arXiv subjects

Rui She

Publications and source records attributed to Rui She.

At least 37 records · Page 2Linked to original sources

arXiv2023

RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments

Camera relocalization has various applications in autonomous driving. Previous camera pose regression models consider only ideal scenarios where there is little environmental perturbation. To deal with challenging driving environments that may have changing seasons, weather, illumination, and the presence of unstable objects, we propose RobustLoc, which derives its robustness against perturbations from neural differential equations. Our model uses a convolutional neural network to extract feature maps from multi-view images, a robust neural differential equation diffusion block module to diffuse information interactively, and a branched pose decoder with multi-layer training to estimate the vehicle poses. Experiments demonstrate that RobustLoc surpasses current state-of-the-art camera pose regression models and achieves robust performance in various environments. Our code is released at: https://github.com/sijieaaa/RobustLoc

cs.CV↗

arXiv2023

HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion

LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision. LiDAR-based retrieval from a database typically incurs high computation storage costs and can lead to globally inaccurate pose estimations if the database is too sparse. On the other hand, pose regression methods take images or point clouds as inputs and directly regress global poses in an end-to-end manner. They do not perform database matching and are more computationally efficient than retrieval techniques. We propose HypLiLoc, a new model for LiDAR pose regression. We use two branched backbones to extract 3D features and 2D projection features, respectively. We consider multi-modal feature fusion in both Euclidean and hyperbolic spaces to obtain more effective feature representations. Experimental results indicate that HypLiLoc achieves state-of-the-art performance in both outdoor and indoor datasets. We also conduct extensive ablation studies on the framework design, which demonstrate the effectiveness of multi-modal feature extraction and multi-space embedding. Our code is released at: https://github.com/sijieaaa/HypLiLoc

cs.CV↗

arXiv2023

Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks

Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data. However, common challenges faced by many GNNs in the literature include the problem of graph node embedding under various geometries and the over-smoothing problem. To address these issues, we propose a novel graph information propagation strategy called Hamiltonian Dynamic GNN (HDG) that uses a Hamiltonian mechanics approach to learn node embeddings in a graph. The Hamiltonian energy function in HDG is learnable and can adapt to the underlying geometry of any given graph dataset. We demonstrate the ability of HDG to automatically learn the underlying geometry of graph datasets, even those with complex and mixed geometries, through comprehensive evaluations against state-of-the-art baselines on various downstream tasks. We also verify that HDG is stable against small perturbations and can mitigate the over-smoothing problem when stacking many layers.

cs.LG↗

arXiv2022

Building Facade Parsing R-CNN

Building facade parsing, which predicts pixel-level labels for building facades, has applications in computer vision perception for autonomous vehicle (AV) driving. However, instead of a frontal view, an on-board camera of an AV captures a deformed view of the facade of the buildings on both sides of the road the AV is travelling on, due to the camera perspective. We propose Facade R-CNN, which includes a transconv module, generalized bounding box detection, and convex regularization, to perform parsing of deformed facade views. Experiments demonstrate that Facade R-CNN achieves better performance than the current state-of-the-art facade parsing models, which are primarily developed for frontal views. We also publish a new building facade parsing dataset derived from the Oxford RobotCar dataset, which we call the Oxford RobotCar Facade dataset. This dataset contains 500 street-view images from the Oxford RobotCar dataset augmented with accurate annotations of building facade objects. The published dataset is available at https://github.com/sijieaaa/Oxford-RobotCar-Facade

cs.CV↗

arXiv2022

From MIM-Based GAN to Anomaly Detection:Event Probability Influence on Generative Adversarial Networks

In order to introduce deep learning technologies into anomaly detection, Generative Adversarial Networks (GANs) are considered as important roles in the algorithm design and realistic applications. In terms of GANs, event probability reflected in the objective function, has an impact on the event generation which plays a crucial part in GAN-based anomaly detection. The information metric, e.g. Kullback-Leibler divergence in the original GAN, makes the objective function have different sensitivity on different event probability, which provides an opportunity to refine GAN-based anomaly detection by influencing data generation. In this paper, we introduce the exponential information metric into the GAN, referred to as MIM-based GAN, whose superior characteristics on data generation are discussed in theory. Furthermore, we propose an anomaly detection method with MIM-based GAN, as well as explain its principle for the unsupervised learning case from the viewpoint of probability event generation. Since this method is promising to detect anomalies in Internet of Things (IoT), such as environmental, medical and biochemical outliers, we make use of several datasets from the online ODDS repository to evaluate its performance and compare it with other methods.

cs.LG↗

arXiv2021

MIM-Based GAN: Information Metric to Amplify Small Probability Events Importance in Generative Adversarial Networks

In terms of Generative Adversarial Networks (GANs), the information metric to discriminate the generative data from the real data, lies in the key point of generation efficiency, which plays an important role in GAN-based applications, especially in anomaly detection. As for the original GAN, there exist drawbacks for its hidden information measure based on KL divergence on rare events generation and training performance for adversarial networks. Therefore, it is significant to investigate the metrics used in GANs to improve the generation ability as well as bring gains in the training process. In this paper, we adopt the exponential form, referred from the information measure, i.e. MIM, to replace the logarithm form of the original GAN. This approach is called MIM-based GAN, has better performance on networks training and rare events generation. Specifically, we first discuss the characteristics of training process in this approach. Moreover, we also analyze its advantages on generating rare events in theory. In addition, we do simulations on the datasets of MNIST and ODDS to see that the MIM-based GAN achieves state-of-the-art performance on anomaly detection compared with some classical GANs.

cs.LG↗

arXiv2020

An Importance Aware Weighted Coding Theorem Using Message Importance Measure

There are numerous scenarios in source coding where not only the code length but the importance of each value should also be taken into account. Different from the traditional coding theorems, by adding the importance weights for the length of the codes, we define the average cost of the weighted codeword length as an importance-aware measure of the codes. This novel information theoretical measure generalizes the average codeword length by assigning importance weights for each symbol according to users' concerns through focusing on user's selections. With such definitions, coding theorems of the bounds are derived and the outcomes are shown to be extensions of traditional coding theorems.

cs.IT↗

arXiv2020

Storage Space Allocation Strategy for Digital Data with Message Importance

This paper mainly focuses on the problem of lossy compression storage from the perspective of message importance when the reconstructed data pursues the least distortion within limited total storage size. For this purpose, we transform this problem to an optimization by means of the importance-weighted reconstruction error in data reconstruction. Based on it, this paper puts forward an optimal allocation strategy in the storage of digital data by a kind of restrictive water-filling. That is, it is a high efficient adaptive compression strategy since it can make rational use of all the storage space. It also characterizes the trade-off between the relative weighted reconstruction error and the available storage size. Furthermore, this paper also presents that both the users' preferences and the special characteristic of data distribution can trigger the small-probability event scenarios where only a fraction of data can cover the vast majority of users' interests. Whether it is for one of the reasons above, the data with highly clustered message importance is beneficial to compression storage. In contrast, the data with uniform information distribution is incompressible, which is consistent with that in information theory.

cs.IT↗

arXiv2019

Importance of Small Probability Events in Big Data: Information Measures, Applications, and Challenges

In many applications (e.g., anomaly detection and security systems) of smart cities, rare events dominate the importance of the total information of big data collected by Internet of Things (IoTs). That is, it is pretty crucial to explore the valuable information associated with the rare events involved in minority subsets of the voluminous amounts of data. To do so, how to effectively measure the information with importance of the small probability events from the perspective of information theory is a fundamental question. This paper first makes a survey of some theories and models with respect to importance measures and investigates the relationship between subjective or semantic importance and rare events in big data. Moreover, some applications for message processing and data analysis are discussed in the viewpoint of information measures. In addition, based on rare events detection, some open challenges related to information measures, such as smart cities, autonomous driving, and anomaly detection in IoTs, are introduced which can be considered as future research directions.

cs.IT↗

arXiv2019

Matching Users' Preference Under Target Revenue Constraints in Optimal Data Recommendation Systems

This paper focuses on the problem of finding a particular data recommendation strategy based on the user preferences and a system expected revenue. To this end, we formulate this problem as an optimization by designing the recommendation mechanism as close to the user behavior as possible with a certain revenue constraint. In fact, the optimal recommendation distribution is the one that is the closest to the utility distribution in the sense of relative entropy and satisfies expected revenue. We show that the optimal recommendation distribution follows the same form as the message importance measure (MIM) if the target revenue is reasonable, i.e., neither too small nor too large. Therefore, the optimal recommendation distribution can be regarded as the normalized MIM, where the parameter, called importance coefficient, presents the concern of the system and switches the attention of the system over data sets with different occurring probability. By adjusting the importance coefficient, our MIM based framework of data recommendation can then be applied to system with various system requirements and data distributions.Therefore,the obtained results illustrate the physical meaning of MIM from the data recommendation perspective and validate the rationality of MIM in one aspect.

cs.IT↗

arXiv2019

Information Measure Similarity Theory: Message Importance Measure via Shannon Entropy

Rare events attract more attention and interests in many scenarios of big data such as anomaly detection and security systems. To characterize the rare events importance from probabilistic perspective, the message importance measure (MIM) is proposed as a kind of semantics analysis tool. Similar to Shannon entropy, the MIM has its special functional on information processing, in which the parameter $\varpi$ of MIM plays a vital role. Actually, the parameter $\varpi$ dominates the properties of MIM, based on which the MIM has three work regions where the corresponding parameters satisfy $ 0 \le \varpi \le 2/\max\{p(x_i)\}$, $\varpi > 2/\max\{p(x_i)\}$ and $\varpi < 0$ respectively. Furthermore, in the case $ 0 \le \varpi \le 2/\max\{p(x_i)\}$, there are some similarity between the MIM and Shannon entropy in the information compression and transmission, which provide a new viewpoint for information theory. This paper first constructs a system model with message importance measure and proposes the message importance loss to enrich the information processing strategies. Moreover, we propose the message importance loss capacity to measure the information importance harvest in a transmission. Furthermore, the message importance distortion function is presented to give an upper bound of information compression based on message importance measure. Additionally, the bitrate transmission constrained by the message importance loss is investigated to broaden the scope for Shannon information theory.

cs.IT↗

arXiv2018

State Variation Mining: On Information Divergence with Message Importance in Big Data

Information transfer which reveals the state variation of variables usually plays a vital role in big data analytics and processing. In fact, the measures for information transfer could reflect the system change by use of the variable distributions, similar to KL divergence and Renyi divergence. Furthermore, in terms of the information transfer in big data, small probability events usually dominate the importance of the total message to some degree. Therefore, it is significant to design an information transfer measure based on the message importance which emphasizes the small probability events. In this paper, we propose a message importance transfer measure (MITM) and investigate its characteristics and applications on three aspects. First, the message importance transfer capacity based on MITM is presented to offer an upper bound for the information transfer process with disturbance. Then, we extend the MITM to the continuous case and discuss the robustness by using it to measuring information distance. Finally, we utilize the MITM to guide the queue length selection in the caching operation of mobile edge computing.

cs.IT↗

arXiv2018

Focusing on a Probability Element: Parameter Selection of Message Importance Measure in Big Data

Message importance measure (MIM) is applicable to characterize the importance of information in the scenario of big data, similar to entropy in information theory. In fact, MIM with a variable parameter can make an effect on the characterization of distribution. Furthermore, by choosing an appropriate parameter of MIM, it is possible to emphasize the message importance of a certain probability element in a distribution. Therefore, parametric MIM can play a vital role in anomaly detection of big data by focusing on probability of an anomalous event. In this paper, we propose a parameter selection method of MIM focusing on a probability element and then present its major properties. In addition, we discuss the parameter selection with prior probability, and investigate the availability in a statistical processing model of big data for anomaly detection problem.

cs.IT↗

arXiv2018

Chandra Survey of Nearby Galaxies: Testing the Accretion Model for Low-luminosity AGNs

From a Chandra sample of active galactic nuclei (AGNs) in nearby galaxies, we find that for low-luminosity AGNs (LLAGNs), either the intrinsic absorption column density, or the fraction of absorbed AGNs, positively scales with the Eddington ratio for $L_{\rm bol}/L_{\rm Edd} \lesssim 10^{-2}$. Such a behavior, along with the softness of the X-ray spectrum at low luminosities, is in good agreement with the picture that they are powered by hot accretion flows surrounding supermassive black holes. Numerical simulations find that outflows are inevitable with hot accretion flows, and the outflow rate is correlated with the innermost accretion rate in the low-luminosity regime. This agrees well with our results, suggesting that the X-ray absorption originates from or is associated with the outflow material. Gas and dust on larger scales may also produce the observed correlation. Future correlation analysis may help differentiate the two scenarios.

astro-ph.HE↗

arXiv2018

A Switch to the Concern of User: Importance Coefficient in Utility Distribution and Message Importance Measure

This paper mainly focuses on the utilization frequency in receiving end of communication systems, which shows the inclination of the user about different symbols. When the average number of use is limited, a specific utility distribution is proposed on the best effort in term of fairness, which is also the closest one to occurring probability in the relative entropy. Similar to a switch, its parameter can be selected to make it satisfy different users' requirements: negative parameter means the user focus on high-probability events and positive parameter means the user is interested in small-probability events. In fact, the utility distribution is a measure of message importance in essence. It illustrates the meaning of message importance measure (MIM), and extend it to the general case by selecting the parameter. Numerical results show that this utility distribution characterizes the message importance like MIM and its parameter determines the concern of users.

cs.IT↗

arXiv2018

Differential Message Importance Measure: A New Approach to the Required Sampling Number in Big Data Structure Characterization

Data collection is a fundamental problem in the scenario of big data, where the size of sampling sets plays a very important role, especially in the characterization of data structure. This paper considers the information collection process by taking message importance into account, and gives a distribution-free criterion to determine how many samples are required in big data structure characterization. Similar to differential entropy, we define differential message importance measure (DMIM) as a measure of message importance for continuous random variable. The DMIM for many common densities is discussed, and high-precision approximate values for normal distribution are given. Moreover, it is proved that the change of DMIM can describe the gap between the distribution of a set of sample values and a theoretical distribution. In fact, the deviation of DMIM is equivalent to Kolmogorov-Smirnov statistic, but it offers a new way to characterize the distribution goodness-of-fit. Numerical results show some basic properties of DMIM and the accuracy of the proposed approximate values. Furthermore, it is also obtained that the empirical distribution approaches the real distribution with decreasing of the DMIM deviation, which contributes to the selection of suitable sampling points in actual system.

cs.IT↗

arXiv2018

How Many Samples Required in Big Data Collection: A Differential Message Importance Measure

Information collection is a fundamental problem in big data, where the size of sampling sets plays a very important role. This work considers the information collection process by taking message importance into account. Similar to differential entropy, we define differential message importance measure (DMIM) as a measure of message importance for continuous random variable. It is proved that the change of DMIM can describe the gap between the distribution of a set of sample values and a theoretical distribution. In fact, the deviation of DMIM is equivalent to Kolmogorov-Smirnov statistic, but it offers a new way to characterize the distribution goodness-of-fit. Numerical results show some basic properties of DMIM and the accuracy of the proposed approximate values. Furthermore, it is also obtained that the empirical distribution approaches the real distribution with decreasing of the DMIM deviation, which contributes to the selection of suitable sampling points in actual system.

cs.IT↗

arXiv2017

Non-parametric Message Important Measure: Storage Code Design and Transmission Planning for Big Data

Storage and transmission in big data are discussed in this paper, where message importance is taken into account. Similar to Shannon Entropy and Renyi Entropy, we define non-parametric message important measure (NMIM) as a measure for the message importance in the scenario of big data, which can characterize the uncertainty of random events. It is proved that the proposed NMIM can sufficiently describe two key characters of big data: rare events finding and large diversities of events. Based on NMIM, we first propose an effective compressed encoding mode for data storage, and then discuss the channel transmission over some typical channel models. Numerical simulation results show that using our proposed strategy occupies less storage space without losing too much message importance, and there are growth region and saturation region for the maximum transmission, which contributes to designing of better practical communication system.

cs.IT↗