Zhaopeng Meng's research while affiliated with Tianjin University of Traditional Chinese Medicine and other places

Publications (71)

Chapter
We propose an efficient multi-view stereo (MVS) network for inferring depth value from multiple RGB images. Recent studies use the cost volume to encode the matching correspondence between different views, but this structure can still be optimized from the perspective of image features. First of all, to fully aggregate the dominant interrelationshi...
Preprint
Deep Reinforcement Learning (Deep RL) and Evolutionary Algorithm (EA) are two major paradigms of policy optimization with distinct learning principles, i.e., gradient-based v.s. gradient free. An appealing research direction is integrating Deep RL and EA to devise new methods by fusing their complementary advantages. However, existing works on comb...
Chapter
Acquiring pixel-level annotations for histological image segmentation is time- and labor- consuming. Semi-supervised learning enables learning from the unlabeled and limited amount of labeled data. A challenging issue is the inconsistent and uncertain predictions on unlabeled data. To enforce invariant predictions over the perturbations applied to...
Conference Paper
Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world scenarios. Although advances have been made recently, most prior works assume sufficient online interaction on...
Article
We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation. Such an extension enables PeVFA to preserve values of multiple policies at the same time and brings an...
Preprint
Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world scenarios. Although advances have been made recently, most prior works assume sufficient online interaction on...
Article
Full-text available
Discriminative correlation filters (DCF) have demonstrated competitive tracking performance in recent years. In these approaches, DCF methods only learn the appearance models with the historical tracking results, thus have the risks of drifting the targets due to the unforeseen target appearances in the future. In this paper, we present a novel tra...
Chapter
Value estimation is one key problem in Reinforcement Learning. Albeit many successes have been achieved by Deep Reinforcement Learning (DRL) in different fields, the underlying structure and learning dynamics of value function, especially with complex function approximation, are not fully understood. In this paper, we report that decreasing rank of...
Chapter
Reconstructing surface normal from the reflectance observations of real objects is a challenging issue. Although recent works on photometric stereo exploit various reflectance-normal mapping models, none of them take both illumination and LDR maximum into account. In this paper, we combine a fusion learning network with LDR maxima to recover the no...
Preprint
Value estimation is one key problem in Reinforcement Learning. Albeit many successes have been achieved by Deep Reinforcement Learning (DRL) in different fields, the underlying structure and learning dynamics of value function, especially with complex function approximation, are not fully understood. In this paper, we report that decreasing rank of...
Preprint
Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant success across a wide range of domains, such as game AI, autonomous vehicles, robotics and finance. However, DRL and deep MARL agents are widely known to be sample-inefficient and millions of interactions are usually needed even for relati...
Preprint
Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or continuous action space, while seldom take into account the hybrid action space. One naive way to add...
Article
The capability of generalization to unseen domains is crucial for deep learning models when considering real-world scenarios. However, current available medical image datasets, such as those for COVID-19 CT images, have large variations of infections and domain shift problems. To address this issue, we propose a prior knowledge driven domain adapta...
Article
Deep reinforcement learning (DRL) algorithms have been demonstrated to be effective on a wide range of challenging decision making and control tasks. However, these methods typically suffer from severe action oscillations in particular in discrete action setting, which means that agents select different actions within consecutive steps even though...
Article
Value function is the central notion of Reinforcement Learning (RL). Value estimation, especially with function approximation, can be challenging since it involves the stochasticity of environmental dynamics and reward signals that can be sparse and delayed in some cases. A typical model-free RL algorithm usually estimates the values of a policy by...
Article
The insufficiency of annotated medical imaging scans for cancer makes it challenging to train and validate data-hungry deep learning models in precision oncology. We propose a new richer generative adversarial network for free-form 3D tumor/lesion synthesis in computed tomography (CT) images. The network is composed of a new richer convolutional fe...
Preprint
The insufficiency of annotated medical imaging scans for cancer makes it challenging to train and validate data-hungry deep learning models in precision oncology. We propose a new richer generative adversarial network for free-form 3D tumor/lesion synthesis in computed tomography (CT) images. The network is composed of a new richer convolutional fe...
Preprint
The capability of generalization to unseen domains is crucial for deep learning models when considering real-world scenarios. However, current available medical image datasets, such as those for COVID-19 CT images, have large variations of infections and domain shift problems. To address this issue, we propose a prior knowledge driven domain adapta...
Article
Full-text available
One challenging problem in multiagent systems is to cooperate or compete with non-stationary agents that change behavior from time to time. An agent in such a non-stationary environment is usually supposed to be able to quickly detect the other agents’ policy during online interaction, and then adapt its own policy accordingly. This article studies...
Article
Screened Poisson Surface Reconstruction has a good performance among the state-of-art surface reconstruction algorithms in obtaining a triangle mesh from oriented points. In order to better deal with nonuniform point clouds, Screened Poisson Surface Reconstruction uses B-spline functions with a fixed support for kernel density estimation to constru...
Preprint
Deep reinforcement learning (DRL) algorithms have been demonstrated to be effective in a wide range of challenging decision making and control tasks. However, these methods typically suffer from severe action oscillations in particular in discrete action setting, which means that agents select different actions within consecutive steps even though...
Preprint
Value function is the central notion of Reinforcement Learning (RL). Value estimation, especially with function approximation, can be challenging since it involves the stochasticity of environmental dynamics and reward signals that can be sparse and delayed in some cases. A typical model-free RL algorithm usually estimates the values of a policy by...
Article
Accurate diagnosis and segmentation of skin lesion is critical for early detection and diagnosis of skin cancer. Recent multi-task learning methods require expensive annotations for skin lesion analysis while single-task driven models cannot fully utilize the potential knowledge. The aim of this study is to utilize the neglected knowledge by a flex...
Article
Full-text available
Automatic extraction of liver and tumor from CT volumes is a challenging task due to their heterogeneous and diffusive shapes. Recently, 2D deep convolutional neural networks have become popular in medical image segmentation tasks because of the utilization of large labeled datasets to learn hierarchical features. However, few studies investigate 3...
Preprint
The value function lies in the heart of Reinforcement Learning (RL), which defines the long-term evaluation of a policy in a given state. In this paper, we propose Policy-extended Value Function Approximator (PeVFA) which extends the conventional value to be not only a function of state but also an explicit policy representation. Such an extension...
Article
Full-text available
Segmentation of retinal vessels in fundus images plays a very important role in diagnosing relevant diseases. In this paper, we have constructed automated segmentation models for the retinal vessel segmentation task based on convolutional neural networks. Since some typical deep convolutional neural networks need to be fed by high-resolution patche...
Conference Paper
Full-text available
Transfer learning has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing approaches either transfer previous knowledge by explicitly computing similarities between tasks or select appropriate source policies to provide guided explorations. However, how...
Conference Paper
Full-text available
Generating diverse behaviors for game artificial intelligence (Game AI) has been long recognized as a challenging task in the game industry. Designing a Game AI with a satisfying behavioral characteristic (style) heavily depends on the domain knowledge and is hard to achieve manually. Deep reinforcement learning sheds light on advancing the automat...
Article
Full-text available
Passive reconstruction methods such as traditional multi-view stereo are capable to accurate reconstruction results. However, the depth calculation of multi-view stereo encounters significant difficulties, especially when the corresponding points have some degree of inaccuracy or unreliability. In this paper, we make use of geometric and shading cu...
Article
Full-text available
Gene selection algorithm in micro-array data classification problem finds a small set of genes which are most informative and distinctive. A well-performed gene selection algorithm should pick a set of genes that achieve high performance and the size of this gene set should be as small as possible. Many of the existing gene selection algorithms suf...
Preprint
With the increasing popularity of electric vehicles, distributed energy generation and storage facilities in smart grid systems, an efficient Demand-Side Management (DSM) is urgent for energy savings and peak loads reduction. Traditional DSM works focusing on optimizing the energy activities for a single household can not scale up to large-scale ho...
Article
With the increasing popularity of electric vehicles, distributed energy generation and storage facilities in smart grid systems, an efficient Demand-Side Management (DSM) is urgent for energy savings and peak loads reduction. Traditional DSM works focusing on optimizing the energy activities for a single household can not scale up to large-scale ho...
Preprint
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. However,...
Preprint
Full-text available
Transfer Learning has shown great potential to enhance the single-agent Reinforcement Learning (RL) efficiency, by sharing previously learned policies. Inspired by this, the team learning performance in multiagent settings can be potentially promoted with agents reusing knowledge between each other when all agents interact with the environment and...
Conference Paper
Multiagent algorithms often aim to accurately predict the behaviors of other agents and find a best response accordingly. Previous works usually assume an opponent uses a stationary strategy or randomly switches among several stationary ones. However, an opponent may exhibit more sophisticated behaviors by adopting more advanced reasoning strategie...
Article
Full-text available
The objective of designing timetables for public transportation is twofold: to ensure an efficient use of limited resources and to provide a comfortable ride for passengers. Two models for timetable optimization are investigated in this study. Model 1 uses a crisp constraint on the rate of vehicle capacity usage. Model 2 improves on model 1 by tran...
Preprint
Full-text available
Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future pre...
Article
In this paper, we experimentally perform the measurement of the backscattered light intensity from the underwater targets with different size. We develop a simple system, which can easily measure the intensity of the backscattered light, after the laser is scattered at the target underwater. We find that, the signal period is related to the particl...
Article
Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels’ local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired...
Article
Full-text available
Gliomas have 2 the highest mortality rate and prevalence among the primary brain tumors. In this study, we proposed a supervised brain tumor segmentation method which detects diverse tumoral structures of both high grade gliomas and low grade gliomas in magnetic resonance imaging (MRI) images based on two types of features, the gradient features an...
Article
Full-text available
In this paper, we theoretically and experimentally analyze the frequency-comb interferometry at 518 nm in the underwater environment, which we use to measure the underwater distance with high accuracy and precision. In the time domain, we analyze the principle of pulse cross correlation. The interferograms can be obtained in the vicinity of N∙lpp,...
Article
Timetable scheduling for public transit seeks to optimize service quality and utilization of limited resources. A new method is proposed to find a sequence of time intervals adjusted to the dynamic passenger flow in a fuzzy environment with improved reverse-flow. The decision making is based on two fuzzy variables – passenger satisfaction and vehic...
Preprint
Full-text available
Automatic extraction of liver and tumor from CT volumes is a challenging task due to their heterogeneous and diffusive shapes. Recently, 2D and 3D deep convolutional neural networks have become popular in medical image segmentation tasks because of the utilization of large labeled datasets to learn hierarchical features. However, 3D networks have s...
Preprint
Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels' local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired...
Article
Full-text available
Although tracking research has achieved excellent performance in mathematical angles, it is still meaningful to analyze tracking problems from multiple perspectives. This motivation not only promotes the independence of tracking research but also increases the flexibility of practical applications. This paper presents a significant tracking framewo...
Preprint
Full-text available
Multiagent algorithms often aim to accurately predict the behaviors of other agents and find a best response during interactions accordingly. Previous works usually assume an opponent uses a stationary strategy or randomly switches among several stationary ones. However, in practice, an opponent may exhibit more sophisticated behaviors by adopting...
Chapter
Full-text available
Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when faced with the non-stationarity due to agents update their policies simultaneously in stochastic cooperative environments. This paper extends the recently proposed weighted double estimator to the...
Article
Full-text available
Feature selection, which identifies a set of most informative features from the original feature space, has been widely used to simplify the predictor. Recursive feature elimination (RFE), as one of the most popular feature selection approaches, is effective in data dimension reduction and efficiency increase. A ranking of features, as well as cand...
Article
Full-text available
In this paper, we demonstrate a method using a frequency comb, which can precisely measure the refractive index of water. We have developed a simple system, in which a Michelson interferometer is placed into a quartz-glass container with a low expansion coefficient, and for which compensation of the thermal expansion of the water container is not r...
Article
Full-text available
With the explosive growth of vehicles on the road, traffic congestion has become an inevitable problem when applying guidance algorithms to transportation networks in a busy and crowded city. In our study, the authors proposed an advanced prediction and navigation models on a dynamic traffic network. In contrast to the traditional shortest path alg...
Article
Social norms serve as an important mechanism to regulate the behaviors of agents and to facilitate coordination among them in multiagent systems. One important research question is how a norm can rapidly emerge through repeated local interaction within an agent society under different environments when their coordination space becomes large. To add...
Article
Full-text available
Motion model and model updater are two necessary components for online visual tracking. On the one hand, an effective motion model needs to strike the right balance between target processing, to account for the target appearance and scene analysis, and to describe stable background information. Most conventional trackers focus on one aspect out of...
Chapter
Motion model and model updater are two important components for online visual tracking. On the one hand, an effective motion model needs to strike the right balance between target processing, to account for the target appearance and scene analysis, to describe stable background information. Most conventional trackers focus on one aspect out of the...
Conference Paper
Indoor localization system based on received signal strength (RSS) often operate under non-line-of-sight (NLOS) conditions that can cause ranging errors. To identify non-line-of-sight status and line-of-sight (LOS) status and improve the accuracy of indoor localization, a D-S evidence theory based NLOS identification algorithm was proposed. The alg...
Article
We present a novel defending strategy, adaptive Markov strategy (AMS), to protect a smart-grid system from being attacked by unknown attackers with unpredictable and dynamic behaviors. One significant merit of deploying AMS to defend the system is that it is theoretically guaranteed to converge to a best response strategy against any stationary att...
Conference Paper
Social norms serve as an important mechanism to regulate the behaviours of agents and to facilitate coordination among them in multiagent systems. One important research question is how a norm can rapidly emerge through repeated local interaction within agent societies under different environments when their coordination space becomes large. To add...
Article
Full-text available
Location data are among the most widely used context data in context-aware and ubiquitous computing applications. Many systems with distinct deployment costs and positioning accuracies have been developed over the past decade for indoor positioning. The most useful method is focused on the received signal strength and provides a set of signal trans...
Article
Full-text available
Advances in mobile screen sizes and feature enhancement for mobile applications have increased the number of users accessing spreadsheets on mobile devices. This paper reports a comparative usability study on four popular mobile spreadsheet applications: OfficeSuite Viewer 6, Documents To Go, ThinkFree Online, and Google Drive. We compare them agai...
Article
Full-text available
Neighbor discovery and the power of sensors play an important role in the formation of Wireless Sensor Networks (WSNs) and mobile networks. Many asynchronous protocols based on wake-up time scheduling have been proposed to enable neighbor discovery among neighboring nodes for the energy saving, especially in the difficulty of clock synchronization....
Article
Most tracking-by-detection approaches train the classifier in an supervised manner in which the samples near the tracked object location are labeled positively while those far from the object location are negative. However, the inaccuracy of the tracker may cause incorrectly labeled training samples, which in turn degrade the classifier when updati...
Article
In this paper, we propose a layered approach to model Jackson Pollock’s dripping style of paintings. Having analyzed fractal-based algorithms and observed the details of Pollock’s paintings, we designed a layered modeling approach that divides Pollock’s artwork into four layers: from bottom up are background layer, irregular shape layer, line layer...