCBF scheme can approximate the Itô derivative of the stochastic control barrier function (SCBF) under partially unknown dynamics using the universal approximation theorem. We also show that we can achieve the same safety guarantee using the DDSCBF scheme as with SCBF in previous work without requiring the knowledge of stochastic dynamics. We use two non-linear stochastic systems to validate our theory in simulations.

eess.SY↗

arXiv2022

GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation

Generating recommendations based on user-item interactions and user-user social relations is a common use case in web-based systems. These connections can be naturally represented as graph-structured data and thus utilizing graph neural networks (GNNs) for social recommendation has become a promising research direction. However, existing graph-based methods fails to consider the bias offsets of users (items). For example, a low rating from a fastidious user may not imply a negative attitude toward this item because the user tends to assign low ratings in common cases. Such statistics should be considered into the graph modeling procedure. While some past work considers the biases, we argue that these proposed methods only treat them as scalars and can not capture the complete bias information hidden in data. Besides, social connections between users should also be differentiable so that users with similar item preference would have more influence on each other. To this end, we propose Graph-Based Decentralized Collaborative Filtering for Social Recommendation (GDSRec). GDSRec treats the biases as vectors and fuses them into the process of learning user and item representations. The statistical bias offsets are captured by decentralized neighborhood aggregation while the social connection strength is defined according to the preference similarity and then incorporated into the model design. We conduct extensive experiments on two benchmark datasets to verify the effectiveness of the proposed model. Experimental results show that the proposed GDSRec achieves superior performance compared with state-of-the-art related baselines. Our implementations are available in \url{https://github.com/MEICRS/GDSRec}.

cs.IR↗

arXiv2022

Surface Representation for Point Clouds

Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present \textbf{RepSurf} (representative surfaces), a novel representation of point clouds to \textbf{explicitly} depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around \textbf{0.008M} number of parameters, \textbf{0.04G} FLOPs, and \textbf{1.12ms} inference time, our method achieves \textbf{94.7\%} (+0.5\%) on ModelNet40, and \textbf{84.6\%} (+1.8\%) on ScanObjectNN for classification, while \textbf{74.3\%} (+0.8\%) mIoU on S3DIS 6-fold, and \textbf{70.0\%} (+1.6\%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains \textbf{71.2\%} (+2.1\%) mAP$\mathit{_{25}}$, \textbf{54.8\%} (+2.0\%) mAP$\mathit{_{50}}$ on ScanNetV2, and \textbf{64.9\%} (+1.9\%) mAP$\mathit{_{25}}$, \textbf{47.7\%} (+2.5\%) mAP$\mathit{_{50}}$ on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at \url{https://github.com/hancyran/RepSurf}.

cs.CV↗

arXiv2022

Robustly Complete Finite-State Abstractions for Verification of Stochastic Systems

In this paper, we focus on discrete-time stochastic systems modelled by nonlinear stochastic difference equations and propose robust abstractions for verifying probabilistic linear temporal specifications. The current literature focuses on developing sound abstraction techniques for stochastic dynamics without perturbations. However, soundness thus far has only been shown for preserving the satisfaction probability of certain types of temporal-logic specification. We present constructive finite-state abstractions for verifying probabilistic satisfaction of general ω-regular linear-time properties of more general nonlinear stochastic systems. Instead of imposing stability assumptions, we analyze the probabilistic properties from the topological view of metrizable space of probability measures. Such abstractions are both sound and approximately complete. That is, given a concrete discrete-time stochastic system and an arbitrarily small L1-perturbation of this system, there exists a family of finite-state Markov chains whose set of satisfaction probabilities contains that of the original system and meanwhile is contained by that of the slightly perturbed system. A direct consequence is that, given a probabilistic linear-time specification, initializing within the winning/losing region of the abstraction system can guarantee a satisfaction/dissatisfaction for the original system. We make an interesting observation that, unlike the deterministic case, point-mass (Dirac) perturbations cannot fulfill the purpose of robust completeness.

math.PR↗

arXiv2022

Uncertainty Modeling for Out-of-Distribution Generalization

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Common methods often consider the feature statistics as deterministic values measured from the learned features and do not explicitly consider the uncertain statistics discrepancy caused by potential domain shifts during testing. In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training. Specifically, we hypothesize that the feature statistic, after considering the potential uncertainties, follows a multivariate Gaussian distribution. Hence, each feature statistic is no longer a deterministic value, but a probabilistic point with diverse distribution possibilities. With the uncertain feature statistics, the models can be trained to alleviate the domain perturbations and achieve better robustness against potential domain shifts. Our method can be readily integrated into networks without additional parameters. Extensive experiments demonstrate that our proposed method consistently improves the network generalization ability on multiple vision tasks, including image classification, semantic segmentation, and instance retrieval. The code can be available at https://github.com/lixiaotong97/DSU.

cs.CV↗

arXiv2022

A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems

This paper proposes a specification-guided framework for control of nonlinear systems with linear temporal logic (LTL) specifications. In contrast with well-known abstraction-based methods, the proposed framework directly characterizes the winning set, i.e., the set of initial conditions from which a given LTL formula can be realized, over the continuous state space of the system via a monotonic operator. Following this characterization, an algorithm is proposed to practically approximate the operator via an adaptive interval subdivision scheme, which yields a finite-memory control strategy. We show that the proposed algorithm is sound for full LTL specifications, and robustly complete for specifications recognizable by deterministic Büchi automata (DBA), the latter in the sense that control strategies can be found whenever the given specification can be satisfied with additional bounded disturbances. Without having to compute and store the abstraction and the resulting product system with the DBA, the proposed method is more memory efficient, which is demonstrated by complexity analysis and performance tests. A pre-processing stage is also devised to reduce computational cost via a decomposition of the specification. We show that the proposed method can effectively solve real-world control problems such as jet engine compressor control and motion planning for manipulators and mobile robots.

eess.SY↗

arXiv2022

A Piecewise Learning Framework for Control of Unknown Nonlinear Systems with Stability Guarantees

We propose a piecewise learning framework for controlling nonlinear systems with unknown dynamics. While model-based reinforcement learning techniques in terms of some basis functions are well known in the literature, when it comes to more complex dynamics, only a local approximation of the model can be obtained using a limited number of bases. The complexity of the identifier and the controller can be considerably high if obtaining an approximation over a larger domain is desired. To overcome this limitation, we propose a general piecewise nonlinear framework where each piece is responsible for locally learning and controlling over some region of the domain. We obtain rigorous uncertainty bounds for the learned piecewise models. The piecewise affine (PWA) model is then studied as a special case, for which we propose an optimization-based verification technique for stability analysis of the closed-loop system. Accordingly, given a time-discretization of the learned {PWA} system, we iteratively search for a common piecewise Lyapunov function in a set of positive definite functions, where a non-monotonic convergence is allowed. This Lyapunov candidate is verified on the uncertain system to either provide a certificate for stability or find a counter-example when it fails. This counter-example is added to a set of samples to facilitate the further learning of a Lyapunov function. We demonstrate the results on two examples and show that the proposed approach yields a less conservative region of attraction (ROA) compared with alternative state-of-the-art approaches. Moreover, we provide the runtime results to demonstrate potentials of the proposed framework in real-world implementations.

math.OC↗

arXiv2022

Quantum coherence of an orbital angular momentum multiplexed continuous-variable entangled state

Orbital angular momentum (OAM) multiplexed entangled state is an important quantum resource for high dimensional quantum information processing. In this paper, we experimentally quantify quantum coherence of OAM multiplexed continuous-variable (CV) entangled state and characterize its evolution in a noisy environment. We show that the quantum coherence of the OAM multiplexed CV entangled state carrying topological charges $l=1$ and $l=2$ are the same as that of the Gaussian mode with $l=0$ in a noisy channel. Furthermore, we show that the quantum coherence of OAM multiplexed entangled state is robust to noise, even though the sudden death of entanglement is observed. Our results provide reference for applying quantum coherence of OAM multiplexed CV entangled state in a noisy environment.

quant-ph↗

arXiv2022

Deterministic distribution of orbital angular momentum multiplexed continuous-variable entanglement and quantum steering

Orbital angular momentum (OAM) multiplexing provides an efficient method to improve data-carrying capacity in various quantum communication protocols. It is a precondition to distribute OAM multiplexed quantum resources in quantum channels for implementing quantum communication. However, quantum steering of OAM multiplexed optical fields and the effect of channel noise on OAM multiplexed quantum resources remain unclear. Here, we generate OAM multiplexed continuous-variable (CV) entangled states and distribute them in lossy or noisy channels. We show that the decoherence property of entanglement and quantum steering of the OAM multiplexed states carrying topological charges $l=1$ and $l=2$ are the same as that of the Gaussian mode with $l=0$ in lossy and noisy channels. The sudden death of entanglement and quantum steering of high-order OAM multiplexed states is observed in the presence of excess noise. Our results demonstrate the feasibility to realize high data-carrying capacity quantum information processing by utilizing OAM multiplexed CV entangled states.

quant-ph↗

arXiv2022

Image Segmentation with Adaptive Spatial Priors from Joint Registration

Image segmentation is a crucial but challenging task that has many applications. In medical imaging for instance, intensity inhomogeneity and noise are common. In thigh muscle images, different muscles are closed packed together and there are often no clear boundaries between them. Intensity based segmentation models cannot separate one muscle from another. To solve such problems, in this work we present a segmentation model with adaptive spatial priors from joint registration. This model combines segmentation and registration in a unified framework to leverage their positive mutual influence. The segmentation is based on a modified Gaussian mixture model (GMM), which integrates intensity inhomogeneity and spacial smoothness. The registration plays the role of providing a shape prior. We adopt a modified sum of squared difference (SSD) fidelity term and Tikhonov regularity term for registration, and also utilize Gaussian pyramid and parametric method for robustness. The connection between segmentation and registration is guaranteed by the cross entropy metric that aims to make the segmentation map (from segmentation) and deformed atlas (from registration) as similar as possible. This joint framework is implemented within a constraint optimization framework, which leads to an efficient algorithm. We evaluate our proposed model on synthetic and thigh muscle MR images. Numerical results show the improvement as compared to segmentation and registration performed separately and other joint models.

cs.CV↗

arXiv2022

Smoothing analysis of two robust multigrid methods for elliptic optimal control problems

In this paper we study and compare two multigrid relaxation schemes with coarsening by two, three, and four for solving elliptic sparse optimal control problems with control constraints. First, we perform a detailed local Fourier analysis (LFA) of a well-known collective Jacobi relaxation (CJR) scheme, where the optimal smoothing factors are derived. This insightful analysis reveals that the optimal relaxation parameters depend on mesh size and regularization parameters, which was not investigated in literature. Second, we propose and analyze a new mass-based Braess-Sarazin relaxation (BSR) scheme, which is proven to provide smaller smoothing factors than the CJR scheme when $α\ge ch^4$ for a small constant $c$. Here $α$ is the regularization parameter and $h$ is the spatial mesh step size. These schemes are successfully extended to control-constrained cases through the semi-smooth Newton method. Coarsening by three or four with BSR is competitive with coarsening by two. Numerical examples are presented to validate our theoretical outcomes. The proposed inexact BSR (IBSR) scheme, where two preconditioned conjugate gradients iterations are applied to the Schur complement system, yields better computational efficiency than the CJR scheme.

math.NA↗

arXiv2022

A Vanka-type multigrid solver for complex-shifted Laplacian systems from diagonalization-based parallel-in-time algorithms

We propose and analyze a Vanka-type multigrid solver for solving a sequence of complex-shifted Laplacian systems arising in diagonalization-based parallel-in-time algorithms for evolutionary equations. Under suitable assumption, local Fourier analysis shows the proposed Vanka-type smoother achieves a uniform smoothing factor, which is verified by several numerical examples.

math.NA↗

arXiv2022

Towards Class-agnostic Tracking Using Feature Decorrelation in Point Clouds

Single object tracking in point clouds has been attracting more and more attention owing to the presence of LiDAR sensors in 3D vision. However, the existing methods based on deep neural networks focus mainly on training different models for different categories, which makes them unable to perform well in real-world applications when encountering classes unseen during the training phase. In this work, we investigate a more challenging task in the LiDAR point clouds, class-agnostic tracking, where a general model is supposed to be learned for any specified targets of both observed and unseen categories. In particular, we first investigate the class-agnostic performances of the state-of-the-art trackers via exposing the unseen categories to them during testing, finding that a key factor for class-agnostic tracking is how to constrain fused features between the template and search region to maintain generalization when the distribution is shifted from observed to unseen classes. Therefore, we propose a feature decorrelation method to address this problem, which eliminates the spurious correlations of the fused features through a set of learned weights and further makes the search region consistent among foreground points and distinctive between foreground and background points. Experiments on the KITTI and NuScenes demonstrate that the proposed method can achieve considerable improvements by benchmarking against the advanced trackers P2B and BAT, especially when tracking unseen objects.

cs.CV↗

arXiv2022

Prompt-based Generative Approach towards Multi-Hierarchical Medical Dialogue State Tracking

The medical dialogue system is a promising application that can provide great convenience for patients. The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging. Firstly, the states need to be able to represent compound entities such as symptoms with their body part or diseases with degrees of severity to provide enough information for decision support. Secondly, these named entities in the utterance might be discontinuous and scattered across sentences and speakers. These also make it difficult to annotate a large corpus which is essential for most methods. Therefore, we first define a multi-hierarchical state structure. We annotate and publish a medical dialogue dataset in Chinese. To the best of our knowledge, there are no publicly available ones before. Then we propose a Prompt-based Generative Approach which can generate slot values with multi-hierarchies incrementally using a top-down approach. A dialogue style prompt is also supplemented to utilize the large unlabeled dialogue corpus to alleviate the data scarcity problem. The experiments show that our approach outperforms other DST methods and is rather effective in the scenario with little data.

cs.CL↗