arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 595 records · Page 33Linked to original sources

arXiv2019

A Joint Planning and Learning Framework for Human-Aided Decision-Making

Conventional reinforcement learning (RL) allows an agent to learn policies via environmental rewards only, with a long and slow learning curve, especially at the beginning stage. On the contrary, human learning is usually much faster because prior and general knowledge and multiple information resources are utilized. In this paper, we propose a \textbf{P}lanner-\textbf{A}ctor-\textbf{C}ritic architecture for hu\textbf{MAN}-centered planning and learning (\textbf{PACMAN}), where an agent uses prior, high-level, deterministic symbolic knowledge to plan for goal-directed actions. PACMAN integrates Actor-Critic algorithm of RL to fine-tune its behavior towards both environmental rewards and human feedback. To the best our knowledge, This is the first unified framework where knowledge-based planning, RL, and human teaching jointly contribute to the policy learning of an agent. Our experiments demonstrate that PACMAN leads to a significant jump-start at the early stage of learning, converges rapidly and with small variance, and is robust to inconsistent, infrequent, and misleading feedback.

cs.AI↗

arXiv2019

Deep Object Co-segmentation via Spatial-Semantic Network Modulation

Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation. A backbone network is adopted to extract multi-resolution image features. With the multi-resolution features of the relevant images as input, we design a spatial modulator to learn a mask for each image. The spatial modulator captures the correlations of image feature descriptors via unsupervised learning. The learned mask can roughly localize the shared foreground object while suppressing the background. For the semantic modulator, we model it as a supervised image classification task. We propose a hierarchical second-order pooling module to transform the image features for classification use. The outputs of the two modulators manipulate the multi-resolution features by a shift-and-scale operation so that the features focus on segmenting co-object regions. The proposed model is trained end-to-end without any intricate post-processing. Extensive experiments on four image co-segmentation benchmark datasets demonstrate the superior accuracy of the proposed method compared to state-of-the-art methods.

cs.CV↗

arXiv2019

Object-Guided Instance Segmentation for Biological Images

Instance segmentation of biological images is essential for studying object behaviors and properties. The challenges, such as clustering, occlusion, and adhesion problems of the objects, make instance segmentation a non-trivial task. Current box-free instance segmentation methods typically rely on local pixel-level information. Due to a lack of global object view, these methods are prone to over- or under-segmentation. On the contrary, the box-based instance segmentation methods incorporate object detection into the segmentation, performing better in identifying the individual instances. In this paper, we propose a new box-based instance segmentation method. Mainly, we locate the object bounding boxes from their center points. The object features are subsequently reused in the segmentation branch as a guide to separate the clustered instances within an RoI patch. Along with the instance normalization, the model is able to recover the target object distribution and suppress the distribution of neighboring attached objects. Consequently, the proposed model performs excellently in segmenting the clustered objects while retaining the target object details. The proposed method achieves state-of-the-art performances on three biological datasets: cell nuclei, plant phenotyping dataset, and neural cells.

cs.CV↗

arXiv2019

FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10

Deep learning and Convolutional Neural Network (CNN) have becoming increasingly more popular and important in both academic and industrial areas in recent years cause they are able to provide better accuracy and result in classification, detection and recognition areas, compared to traditional approaches. Currently, there are many popular frameworks in the market for deep learning development, such as Caffe, TensorFlow, Pytorch, and most of frameworks natively support CPU and consider GPU as the mainline accelerator by default. FPGA device, viewed as a potential heterogeneous platform, still cannot provide a comprehensive support for CNN development in popular frameworks, in particular to the training phase. In this paper, we firstly propose the FeCaffe, i.e. FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e.g. training and inference with Caffe. Furthermore, we provide some benchmarks with FeCaffe by taking some classical CNN networks as examples, and further analysis of kernel execution time in details accordingly. Finally, some optimization directions including FPGA kernel design, system pipeline, network architecture, user case application and heterogeneous platform levels, have been proposed gradually to improve FeCaffe performance and efficiency. The result demonstrates the proposed FeCaffe is capable of supporting almost full features during CNN network training and inference respectively with high degree of design flexibility, expansibility and reusability for deep learning development. Compared to prior studies, our architecture can support more network and training settings, and current configuration can achieve 6.4x and 8.4x average execution time improvement for forward and backward respectively for LeNet.

cs.DC↗

arXiv2019

Privacy Preserving Location Data Publishing: A Machine Learning Approach

Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users' private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use $k$-means algorithm for this purpose. A variation of $k$-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to TDrive and Geolife location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework.

cs.LG↗

arXiv2019

Robust Matrix Completion State Estimation in Distribution Systems

Due to the insufficient measurements in the distribution system state estimation (DSSE), full observability and redundant measurements are difficult to achieve without using the pseudo measurements. The matrix completion state estimation (MCSE) combines the matrix completion and power system model to estimate voltage by exploring the low-rank characteristics of the matrix. This paper proposes a robust matrix completion state estimation (RMCSE) to estimate the voltage in a distribution system under a low-observability condition. Tradition state estimation weighted least squares (WLS) method requires full observability to calculate the states and needs redundant measurements to proceed a bad data detection. The proposed method improves the robustness of the MCSE to bad data by minimizing the rank of the matrix and measurements residual with different weights. It can estimate the system state in a low-observability system and has robust estimates without the bad data detection process in the face of multiple bad data. The method is numerically evaluated on the IEEE 33-node radial distribution system. The estimation performance and robustness of RMCSE are compared with the WLS with the largest normalized residual bad data identification (WLS-LNR), and the MCSE.

cs.LG↗

arXiv2019

Discovery of Metastable He I* $λ$10830 Mini-broad Absorption Lines and Very Narrow Paschen $α$ Emission Lines in the ULIRG Quasar IRAS F11119+3257

IRAS F11119+3257 is a quasar-dominated Ultra-Luminous InfraRed Galaxy, with a partially obscured narrow-line seyfert 1 nucleus. In this paper, we present the NIR spectroscopy of F11119+3257, in which we find unusual Paschen emission lines, and metastable He I* $λ$10830 absorption associated with the previously reported atomic sodium and molecular OH mini-BAL (Broad Absorption Line) outflow. Photo-ionization diagnosis confirms previous findings that the outflows are at kilo-parsec scales. Such large-scale outflows should produce emission lines. We indeed find that high-ionization emission lines ([O III], [Ne III], and [Ne V]) are dominated by blueshifted components at similar speeds to the mini-BALs. The blueshifted components are also detected in some low-ionization emission lines, such as [O II] $λ$3727 and some Balmer lines (H$α$, H$β$, and H$γ$), even though their cores are dominated by narrow ($FWHM_{\rm NEL} = 570\pm40$km s$^{-1}$) or broad components at the systemic redshift of $z=0.18966\pm0.00006$. The mass flow rate (230-730$~M_\odot \rm yr^{-1}$) and the kinetic luminosity ($\dot{E}_k \sim 10^{43.6-44.8} $erg s$^{-1}$) are then inferred jointly from the blueshifted emission and absorption lines. In the NIR spectrum of F11119+3257, we also find that the Paschen emission lines are unique, in which a very narrow ($FWHM=260\pm20~$km s$^{-1}$) component is shown in only Pa$α$. This narrow component most probably comes from heavily obscured star formation. Based on the Pa$α$ and Pa$β$ emissions, we obtain an extinction at the $H$ band, $A_H~>~2.1$ (or a reddenning of $E_{B-V}~>~$3.7), and a star formation rate of $SFR~>~130\rm M_\odot yr^{-1}$ that resembles the estimates inferred from the FIR emissions ($SFR_{\rm FIR} = 190\pm90$ $M_\odot$ yr$^{-1}$).

astro-ph.GA↗

arXiv2019

Revisiting black hole thermodynamics in massive gravity: charged particle absorption and shell of dust falling

We study the variation of the massive black hole in both normal and extended thermodynamic phase spaces via two methods. The first method includes a charged particle absorbed by the black hole, while the second method includes a shell of dust falling into the black hole. Using the former method, the first and second laws of thermodynamics are always satisfied in the normal phase space, while in the extended phase space, the first law of thermodynamics is also satisfied, but the validity of the second law of thermodynamics depends on the model parameters. Applying the latter method, the first and second laws of thermodynamics are both valid. We argue that the possible reason for the violation of the second law of thermodynamics via the former method may be attributed to the assumption that the change of internal energy of the black hole is equal to the energy of the particle. Finally, we show that the event horizon always exists to guarantee the validity of the weak cosmic censorship in both phase spaces, which means that the violation of the second law of thermodynamics under the assumption does not affect the weak cosmic censorship conjecture. This further supports our argument that the assumption in the first method may be the reason for the violation of the law and it requires deeper treatment.

gr-qc↗

arXiv2019

Profile of and Variability in Double-Peaked Balmer Emission Lines in 3C 445

We extract the multiple-epoch Balmer-line profiles of the heavily obscured quasar 3C 445 from the spectral curves in the literature, and analyze the emission-line profiles of the H$α$ and H$β$ lines and the profile variability in the H$α$ line in the large time interval of more than three decades. The profile comparison between the H$α$ and H$β$ lines shows that both Balmer lines share the profile with the same form, while the blue system of the H$β$ line is seriously weaker than that of the H$α$ line. Moreover, the blue system of the H$α$ line suddenly disappeared completely and then did not appear again, however the other two components did not exhibit significant variation in the velocity or the amplitude. These findings suggest that the blue system of 3C 445, as with SDSS J153636.22+044127.0 and its analogs, is probable the result of the shock-heated outflowing gases. The observation angle of almost edge-on which the previous studies suggested can easily produce the high-speed and high-temperature shock in the collision between the massive outflow and the inner surface of the dusty torus.

astro-ph.GA↗

arXiv2019

Protracted Kondo coherence with dilute carrier density in Cerium based nickel pnictides

Nozi$\grave{e}$res' exhaustion theory argues the temperature for coherently screening of all local moments in Kondo lattice could be much lower than the temperature of single moment screening with insufficient number of conduction electrons. Recent experiment [Luo et al, PNAS, 112,13520 (2015)] indicates the cerium based nickel pnictides $CeNi_{2-δ}As_2 (δ\approx0.28)$ with low carrier density is an ideal material to exam such protracted Kondo screening. Using the density functional theory and dynamical mean-field theory, we calculated the respective electronic structures of paramagnetic $CeNi_2As_2$/$CeNi_2P_2$. In contrast to structurally analogous layered iron pnictides, the electronic structures of the present systems show strong three-dimensionality with substantially small contributions of Ni-3d electrons to the carrier density. Moreover, we find significant Kondo resonance peaks in the compressed $CeNi_2As_2$ and $CeNi_2P_2$ at low temperatures, accompanied by topological changes of the Fermi surfaces. We also find similar quantum phase transition in $CeNi_2As_2$ driven by chemical pressure via the isovalence As$\rightarrow$P substitution.

cond-mat.str-el↗

arXiv2019

Anharmonicity Induced Supersolidity In Spin-Orbit Coupled Bose-Einstein Condensates

Supersolid, a fascinating quantum state of matter, features novel phenomena such as the non-classical rotational inertia and transport anomalies. It is a long standing issue of the coexistence of superfluidity and broken translational symmetry in condensed matter physics. By recent experimental advances to create tunable synthetic spin-orbit coupling in ultracold gases, such highly controllable atomic systems would provide new possibilities to access supersolidity with no counterpart in solids. Here we report that the combination of anharmonicity of trapping potential and spin-orbit coupling will provide a new paradigm to achieve supersolids. By means of imaginary time evolution of the Gross-Pitaevskii equation, we demonstrate that a supersolid state can be found when considering a trapped Rashba-type spin-orbit coupled bosonic atoms loaded in a one-dimensional optical lattice. Furthermore, a skyrmion-anti-skyrmion lattice is associated with the appearance of such supersoildity, indicating the topological nontrivial properties of our proposed supersolids.

cond-mat.quant-gas↗

arXiv2019

A Human-Centered Data-Driven Planner-Actor-Critic Architecture via Logic Programming

Recent successes of Reinforcement Learning (RL) allow an agent to learn policies that surpass human experts but suffers from being time-hungry and data-hungry. By contrast, human learning is significantly faster because prior and general knowledge and multiple information resources are utilized. In this paper, we propose a Planner-Actor-Critic architecture for huMAN-centered planning and learning (PACMAN), where an agent uses its prior, high-level, deterministic symbolic knowledge to plan for goal-directed actions, and also integrates the Actor-Critic algorithm of RL to fine-tune its behavior towards both environmental rewards and human feedback. This work is the first unified framework where knowledge-based planning, RL, and human teaching jointly contribute to the policy learning of an agent. Our experiments demonstrate that PACMAN leads to a significant jump-start at the early stage of learning, converges rapidly and with small variance, and is robust to inconsistent, infrequent, and misleading feedback.

cs.AI↗

arXiv2019

Optimal Function Approximation with Relu Neural Networks

We consider in this paper the optimal approximations of convex univariate functions with feed-forward Relu neural networks. We are interested in the following question: what is the minimal approximation error given the number of approximating linear pieces? We establish the necessary and sufficient conditions and uniqueness of optimal approximations, and give lower and upper bounds of the optimal approximation errors. Relu neural network architectures are then presented to generate these optimal approximations. Finally, we propose an algorithm to find the optimal approximations, as well as prove its convergence and validate it with experimental results.

cs.LG↗

arXiv2019

Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks

Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential. To evaluate and improve the effectiveness of watermark, watermark removal attracts increasing attention and becomes a hot research top. Current methods cast the watermark removal as an image-to-image translation problem where the encode-decode architectures with pixel-wise loss are adopted to transfer the transparent watermarked pixels into unmarked pixels. However, when a number of realistic images are presented, the watermarks are more likely to be unknown and diverse (i.e., the watermarks might be opaque or semi-transparent; the category and pattern of watermarks are unknown). When applying existing methods to the real-world scenarios, they mostly can not satisfactorily reconstruct the hidden information obscured under the complex and various watermarks (i.e., the residual watermark traces remain and the reconstructed images lack reality). To address this difficulty, in this paper, we present a new watermark processing framework using the conditional generative adversarial networks (cGANs) for visible watermark removal in the real-world application. The proposed method enables the watermark removal solution to be more closed to the photo-realistic reconstruction using a patch-based discriminator conditioned on the watermarked images, which is adversarially trained to differentiate the difference between the recovered images and original watermark-free images. Extensive experimental results on a large-scale visible watermark dataset demonstrate the effectiveness of the proposed method and clearly indicate that our proposed approach can produce more photo-realistic and convincing results compared with the state-of-the-art methods.

cs.CV↗

arXiv2019

Transfer Learning-Based Label Proportions Method with Data of Uncertainty

Learning with label proportions (LLP), which is a learning task that only provides unlabeled data in bags and each bag's label proportion, has widespread successful applications in practice. However, most of the existing LLP methods don't consider the knowledge transfer for uncertain data. This paper presents a transfer learning-based approach for the problem of learning with label proportions(TL-LLP) to transfer knowledge from source task to target task where both the source and target tasks contain uncertain data. Our approach first formulates objective model for the uncertain data and deals with transfer learning at the same time, and then proposes an iterative framework to build an accurate classifier for the target task. Extensive experiments have shown that the proposed TL-LLP method can obtain the better accuracies and is less sensitive to noise compared with the existing LLP methods.

cs.LG↗

arXiv2019

Sharpen Focus: Learning with Attention Separability and Consistency

Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks. Despite good localization for an individual class of interest, these techniques produce attention maps with substantially overlapping responses among different classes, leading to the problem of visual confusion and the need for discriminative attention. In this paper, we address this problem by means of a new framework that makes class-discriminative attention a principled part of the learning process. Our key innovations include new learning objectives for attention separability and cross-layer consistency, which result in improved attention discriminability and reduced visual confusion. Extensive experiments on image classification benchmarks show the effectiveness of our approach in terms of improved classification accuracy, including CIFAR-100 (+3.33%), Caltech-256 (+1.64%), ILSVRC2012 (+0.92%), CUB-200-2011 (+4.8%) and PASCAL VOC2012 (+5.73%).

cs.CV↗

arXiv2019

Multi-scale Cell Instance Segmentation with Keypoint Graph based Bounding Boxes

Most existing methods handle cell instance segmentation problems directly without relying on additional detection boxes. These methods generally fails to separate touching cells due to the lack of global understanding of the objects. In contrast, box-based instance segmentation solves this problem by combining object detection with segmentation. However, existing methods typically utilize anchor box-based detectors, which would lead to inferior instance segmentation performance due to the class imbalance issue. In this paper, we propose a new box-based cell instance segmentation method. In particular, we first detect the five pre-defined points of a cell via keypoints detection. Then we group these points according to a keypoint graph and subsequently extract the bounding box for each cell. Finally, cell segmentation is performed on feature maps within the bounding boxes. We validate our method on two cell datasets with distinct object shapes, and empirically demonstrate the superiority of our method compared to other instance segmentation techniques. Code is available at: https://github.com/yijingru/KG_Instance_Segmentation.

cs.CV↗

arXiv2019

Passively stable distribution of polarisation entanglement over 192 km of deployed optical fibre

Quantum key distribution (QKD) based on entangled photon pairs holds the potential for repeater-based quantum networks connecting clients over long distance. We demonstrate long-distance entanglement distribution by means of polarisation-entangled photon pairs through two successive deployed 96 km-long telecommunications fibres in the same submarine cable. One photon of each pair was detected directly after the source, while the other travelled the fibre cable in both directions for a total distance of 192 km and attenuation of 48 dB. The observed two-photon Bell state exhibited a fidelity 85% $\pm$ 2% and was stable over several hours. We employed neither active stabilisation of the quantum state nor chromatic dispersion compensation for the fibre.

quant-ph↗