arXiv subjects

Bin Jiang

Publications and source records attributed to Bin Jiang.

At least 109 records · Page 6Linked to original sources

arXiv2020

Constrained R-CNN: A general image manipulation detection model

Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on manipulation localization and overlook manipulation classification. To address these issues, we propose a coarse-to-fine architecture named Constrained R-CNN for complete and accurate image forensics. First, the learnable manipulation feature extractor learns a unified feature representation directly from data. Second, the attention region proposal network effectively discriminates manipulated regions for the next manipulation classification and coarse localization. Then, the skip structure fuses low-level and high-level information to refine the global manipulation features. Finally, the coarse localization information guides the model to further learn the finer local features and segment out the tampered region. Experimental results show that our model achieves state-of-the-art performance. Especially, the F1 score is increased by 28.4%, 73.2%, 13.3% on the NIST16, COVERAGE, and Columbia dataset.

cs.CV↗

arXiv2020

Automatic Segmentation, Feature Extraction and Comparison of Healthy and Stroke Cerebral Vasculature

Accurate segmentation of cerebral vasculature and a quantitative assessment of cerebrovascular morphology is critical to various diagnostic and therapeutic purposes and is pertinent to studying brain health and disease. However, this is still a challenging task due to the complexity of the vascular imaging data. We propose an automated method for cerebral vascular segmentation without the need of any manual intervention as well as a method to skeletonize the binary volume to extract vascular geometric features which can characterize vessel structure. We combine a probabilistic vessel-enhancing filtering with an active-contour technique to segment magnetic resonance and computed tomography angiograms (MRA and CTA) and subsequently extract the vessel centerlines and diameters to calculate the geometrical properties of the vasculature. Our method was validated using a 3D phantom of the Circle-of-Willis region with 84% mean Dice Similarity and 85% mean Pearson Correlation with minimal modified Hausdorff distance error. We applied this method to a dataset of healthy subjects and stroke patients and present a quantitative comparison between them. We found significant differences in the geometric features including total length (2.88 +/- 0.38 m for healthy and 2.20 +/- 0.67 m for stroke), volume (40.18 +/- 25.55 ml for healthy and 34.43 +/- 21.83 ml for stroke), tortuosity (3.24 +/- 0.88 rad/cm for healthy and 5.80 +/- 0.92 rad/cm for stroke) and fractality (box dimension 1.36 +/- 0.28 for healthy vs. 1.69 +/- 0.20 for stroke). This technique can be applied on any imaging modality and can be used in the future to automatically obtain the 3D segmented vasculature for diagnosis and treatment planning of Stroke and other cerebrovascular diseases (CVD) in the clinic and also to study the morphological changes caused by various CVD.

q-bio.QM↗

arXiv2020

Context-Integrated and Feature-Refined Network for Lightweight Object Parsing

Semantic segmentation for lightweight object parsing is a very challenging task, because both accuracy and efficiency (e.g., execution speed, memory footprint or computational complexity) should all be taken into account. However, most previous works pay too much attention to one-sided perspective, either accuracy or speed, and ignore others, which poses a great limitation to actual demands of intelligent devices. To tackle this dilemma, we propose a novel lightweight architecture named Context-Integrated and Feature-Refined Network (CIFReNet). The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM). The LRM is designed to ease the propagation of spatial information between low-level and high-level stages. Furthermore, channel attention mechanism is introduced into the process of long-skip learning to boost the quality of low-level feature refinement. Meanwhile, the MCIM consists of three cascaded Dense Semantic Pyramid (DSP) blocks with image-level features, which is presented to encode multiple context information and enlarge the field of view. Specifically, the proposed DSP block exploits a dense feature sampling strategy to enhance the information representations without significantly increasing the computation cost. Comprehensive experiments are conducted on three benchmark datasets for object parsing including Cityscapes, CamVid, and Helen. As indicated, the proposed method reaches a better trade-off between accuracy and efficiency compared with the other state-of-the-art methods.

cs.CV↗

arXiv2020

Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy

An efficient and trajectory-free active learning method is proposed to automatically sample data points for constructing globally accurate reactive potential energy surfaces (PESs) using neural networks (NNs). Although NNs do not provide the predictive variance as the Gaussian process regression does, we can alternatively minimize the negative of the squared difference surface (NSDS) given by two different NN models to actively locate the point where the PES is least confident. A batch of points in the minima of this NSDS can be iteratively added into the training set to improve the PES. The configuration space is gradually and globally covered with no need to run classical trajectory (or equivalently molecular dynamics) simulations. Through refitting the available analytical PESs of H3 and OH3 reactive systems, we demonstrate the efficiency and robustness of this new strategy, which enables fast convergence of the reactive PESs with respect to the number of points in terms of quantum scattering probabilities.

physics.chem-ph↗

arXiv2020

Joint Beamforming And Power Splitting Design For C-RAN With Multicast Fronthaul

In this paper, we investigate the joint beamforming and power splitting design problem in a base station (BS) cluster-based cloud radio access network (C-RAN) with multicast fronthaul, where users are jointly served by BSs within each cluster. Meanwhile, each user can simultaneously obtain information and energy from received signals. On this basis, under predefined minimum harvested energy of each user and maximum transmit power of each BS and central processor, we formulate a sum rate maximization problem by jointly optimizing multicast fronthaul beamforming, cooperative access beamforming and power split ratios. Due to the difficulty in solving the formulated problem, we first transform it into a convex one by successive convex approximate and semidefinite program (SDP) relaxation techniques, and then propose an effective iterative algorithm. Moreover, we design a randomization method that can always obtain the rank-one solution. Finally, numerical results are conducted to validate the effectiveness of our proposed algorithm.

cs.IT↗

arXiv2019

Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals

Nonadiabatic effects in chemical reaction at metal surfaces, due to excitation of electron-hole pairs, stand at the frontier of the studies of gas-surface reaction dynamics. However, the first principles description of electronic excitation remains challenging. In an efficient molecular dynamics with electronic friction (MDEF) method, the nonadiabatic couplings are effectively included in a so-called electronic friction tensor (EFT), which can be computed from first-order time-dependent perturbation theory (TDPT) in terms of density functional theory (DFT) orbitals. This second-rank tensor depends on adsorbate position and features a complicated transformation with regard to the intrinsic symmetry operations of the system. In this work, we develop a new symmetry-adapted neural network representation of EFT, based on our recently proposed embedded atom neural network (EANN) framework. Inspired by the derivation of the nonadiabatic coupling matrix, we represent the tensorial friction by the first and second derivatives of multiple outputs of NNs with respect to atomic Cartesian coordinates. This rigorously preserves the positive semidefiniteness, directional property, and correct symmetry-equivariance of EFT. Unlike previous methods, our new approach can readily include both molecular and surface degrees of freedom, regardless of the type of surface. Tests on the H2+Ag(111) system show that this approach yields an accurate, efficient, and continuous representation of EFT, making it possible to perform large scale TDPT-based MDEF simulations to study both adiabatic and nonadiabatic energy dissipation in a unified framework.

physics.chem-ph↗

arXiv2019

One-Stage Inpainting with Bilateral Attention and Pyramid Filling Block

Recent deep learning based image inpainting methods which utilize contextual information and two-stage architecture have exhibited remarkable performance. However, the two-stage architecture is time-consuming, the contextual information lack high-level semantics and ignores both the semantic relevance and distance information of hole's feature patches, these limitations result in blurry textures and distorted structures of final result. Motivated by these observations, we propose a new deep generative model-based approach, which trains a shared network twice with different targets and utilizes a single network during the testing phase, so that we can effectively save inference time. Specifically, the targets of two training steps are structure reconstruction and texture generation respectively. During the second training, we first propose a Pyramid Filling Block (PF-block) to utilize the high-level features that the hole regions has been filled to guide the filling process of low-level features progressively, the missing content can be filled from deep to shallow in a pyramid fashion. Then, inspired by the classical bilateral filter [30], we propose the Bilateral Attention layer (BA-layer) to optimize filled feature map, which synthesizes feature patches at each position by computing weighted sums of the surrounding feature patches, these weights are derived by considering both distance and value relationships between feature patches, thus making the visually plausible inpainting results. Finally, experiments on multiple publicly available datasets show the superior performance of our approach.

cs.CV↗

arXiv2019

Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network

Recent deep learning based salient object detection methods which utilize both saliency and boundary features have achieved remarkable performance. However, most of them ignore the complementarity between saliency features and boundary features, thus get worse predictions in scenes with low contrast between foreground and background. To address this issue, we propose a novel Recurrent Two-Stream Guided Refinement Network (RTGRNet) that consists of iterating Two-Stream Guided Refinement Modules (TGRMs). TGRM consists of a Guide Block and two feature streams: saliency and boundary, the Guide Block utilizes the refined features after previous TGRM to further improve the performance of two feature streams in current TGRM. Meanwhile, the low-level integrated features are also utilized as a reference to get better details. Finally, we progressively refine these features by recurrently stacking more TGRMs. Extensive experiments on six public datasets show that our proposed RTGRNet achieves the state-of-the-art performance in salient object detection.

cs.CV↗

arXiv2019

Ring Polymer Molecular Dynamics in Gas-Surface Reactions: Inclusion of Quantum Effects Made Simple

Accurately modeling gas-surface collision dynamics presents a great challenge for theory, especially in the low energy (or temperature) regime where quantum effects are important. Here, a path integral based non-equilibrium ring polymer molecular dynamics (NE-RPMD) approach is adapted to calculate dissociative initial sticking probabilities (S0) of H2 on Cu(111) and D2O on Ni(111), revealing distinct quantum nature in the two benchmark surface reactions. NE-RPMD successfully captures quantum tunneling in H2 dissociation at very low energies, where the quasi-classical trajectory (QCT) method suddenly fails. Additionally, QCT substantially overestimates S0 of D2O due to severe zero point energy (ZPE) leakage, even at collision energies higher than the ZPE-corrected barrier. Immune to such a problem, NE-RPMD predicts S0 values of D2O in much improved agreement with the benchmark results obtained by the accurate but expensive quantum wavepacket method. Our results suggest NE-RPMD as a promising approach to model quantum effects in gas-surface reactions.

physics.chem-ph↗

arXiv2019

Strong Vibrational Relaxation of NO Scattered from Au(111): Importance of an Accurate Adiabatic Potential Energy Surface

Experimental observations of multi-quantum relaxation of highly vibrationally excited NO scattering from Au(111) are a benchmark for the breakdown of Born-Oppenheimer approximation in molecule-surface systems. This remarkable vibrational inelasticity was long thought to be almost exclusively mediated by electron transfer; but, no theories have quantitatively reproduced various experimental data. This was suggested to be due to errors in the adiabatic potential energy surface (PES) used in those studies. Here, we investigate electronically adiabatic molecular dynamics of this system with a globally accurate high dimensional PES, newly developed with neural networks from first principles. The NO vibrational energy loss is much larger than that on earlier adiabatic PES. Additionally, the translational inelasticity and translational energy dependence of vibrational inelasticity are also more accurately reproduced. There is reason to be optimistic that electronically nonadiabatic theories using this adiabatic PES as a starting point might accurately reproduce experimental results on this important system.

physics.chem-ph↗

arXiv2019

Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation

We propose a simple, but efficient and accurate machine learning (ML) model for developing high-dimensional potential energy surface. This so-called embedded atom neural network (EANN) approach is inspired by the well-known empirical embedded atom method (EAM) model used in condensed phase. It simply replaces the scalar embedded atom density in EAM with a Gaussian-type orbital based density vector, and represents the complex relationship between the embedded density vector and atomic energy by neural networks. We demonstrate that the EANN approach is equally accurate as several established ML models in representing both big molecular and extended periodic systems, yet with much fewer parameters and configurations. It is highly efficient as it implicitly contains the three-body information without an explicit sum of the conventional costly angular descriptors. With high accuracy and efficiency, EANN potentials can vastly accelerate molecular dynamics and spectroscopic simulations in complex systems at ab initio level.

physics.chem-ph↗

arXiv2019

Alexander's Wholeness as the Scientific Foundation of Sustainable Urban Design and Planning

As Christopher Alexander conceived and defined through his life's work - The Nature of Order - wholeness is a recursive structure that recurs in space and matter and is reflected in human minds and cognition. Based on the definition of wholeness, a mathematical model of wholeness, together with its topological representation, has been developed, and it is able to address not only why a structure is beautiful, but also how much beauty the structure has. Given the circumstance, this paper is attempted to argue for the wholeness as the scientific foundation of sustainable urban design and planning, with the help of the mathematical model and topological representation. We start by introducing the wholeness as a mathematical structure of physical space that pervasively exists in our surroundings, along with two fundamental laws - scaling law and Tobler's law - that underlie the 15 properties for characterizing and making living structures. We argue that urban design and planning can be considered to be wholeness-extending processes, guided by two design principles of differentiation and adaptation, to transform a space - in a piecemeal fashion - into a living or more living structure. We further discuss several other urban design theories and how they can be justified by and placed within the theory of wholeness. With the wholeness as the scientific foundation, urban design can turn into a rigorous science with creation of living structures as the primary aim. Keywords: Beauty, life, scaling law, adaptation, differentiation, and organic world view

physics.soc-ph↗

arXiv2019

Living Structure Down to Earth and Up to Heaven: Christopher Alexander

Discovered by Christopher Alexander, living structure is a physical phenomenon, through which the quality of the built environment or artifacts can be judged objectively. It bears two distinguished properties just like a tree: "far more small things than large ones" across all scales, and "more or less similar things" on each scale. As a physical phenomenon, and mathematical concept, living structure is essentially empirical, discovered and developed from miniscule observation in nature- and human-made things, and it affects our daily lives in some substantial ways, such as where to put a table or a flower vase in a room, helping us to make beautiful things and environments. Living structure is not only empirical, but also philosophical and visionary, enabling us to see the world and space in more meaningful ways. This paper is intended to defend living structure as a physical phenomenon, clarifying some common questions and misgivings surrounding Alexander's design thoughts, such as the objective or structural nature of beauty, building styles advocated by Alexander, and mysterious nature of his concepts. We first illustrate living structure - essentially organized complexity, as advocated by the late Jane Jacobs (1916-2006) - that is governed by two fundamental laws (scaling law and Tobler's law), and generated in some step by step fashion by two design principles (differentiation and adaptation) through the 15 structural properties. We then verify why living structure is primarily empirical, drawing evidence from Alexander's own work, as well as our case studies applied to the Earth's surface including cities, streets, and buildings, and two logos. Before reaching conclusions, we concentrate on the most mysterious part of Alexander's work - the hypothesized "I" - as a substance that pervasively exists everywhere, in order to make better sense of living structure in our minds.

physics.soc-ph↗

arXiv2019

A Recursive Definition of Goodness of Space for Bridging the Concepts of Space and Place for Sustainability

Conceived and developed by Christopher Alexander through his life's work: The Nature of Order, wholeness is defined as a mathematical structure of physical space in our surroundings. Yet, there was no mathematics, as Alexander admitted then, that was powerful enough to capture his notion of wholeness. Recently, a mathematical model of wholeness, together with its topological representation, has been developed that is capable of addressing not only why a space is good, but also how much goodness the space has. This paper develops a structural perspective on goodness of space - both large- and small-scale - in order to bridge two basic concepts of space and place through the very concept of wholeness. The wholeness provides a de facto recursive definition of goodness of space from a holistic and organic point of view. A space is good, genuinely and objectively, if its adjacent spaces are good, the larger space to which it belongs is good, and what is contained in the space is also good. Eventually, goodness of space - sustainability of space - is considered a matter of fact rather than of opinion under the new view of space: space is neither lifeless nor neutral, but a living structure capable of being more living or less living, or more sustainable or less sustainable. Under the new view of space, geography or architecture will become part of complexity science, not only for understanding complexity, but also for making and remaking complex or living structures. Keywords: Scaling law, head/tail breaks, living structure, beauty, streets, cities

physics.soc-ph↗

arXiv2019

Coherent Semantic Attention for Image Inpainting

The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image. However, the existing methods often generate contents with blurry textures and distorted structures due to the discontinuity of the local pixels. From a semantic-level perspective, the local pixel discontinuity is mainly because these methods ignore the semantic relevance and feature continuity of hole regions. To handle this problem, we investigate the human behavior in repairing pictures and propose a fined deep generative model-based approach with a novel coherent semantic attention (CSA) layer, which can not only preserve contextual structure but also make more effective predictions of missing parts by modeling the semantic relevance between the holes features. The task is divided into rough, refinement as two steps and model each step with a neural network under the U-Net architecture, where the CSA layer is embedded into the encoder of refinement step. To stabilize the network training process and promote the CSA layer to learn more effective parameters, we propose a consistency loss to enforce the both the CSA layer and the corresponding layer of the CSA in decoder to be close to the VGG feature layer of a ground truth image simultaneously. The experiments on CelebA, Places2, and Paris StreetView datasets have validated the effectiveness of our proposed methods in image inpainting tasks and can obtain images with a higher quality as compared with the existing state-of-the-art approaches.

cs.CV↗

arXiv2019

Adiabatic and Nonadiabatic Energy Dissipation during Scattering of Vibrationally Excited CO from Au(111)

A high-dimensional potential energy surface (PES) for CO interaction with the Au(111) surface is developed using a machine-learning algorithm. Including both molecular and surface coordinates, this PES enables the simulation of the recent experiment on scattering of vibrationally excited CO from Au(111). Trapping in a physisorption well is observed to increase with decreasing incidence energy. While energy dissipation of physisorbed CO is slow, due to weak coupling with both the phonons and electron-hole pairs, its access to the chemisorption well facilitates fast vibrational relaxation of CO through nonadiabatic coupling with surface electron-hole pairs.

physics.chem-ph↗

arXiv2018

Why Topology Matters in Predicting Human Activities

Geographic space is better understood through the topological relationship of the underlying streets (note: entire streets rather than street segments), which enables us to see scaling or fractal or living structure of far more less-connected streets than well-connected ones. It is this underlying scaling structure that makes human activities predictable, albeit in the sense of collective rather than individual human moving behavior. This topological analysis has not yet received its deserved attention in the literature, as many researchers continue to rely on segment analysis for predicting human activities. The segment-analysis-based methods are essentially geometric, with a focus on geometric details of locations, lengths, and directions, and are unable to reveal the scaling property, which means they cannot be used for human activities prediction. We conducted a series of case studies using London streets and tweet location data, based on related concepts such as natural streets, and natural street segments (or street segments for short), axial lines, and axial line segments (or line segments for short). We found that natural streets are the best representation in terms of human activities or traffic prediction, followed by axial lines, and that neither street segments nor line segments bear a good correlation between network parameters and tweet locations. These findings point to the fact that the reason why axial lines-based space syntax, or the kind of topological analysis in general, works has little to do with individual human travel behavior or ways that human conceptualize distances or spaces. Instead, it is the underlying scaling hierarchy of streets - numerous least-connected, a very few most-connected, and some in between the least- and most-connected - that makes human activities predictable.

physics.soc-ph↗

arXiv2018

Spatial Heterogeneity, Scale, Data Character, and Sustainable Transport in the Big Data Era

In light of the emergence of big data, I have advocated and argued for a paradigm shift from Tobler's law to scaling law, from Euclidean geometry to fractal geometry, from Gaussian statistics to Paretian statistics, and - more importantly - from Descartes' mechanistic thinking to Alexander's organic thinking. Fractal geometry falls under the third definition of fractal - that is, a set or pattern is fractal if the scaling of far more small things than large ones recurs multiple times (Jiang and Yin 2014) - rather than under the second definition of fractal, which requires a power law between scales and details (Mandelbrot 1982). The new fractal geometry is more towards living geometry that "follows the rules, constraints, and contingent conditions that are, inevitably, encountered in the real world" (Alexander et al. 2012, p. 395), not only for understanding complexity, but also for creating complex or living structure (Alexander 2002-2005). This editorial attempts to clarify why the paradigm shift is essential and to elaborate on several concepts, including spatial heterogeneity (scaling law), scale (or the fourth meaning of scale), data character (in contrast to data quality), and sustainable transport in the big data era.

cs.DB↗