arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 559 records · Page 31Linked to original sources

arXiv2020

Identifying Melanoma Images using EfficientNet Ensemble: Winning Solution to the SIIM-ISIC Melanoma Classification Challenge

We present our winning solution to the SIIM-ISIC Melanoma Classification Challenge. It is an ensemble of convolutions neural network (CNN) models with different backbones and input sizes, most of which are image-only models while a few of them used image-level and patient-level metadata. The keys to our winning are: (1) stable validation scheme (2) good choice of model target (3) carefully tuned pipeline and (4) ensembling with very diverse models. The winning submission scored 0.9600 AUC on cross validation and 0.9490 AUC on private leaderboard.

cs.CV↗

arXiv2020

Spin-wave focusing induced skyrmion generation

We propose a new method to generate magnetic skyrmions through spin-wave focusing in chiral ferromagnets.A lens is constructed to focus spin waves by a curved interface between two ferromagnetic thin films with different perpendicular magnetic anisotropies. Based on the principle of identical magnonic path length, we derive the lens contour that can be either elliptical or hyperbolical depending on the magnon refractive index. Micromagnetic simulations are performed to verify the theoretical design. It is found that under proper condition magnetic skyrmions emerge near the focus point of the lens where the spin-wave intensity has been significantly enhanced. A close investigation shows that a magnetic droplet first forms and then converts to the skyrmion accompanying with a change of topological charge. Phase diagram about the amplitude and duration-time of the exciting field for skyrmion generation is obtained. Our findings would be helpful for designing novel spintronic devices combining the advantages of skyrmionics and magnonics.

cond-mat.mes-hall↗

arXiv2020

Variance-Reduced Off-Policy Memory-Efficient Policy Search

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with convergence. A few variance-reduced on-policy policy gradient algorithms have been recently proposed that use methods from stochastic optimization to reduce the variance of the gradient estimate in the REINFORCE algorithm. However, these algorithms are not designed for the off-policy setting and are memory-inefficient, since they need to collect and store a large ``reference'' batch of samples from time to time. To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples. Empirical studies validate the effectiveness of the proposed approaches.

cs.LG↗

arXiv2020

A trusted-node-free eight-user metropolitan quantum communication network

Quantum communication is rapidly gaining popularity due to its high security and technological maturity. However, most implementations are limited to just two communicating parties (users). Quantum communication networks aim to connect a multitude of users. Here we present a fully connected quantum communication network on a city wide scale without active switching or trusted nodes. We demonstrate simultaneous and secure connections between all 28 pairings of 8 users. Our novel network topology is easily scalable to many users, allows traffic management features and minimises the infrastructure as well as the user hardware needed.

quant-ph↗

arXiv2020

A Broad Absorption Line Outflow Associated with the Broad Emission Line Region in the Quasar SDSS J075133.35+134548.3

We report the discovery of unusual broad absorption lines (BALs) in the bright quasar SDSS J075133.35+134548.3 at z~1, and present a detailed study of BAL and emission lines using the archived and newly obtained optical and NIR spectroscopic data. The BALs are detected tentatively in Mg II, Al III and reliably in HeI*3889, HeI*10830, which show complexed velocity structures splitting into two components: a high-velocity component (HV), with a blueshifted velocity range of -9300 ~ -3500 km/s, can be reliably detected tentatively in Mg II, Al III and reliably in HeI* 10830, whereas it is undetectable in HeI* 3889; and low-Velocity component (LV), with the velocity of -3500 ~ -1800 km/s, is only detected in HeI*3889 and HeI* 10830. With the BALs from different ions, the HV outflowing gas can be constrained to have a density n_H~10^10.3-10^11.4 cm^-3, a column density N_H~10^21 cm^-2 and an ionization parameter U~10^-1.83 - 10^-1.72; and thus inferring a distance of R_HV~0.5 pc from the central continuum source with a monochromatic luminosity of 7.0*10^45 erg/s at 5100 A. This distance is remarkable similar to that of normal broad emission line region (BLR) estimated according to the luminosity-distance from the reverberation experiments, suggesting the association between the BLR and the HV BAL outflowing gas. Interestingly enough, a blueshifted component is also significantly detected in Mg II and Al III broad emission lines (BELs), and the Al III/Mg II of such a BEL component can be reproduced by the physical parameters inferred from the HV BAL gas. The LV BAL gas very likely have a larger column density and a higher ionization level than the HV BAL gas, and hence a smaller distance than that of the latter. Further spectroscopy with high S/N ratio and broader wavelength coverage is needed to confirm this and shed new light on the possible connection between BALs and BELs.

astro-ph.GA↗

arXiv2020

Anisotropic ultrafast spin/valley dynamics in WTe2 films

WTe2 Weyl semimetal hosts the natural broken inversion symmetry and strong spin orbit coupling, making it promising for exotic spin/valley dynamics within a picosecond timescale. Here, we unveil an anisotropic ultrafast spin/valley dynamics in centimeter-scale, single-crystalline Td-WTe2 films using a femtosecond pump-probe technique at room temperature. We observe a transient (~0.8 ps) intra-valley transition and a subsequent polarization duration (~5 ps) during the whole spin/valley relaxation process. Furthermore, the relaxation exhibits the remarkable anisotropy of approximately six-fold and two-fold symmetries due to the intrinsic anisotropy along the crystalline orientation and the extrinsic matrix element effect, respectively. Our results offer a prospect for the ultrafast manipulation of spin/valleytronics in topological quantum materials for dissipationless high-speed spin/valleytronic devices.

cond-mat.mtrl-sci↗

arXiv2020

Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Oriented object detection in aerial images is a challenging task as the objects in aerial images are displayed in arbitrary directions and are usually densely packed. Current oriented object detection methods mainly rely on two-stage anchor-based detectors. However, the anchor-based detectors typically suffer from a severe imbalance issue between the positive and negative anchor boxes. To address this issue, in this work we extend the horizontal keypoint-based object detector to the oriented object detection task. In particular, we first detect the center keypoints of the objects, based on which we then regress the box boundary-aware vectors (BBAVectors) to capture the oriented bounding boxes. The box boundary-aware vectors are distributed in the four quadrants of a Cartesian coordinate system for all arbitrarily oriented objects. To relieve the difficulty of learning the vectors in the corner cases, we further classify the oriented bounding boxes into horizontal and rotational bounding boxes. In the experiment, we show that learning the box boundary-aware vectors is superior to directly predicting the width, height, and angle of an oriented bounding box, as adopted in the baseline method. Besides, the proposed method competes favorably with state-of-the-art methods. Code is available at https://github.com/yijingru/BBAVectors-Oriented-Object-Detection.

cs.CV↗

arXiv2020

Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature

Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly overlapped, resulting in inaccurate object recognition. Addressing this problem, we propose a novel adversarial network to synthesize compact semantic visual features for ZSL, consisting of a residual generator, a prototype predictor, and a discriminator. The residual generator is to generate the visual feature residual, which is integrated with a visual prototype predicted via the prototype predictor for synthesizing the visual feature. The discriminator is to distinguish the synthetic visual features from the real ones extracted from an existing categorization CNN. Since the generated residuals are generally numerically much smaller than the distances among all the prototypes, the distributions of the unseen-class features synthesized by the proposed network are less overlapped. In addition, considering that the visual features from categorization CNNs are generally inconsistent with their semantic features, a simple feature selection strategy is introduced for extracting more compact semantic visual features. Extensive experimental results on six benchmark datasets demonstrate that our method could achieve a significantly better performance than existing state-of-the-art methods by 1.2-13.2% in most cases.

cs.CV↗

arXiv2020

Energy recovery operation for continuous-wave X-ray free-electron lasers

A superconducting linear accelerator operating in continuous-wave mode could produce X-ray free electron lasers (XFEL) at megahertz repetition rate, with the capability that delivering wide spectral range coherent radiation to multi end stations. In this Letter, the energy recovery Linac (ERL) mode is proposed to flexibly control the electron beam energy for a continuous-wave superconducting Linac. Theoretical investigations and multi-dimensional numerical simulations are applied to the Linac case of Shanghai high-repetition-rate XFEL and extreme light facility. The results show that, with ERL operation in the last 25 cryo-modules, the strict requirements on RF power system could be significantly relaxed. And if one exhaust the RF power, the maximum electron beam energy can be enhanced from 8.74 GeV to 11.41GeV in ERL mode. The optimization of the ERL operation, the multi-energy electron beam transport and the XFEL performance improvements are presented.

physics.acc-ph↗

arXiv2020

Meta-Learning with Network Pruning

Meta-learning is a powerful paradigm for few-shot learning. Although with remarkable success witnessed in many applications, the existing optimization based meta-learning models with over-parameterized neural networks have been evidenced to ovetfit on training tasks. To remedy this deficiency, we propose a network pruning based meta-learning approach for overfitting reduction via explicitly controlling the capacity of network. A uniform concentration analysis reveals the benefit of network capacity constraint for reducing generalization gap of the proposed meta-learner. We have implemented our approach on top of Reptile assembled with two network pruning routines: Dense-Sparse-Dense (DSD) and Iterative Hard Thresholding (IHT). Extensive experimental results on benchmark datasets with different over-parameterized deep networks demonstrate that our method not only effectively alleviates meta-overfitting but also in many cases improves the overall generalization performance when applied to few-shot classification tasks.

cs.LG↗

arXiv2020

Ion specificity modulated inhomogeneous interfacial flow inhibits bubble coalescence in electrolyte solutions

Inhibition of bubble coalescence in electrolyte solutions enables the formation of oceanic whitecaps and affects the heat and mass transfer in many bubble related engineering processes. For different electrolytes, the ability to inhibit bubble coalescence correlates to the ion specificity at the air water interface at an abnormal cation-anion pair relationship, rather than the typically expected cation or anion series that was widely reported in atmospheric, bio- and chemical processes. Here we show that the inhomogeneous interfacial flow, at a different electrolyte concentration from the solution because of the surface specificity of both cation and anion, contributes to the bubble coalescence inhibition behavior in electrolyte solutions. The interfacial flow, achieved with the mobile air-water interface, contributes to the continuous change of electrolyte concentration within the liquid film formed between two colliding bubbles, thereby resulting in a concentration gradient of electrolytes between the thin film and the bulk solution. The electrolyte concentration gradient, hence surface tension gradient, becomes significant to resist film thinning when the film thickness reaches tens of nanometers. The retarded film thinning between two bubbles and delayed bubble coalescence were experimentally captured by high-speed interferometry and quantitatively explained by the proposed electrolyte transportation model. This finding clearly highlights the coupled effect of interfacial flow and ion specificity, and shows important implications for improved understanding of ocean waves, for future development of colloidal science in high concentration electrolyte solutions that is critical for biology, and benefits many applied fields like water splitting and mineral extraction.

cond-mat.soft↗

arXiv2020

APPLD: Adaptive Planner Parameter Learning from Demonstration

Existing autonomous robot navigation systems allow robots to move from one point to another in a collision-free manner. However, when facing new environments, these systems generally require re-tuning by expert roboticists with a good understanding of the inner workings of the navigation system. In contrast, even users who are unversed in the details of robot navigation algorithms can generate desirable navigation behavior in new environments via teleoperation. In this paper, we introduce APPLD, Adaptive Planner Parameter Learning from Demonstration, that allows existing navigation systems to be successfully applied to new complex environments, given only a human teleoperated demonstration of desirable navigation. APPLD is verified on two robots running different navigation systems in different environments. Experimental results show that APPLD can outperform navigation systems with the default and expert-tuned parameters, and even the human demonstrator themselves.

cs.RO↗

arXiv2020

RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network

Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. Without directly interactive with training examples, the generative model can be fully used to estimate the underlying distribution of an original dataset while the discriminative model can examine the quality of the generated samples by comparing the label values with the training examples. However, when GANs are applied on sensitive or private training examples, such as medical or financial records, it is still probable to divulge individuals' sensitive and private information. To mitigate this information leakage and construct a private GAN, in this work we propose a Rényi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random noises on the value of the loss function during training. Moreover, we derive the analytical results of the total privacy loss under the subsampling method and cumulated iterations, which show its effectiveness on the privacy budget allocation. In addition, in order to mitigate the negative impact brought by the injecting noise, we enhance the proposed algorithm by adding an adaptive noise tuning step, which will change the volume of added noise according to the testing accuracy. Through extensive experimental results, we verify that the proposed algorithm can achieve a better privacy level while producing high-quality samples compared with a benchmark DP-GAN scheme based on noise perturbation on training gradients.

cs.LG↗

arXiv2020

Finite-Sample Analysis of Proximal Gradient TD Algorithms

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our knowledge, no finite-sample analysis has been done. Moreover, there has been not much work on finite-sample analysis for convergent off-policy reinforcement learning algorithms. In this paper, we formulate GTD methods as stochastic gradient algorithms w.r.t.~a primal-dual saddle-point objective function, and then conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Two revised algorithms are also proposed, namely projected GTD2 and GTD2-MP, which offer improved convergence guarantees and acceleration, respectively. The results of our theoretical analysis show that the GTD family of algorithms are indeed comparable to the existing LSTD methods in off-policy learning scenarios.

cs.LG↗

arXiv2020

A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection

Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation. Motivated by this, in this paper, we propose a lightweight neural network to reduce the computational and spatial complexity and facilitate the change detection on an edge device. In the proposed network, we replace normal convolutional layers with bottleneck layers that keep the same number of channels between input and output. Next, we employ dilated convolutional kernels with a few non-zero entries that reduce the running time in convolutional operators. Comparing with the conventional convolutional neural network, our light-weighted neural network will be more efficient with fewer parameters. We verify our light-weighted neural network on four sets of bitemporal SAR images. The experimental results show that the proposed network can obtain better performance than the conventional CNN and has better model generalization, especially on the challenging datasets with complex scenes.

eess.IV↗

arXiv2020

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 1: Theory

For one-hidden-layer ReLU networks, we prove that all differentiable local minima are global inside differentiable regions. We give the locations and losses of differentiable local minima, and show that these local minima can be isolated points or continuous hyperplanes, depending on an interplay between data, activation pattern of hidden neurons and network size. Furthermore, we give necessary and sufficient conditions for the existence of saddle points as well as non-differentiable local minima, and their locations if they exist.

cs.LG↗

arXiv2020

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 2: Experiments and Analysis

The existence of local minima for one-hidden-layer ReLU networks has been investigated theoretically in [8]. Based on the theory, in this paper, we first analyze how big the probability of existing local minima is for 1D Gaussian data and how it varies in the whole weight space. We show that this probability is very low in most regions. We then design and implement a linear programming based approach to judge the existence of genuine local minima, and use it to predict whether bad local minima exist for the MNIST and CIFAR-10 datasets, and find that there are no bad differentiable local minima almost everywhere in weight space once some hidden neurons are activated by samples. These theoretical predictions are verified experimentally by showing that gradient descent is not trapped in the cells from which it starts. We also perform experiments to explore the count and size of differentiable cells in the weight space.

cs.LG↗

arXiv2020

Operational definition of a quantum speed limit

The quantum speed limit is a fundamental concept in quantum mechanics, which aims at finding the minimum time scale or the maximum dynamical speed for some fixed targets. In a large number of studies in this field, the construction of valid bounds for the evolution time is always the core mission, yet the physics behind it and some fundamental questions like which states can really fulfill the target, are ignored. Understanding the physics behind the bounds is at least as important as constructing attainable bounds. Here we provide an operational approach for the definition of the quantum speed limit, which utilizes the set of states that can fulfill the target to define the speed limit. Its performances in various scenarios have been investigated. For time-independent Hamiltonians, it is inverse-proportional to the difference between the highest and lowest energies. The fact that its attainability does not require a zero ground-state energy suggests it can be used as an indicator of quantum phase transitions. For time-dependent Hamiltonians, it is shown that contrary to the results given by existing bounds, the true speed limit should be independent of the time. Moreover, in the case of spontaneous emission, we find a counterintuitive phenomenon that a lousy purity can benefit the reduction of the quantum speed limit.

quant-ph↗