arXiv subjects

Bo Chen

Publications and source records attributed to Bo Chen.

At least 325 records · Page 18Linked to original sources

arXiv2021

Kalman-Like Filter under Binary Sensors

This paper is concerned with the linear/nonlinear Kalman-like filtering problem under binary sensors. Since innovation represents new information in the sensor measurement and serves to correct the prediction for the Kalman-like filter (KLF), a novel uncertain measurement model is proposed such that the innovation generated from binary sensor can be captured. When considering linear dynamic systems, a conservative estimation error covariance with adjustable parameters is constructed by matrix inequality, and then an optimal filter gain is derived by minimizing its trace. Meanwhile, the optimal selection criterion of an adjustable parameter is developed by minimizing the upper bound of the conservative estimation error covariance. When considering nonlinear dynamic systems, a conservative estimation error covariance with adjustable parameters is also constructed via unscented transform and matrix inequalities. Then, following the idea of designing KLF in linear dynamic systems, the nonlinear filter gain and the optimal adjustable parameter are designed. Finally, $O_2$ content estimation and nonlinear numerical system are employed to show the effectiveness and advantages of the proposed methods.

eess.SY↗

arXiv2021

TopicNet: Semantic Graph-Guided Topic Discovery

Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior beliefs such as knowledge graph to guide the learning of the topic hierarchy. To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as an inductive bias to influence learning. TopicNet represents each topic as a Gaussian-distributed embedding vector, projects the topics of all layers into a shared embedding space, and explores both the symmetric and asymmetric similarities between Gaussian embedding vectors to incorporate prior semantic hierarchies. With an auto-encoding variational inference network, the model parameters are optimized by minimizing the evidence lower bound and a regularization term via stochastic gradient descent. Experiments on widely used benchmarks show that TopicNet outperforms related deep topic models on discovering deeper interpretable topics and mining better document~representations.

cs.LG↗

arXiv2021

Occlusion-Robust Object Pose Estimation with Holistic Representation

Practical object pose estimation demands robustness against occlusions to the target object. State-of-the-art (SOTA) object pose estimators take a two-stage approach, where the first stage predicts 2D landmarks using a deep network and the second stage solves for 6DOF pose from 2D-3D correspondences. Albeit widely adopted, such two-stage approaches could suffer from novel occlusions when generalising and weak landmark coherence due to disrupted features. To address these issues, we develop a novel occlude-and-blackout batch augmentation technique to learn occlusion-robust deep features, and a multi-precision supervision architecture to encourage holistic pose representation learning for accurate and coherent landmark predictions. We perform careful ablation tests to verify the impact of our innovations and compare our method to SOTA pose estimators. Without the need of any post-processing or refinement, our method exhibits superior performance on the LINEMOD dataset. On the YCB-Video dataset our method outperforms all non-refinement methods in terms of the ADD(-S) metric. We also demonstrate the high data-efficiency of our method. Our code is available at http://github.com/BoChenYS/ROPE

cs.CV↗

arXiv2021

A Prototype-Oriented Framework for Unsupervised Domain Adaptation

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation. Requiring no additional model parameters and having a moderate increase in computation over the source model alone, the proposed method achieves competitive performance with state-of-the-art methods.

cs.LG↗

arXiv2021

Physical Adversarial Attacks on an Aerial Imagery Object Detector

Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this weakness also plagues DNNs for aerial imagery. In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. Physical adversarial attacks on aerial images, particularly those captured from satellite platforms, are challenged by atmospheric factors (lighting, weather, seasons) and the distance between the observer and target. To investigate the effects of these challenges, we devised novel experiments and metrics to evaluate the efficacy of physical adversarial attacks against object detectors in aerial scenes. Our results indicate the palpable threat posed by physical adversarial attacks towards DNNs for processing satellite imagery.

cs.CV↗

arXiv2021

Enhanced Sequential Covariance Intersection Fusion

This paper is concerned with the sequential covariance intersection (CI) fusion problem that the fusion result is independent of fusion structure including the fusion order and the number of estimates fused in each sequential fusion. An enhanced sequential CI fusion is first developed to better meet the practical requirements as compared with the existing batch and sequential CI fusion. Meanwhile, it is proved that the enhanced sequential CI fusion ensures the fusion estimate and covariance are unbiased and consistent. Notice that the fusion structure of the enhanced sequential CI fusion is unpredictable in practice, which may have negative impacts on the fusion performance. To this end, a weighting fusion criterion with analytical form is further proposed, and can be depicted by different formulas when choosing different performance indexes. For this criterion, it is proved that the fusion results are not affected by the fusion structure, and thus the fusion performance can be guaranteed. Finally, simulation examples are utilized to demonstrate the effectiveness and advantages of the proposed methods.

eess.SY↗

arXiv2021

Optimizing Voting Order on Sequential Juries: A Median Voter Theorem and Beyond

We consider an odd-sized "jury", which votes sequentially between two states of Nature (say A and B, or Innocent and Guilty) with the majority opinion determining the verdict. Jurors have private information in the form of a signal in [-1,+1], with higher signals indicating A more likely. Each juror has an ability in [0,1], which is proportional to the probability of A given a positive signal, an analog of Condorcet's p for binary signals. We assume that jurors vote honestly for the alternative they view more likely, given their signal and prior voting, because they are experts who want to enhance their reputation (after their vote and actual state of Nature is revealed). For a fixed set of jury abilities, the reliability of the verdict depends on the voting order. For a jury of size three, the optimal ordering is always as follows: middle ability first, then highest ability, then lowest. For sufficiently heterogeneous juries, sequential voting is more reliable than simultaneous voting and is in fact optimal (allowing for non-honest voting). When average ability is fixed, verdict reliability is increasing in heterogeneity. For medium-sized juries, we find through simulation that the median ability juror should still vote first and the remaining ones should have increasing and then decreasing abilities.

econ.TH↗

arXiv2021

Fairness Criteria for Allocating Indivisible Chores: Connections and Efficiencies

We study several fairness notions in allocating indivisible chores (i.e., items with non-positive values) to agents who have additive and submodular cost functions. The fairness criteria we are concern with are envy-free up to any item (EFX), envy-free up to one item (EF1), maximin share (MMS), and pairwise maximin share (PMMS), which are proposed as relaxations of envy-freeness in the setting of additive cost functions. For allocations under each fairness criterion, we establish their approximation guarantee for other fairness criteria. Under the additive setting, our results show strong connections between these fairness criteria and, at the same time, reveal intrinsic differences between goods allocation and chores allocation. However, such strong relationships cannot be inherited by the submodular setting, under which PMMS and MMS are no longer relaxations of envy-freeness and, even worse, few non-trivial guarantees exist. We also investigate efficiency loss under these fairness constraints and establish their prices of fairness.

cs.GT↗

arXiv2021

Extracting Attentive Social Temporal Excitation for Sequential Recommendation

In collaborative filtering, it is an important way to make full use of social information to improve the recommendation quality, which has been proved to be effective because user behavior will be affected by her friends. However, existing works leverage the social relationship to aggregate user features from friends' historical behavior sequences in a user-level indirect paradigm. A significant defect of the indirect paradigm is that it ignores the temporal relationships between behavior events across users. In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm. Moreover, we propose to decompose the temporal effect in sequential recommendation into social mutual temporal effect and ego temporal effect. Specifically, we employ a social heterogeneous graph embedding layer to refine user representation via structural information. To enhance temporal information propagation, STEN directly extracts the fine-grained temporal mutual influence of friends' behaviors through the mutually exciting temporal network. Besides, the user s dynamic interests are captured through the self-exciting temporal network. Extensive experiments on three real-world datasets show that STEN outperforms state-of-the-art baseline methods. Moreover, STEN provides event-level recommendation explainability, which is also illustrated experimentally.

cs.SI↗

arXiv2021

Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network

Dual-view snapshot compressive imaging (SCI) aims to capture videos from two field-of-views (FoVs) using a 2D sensor (detector) in a single snapshot, achieving joint FoV and temporal compressive sensing, and thus enjoying the advantages of low-bandwidth, low-power, and low-cost. However, it is challenging for existing model-based decoding algorithms to reconstruct each individual scene, which usually require exhaustive parameter tuning with extremely long running time for large scale data. In this paper, we propose an optical flow-aided recurrent neural network for dual video SCI systems, which provides high-quality decoding in seconds. Firstly, we develop a diversity amplification method to enlarge the differences between scenes of two FoVs, and design a deep convolutional neural network with dual branches to separate different scenes from the single measurement. Secondly, we integrate the bidirectional optical flow extracted from adjacent frames with the recurrent neural network to jointly reconstruct each video in a sequential manner. Extensive results on both simulation and real data demonstrate the superior performance of our proposed model in a short inference time. The code and data are available at https://github.com/RuiyingLu/OFaNet-for-Dual-view-SCI.

eess.IV↗

arXiv2021

Practical Challenges in Real-time Demand Response

We report on a real-time demand response experiment with 100 controllable devices. The experiment reveals several key challenges in the deployment of a real-time demand response program, including time delays, uncertainties, characterization errors, multiple timescales, and nonlinearity, which have been largely ignored in previous studies. To resolve these practical issues, we develop and implement a two-level multi-loop control structure integrating feed-forward proportional-integral controllers and optimization solvers in closed loops, which eliminates steady-state errors and improves the dynamical performance of the overall building response. The proposed methods are validated by Hardware-in-the-Loop (HiL) tests.

eess.SY↗

arXiv2021

Atomistic Mechanism of Phase Transition in Shock Compressed Gold Revealed by Deep Potential

A detailed understanding of the material response to rapid compression is challenging and demanding. For instance, the element gold under dynamic compression exhibits complex phase transformations where there exist some large discrepancies between experimental and theoretical studies. Here, we combined large-scale molecular dynamics simulations with a deep potential to elucidate the dynamic compression processes of gold from an atomic level. The potential is constructed by accurately reproducing the free energy surfaces of density-functional-theory calculations for gold, from ambient conditions to 15 500 K and 500 GPa. Within this framework, we extend the simulations up to 200 000 atoms size, and found a much lower pressure threshold for phase transitioning from face-centered cubic (FCC) to body-centered (BCC), as compared to previous calculations. Furthermore, the transition pressure is strongly dependent on the shock direction, namely 159 GPa for (100) orientation and 219 GPa for (110) orientation, respectively. Most importantly, the accurate atomistic perspective presents that the shocked BCC structure contains unique features of medium-range and short-range orders, which is named disorders here. We propose a model and demonstrate that the existence of disorders significantly reduces the Gibbs free energies of shocked structures, therefore leading to the lowering of the phase transition pressure. The present study provides a new path to understand the structure dynamics under extreme conditions.

cond-mat.mtrl-sci↗

arXiv2021

Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision

Despite recent success in machine reading comprehension (MRC), learning high-quality MRC models still requires large-scale labeled training data, even using strong pre-trained language models (PLMs). The pre-training tasks for PLMs are not question-answering or MRC-based tasks, making existing PLMs unable to be directly used for unsupervised MRC. Specifically, MRC aims to spot an accurate answer span from the given document, but PLMs focus on token filling in sentences. In this paper, we propose a new framework for unsupervised MRC. Firstly, we propose to learn to spot answer spans in documents via self-supervised learning, by designing a self-supervision pretext task for MRC - Spotting-MLM. Solving this task requires capturing deep interactions between sentences in documents. Secondly, we apply a simple sentence rewriting strategy in the inference stage to alleviate the expression mismatch between questions and documents. Experiments show that our method achieves a new state-of-the-art performance for unsupervised MRC.

cs.CL↗

arXiv2021

Delay-Dependent Distributed Kalman Fusion Estimation with Dimensionality Reduction in Cyber-Physical Systems

This paper studies the distributed dimensionality reduction fusion estimation problem with communication delays for a class of cyber-physical systems (CPSs). The raw measurements are preprocessed in each sink node to obtain the local optimal estimate (LOE) of a CPS, and the compressed LOE under dimensionality reduction encounters with communication delays during the transmission. Under this case, a mathematical model with compensation strategy is proposed to characterize the dimensionality reduction and communication delays. This model also has the property to reduce the information loss caused by the dimensionality reduction and delays. Based on this model, a recursive distributed Kalman fusion estimator (DKFE) is derived by optimal weighted fusion criterion in the linear minimum variance sense. A stability condition for the DKFE, which can be easily verified by the exiting software, is derived. In addition, this condition can guarantee that estimation error covariance matrix of the DKFE converges to the unique steady-state matrix for any initial values, and thus the steady-state DKFE (SDKFE) is given. Notice that the computational complexity of the SDKFE is much lower than that of the DKFE. Moreover, a probability selection criterion for determining the dimensionality reduction strategy is also presented to guarantee the stability of the DKFE. Two illustrative examples are given to show the advantage and effectiveness of the proposed methods.

eess.SY↗

arXiv2021

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

Hierarchical topic models such as the gamma belief network (GBN) have delivered promising results in mining multi-layer document representations and discovering interpretable topic taxonomies. However, they often assume in the prior that the topics at each layer are independently drawn from the Dirichlet distribution, ignoring the dependencies between the topics both at the same layer and across different layers. To relax this assumption, we propose sawtooth factorial topic embedding guided GBN, a deep generative model of documents that captures the dependencies and semantic similarities between the topics in the embedding space. Specifically, both the words and topics are represented as embedding vectors of the same dimension. The topic matrix at a layer is factorized into the product of a factor loading matrix and a topic embedding matrix, the transpose of which is set as the factor loading matrix of the layer above. Repeating this particular type of factorization, which shares components between adjacent layers, leads to a structure referred to as sawtooth factorization. An auto-encoding variational inference network is constructed to optimize the model parameter via stochastic gradient descent. Experiments on big corpora show that our models outperform other neural topic models on extracting deeper interpretable topics and deriving better document representations.

cs.IR↗

arXiv2021

A Spacecraft Dataset for Detection, Segmentation and Parts Recognition

Virtually all aspects of modern life depend on space technology. Thanks to the great advancement of computer vision in general and deep learning-based techniques in particular, over the decades, the world witnessed the growing use of deep learning in solving problems for space applications, such as self-driving robot, tracers, insect-like robot on cosmos and health monitoring of spacecraft. These are just some prominent examples that has advanced space industry with the help of deep learning. However, the success of deep learning models requires a lot of training data in order to have decent performance, while on the other hand, there are very limited amount of publicly available space datasets for the training of deep learning models. Currently, there is no public datasets for space-based object detection or instance segmentation, partly because manually annotating object segmentation masks is very time consuming as they require pixel-level labelling, not to mention the challenge of obtaining images from space. In this paper, we aim to fill this gap by releasing a dataset for spacecraft detection, instance segmentation and part recognition. The main contribution of this work is the development of the dataset using images of space stations and satellites, with rich annotations including bounding boxes of spacecrafts and masks to the level of object parts, which are obtained with a mixture of automatic processes and manual efforts. We also provide evaluations with state-of-the-art methods in object detection and instance segmentation as a benchmark for the dataset. The link for downloading the proposed dataset can be found on https://github.com/Yurushia1998/SatelliteDataset.

cs.CV↗

arXiv2021

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding

Semantic parsing is challenging due to the structure gap and the semantic gap between utterances and logical forms. In this paper, we propose an unsupervised semantic parsing method - Synchronous Semantic Decoding (SSD), which can simultaneously resolve the semantic gap and the structure gap by jointly leveraging paraphrasing and grammar constrained decoding. Specifically, we reformulate semantic parsing as a constrained paraphrasing problem: given an utterance, our model synchronously generates its canonical utterance and meaning representation. During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly. Experimental results show that SSD is a promising approach and can achieve competitive unsupervised semantic parsing performance on multiple datasets.

cs.CL↗

arXiv2021

Bayesian Attention Belief Networks

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated model design. This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights with a hierarchy of gamma distributions, and an encoder network by stacking Weibull distributions with a deterministic-upward-stochastic-downward structure to approximate the posterior. The resulting auto-encoding networks can be optimized in a differentiable way with a variational lower bound. It is simple to convert any models with deterministic attention, including pretrained ones, to the proposed Bayesian attention belief networks. On a variety of language understanding tasks, we show that our method outperforms deterministic attention and state-of-the-art stochastic attention in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks. We further demonstrate the general applicability of our method on neural machine translation and visual question answering, showing great potential of incorporating our method into various attention-related tasks.

cs.LG↗