arXiv subjects

Yuhang Jiang

Publications and source records attributed to Yuhang Jiang.

At least 55 records · Page 3Linked to original sources

arXiv2022

Improved lightweight identification of agricultural diseases based on MobileNetV3

At present, the identification of agricultural pests and diseases has the problem that the model is not lightweight enough and difficult to apply. Based on MobileNetV3, this paper introduces the Coordinate Attention block. The parameters of MobileNetV3-large are reduced by 22%, the model size is reduced by 19.7%, and the accuracy is improved by 0.92%. The parameters of MobileNetV3-small are reduced by 23.4%, the model size is reduced by 18.3%, and the accuracy is increased by 0.40%. In addition, the improved MobileNetV3-small was migrated to Jetson Nano for testing. The accuracy increased by 2.48% to 98.31%, and the inference speed increased by 7.5%. It provides a reference for deploying the agricultural pest identification model to embedded devices.

cs.CV↗

arXiv2021

Imaging topological torus lattice from an electron crystal in twisted mono-bilayer graphene

A variety of exotic quantum phases of matter have been created by Van der Waals heterostructures. Moreover, these twisted heterostructures provide a feasible way of braiding correlation effect and nontrivial band topology together. Here, through a comprehensive spectrum study, we report the discovery of topological torus lattice in twisted mono-bilayer graphene. The strong Coulomb correlations give rise to an unusual charge localization behavior within the moiré supercell, leading to an electron crystal. The nontrivial band topology is encoded into the electron crystal, which would result in spatial modulated Chern numbers, and is evidenced by an emergent topological torus lattice state. Our result illustrates an efficient strategy for entwining and engineering topological physics with a strong electron correlation.

cond-mat.mes-hall↗

arXiv2021

Wasserstein Unsupervised Reinforcement Learning

Unsupervised reinforcement learning aims to train agents to learn a handful of policies or skills in environments without external reward. These pre-trained policies can accelerate learning when endowed with external reward, and can also be used as primitive options in hierarchical reinforcement learning. Conventional approaches of unsupervised skill discovery feed a latent variable to the agent and shed its empowerment on agent's behavior by mutual information (MI) maximization. However, the policies learned by MI-based methods cannot sufficiently explore the state space, despite they can be successfully identified from each other. Therefore we propose a new framework Wasserstein unsupervised reinforcement learning (WURL) where we directly maximize the distance of state distributions induced by different policies. Additionally, we overcome difficulties in simultaneously training N(N >2) policies, and amortizing the overall reward to each step. Experiments show policies learned by our approach outperform MI-based methods on the metric of Wasserstein distance while keeping high discriminability. Furthermore, the agents trained by WURL can sufficiently explore the state space in mazes and MuJoCo tasks and the pre-trained policies can be applied to downstream tasks by hierarchical learning.

cs.LG↗

arXiv2021

Combining dissimilarity measure for the study of evolution in scientific fields

The evolution of scientific fields has been attracting much attention in recent years. One of the key issues in evolution of scientific field is to quantify the dissimilarity between two collections of scientific publications in literature. Many existing works study the evolution based on one or two dissimilarity measures, despite the fact that there are many different dissimilarity measures. Finding the appropriate dissimilarity measures among such a collection of choices is of fundamental importance to the study of scientific evolution. In this article, we develop a new measure of the evolution combining twelve keyword-based temporal dissimilarities of the scientific fields using the method of principal component analysis. To demonstrate the usage of this new measure, we chose four scientific fields: environmental studies, information science & library science, mechanical informatics, and religion. A database consisting of 274453 bibliographic records in these four chosen fields from 1991 to 2019 are built. The results show that all these four scientific fields share an overall decreasing trend in evolution from 1991 to 2019 and different fields exhibits different evolution patterns during different time periods.

cs.DL↗

arXiv2021

Reducing Conservativeness Oriented Offline Reinforcement Learning

In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value function. However, exorbitant conservation tends to impair the policy's generalization ability and degrade its performance, especially for the mixed datasets. In this paper, we propose the method of reducing conservativeness oriented reinforcement learning. On the one hand, the policy is trained to pay more attention to the minority samples in the static dataset to address the data imbalance problem. On the other hand, we give a tighter lower bound of value function than previous methods to discover potential optimal actions. Consequently, our proposed method is able to tackle the skewed distribution of the provided dataset and derive a value function closer to the expected value function. Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods in D4RL offline reinforcement learning evaluation tasks and our own designed mixed datasets.

cs.LG↗

arXiv2021

PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation

6D pose estimation from a single RGB image is a challenging and vital task in computer vision. The current mainstream deep model methods resort to 2D images annotated with real-world ground-truth 6D object poses, whose collection is fairly cumbersome and expensive, even unavailable in many cases. In this work, to get rid of the burden of 6D annotations, we formulate the 6D pose refinement as a Markov Decision Process and impose on the reinforcement learning approach with only 2D image annotations as weakly-supervised 6D pose information, via a delicate reward definition and a composite reinforced optimization method for efficient and effective policy training. Experiments on LINEMOD and T-LESS datasets demonstrate that our Pose-Free approach is able to achieve state-of-the-art performance compared with the methods without using real-world ground-truth 6D pose labels.

cs.CV↗

arXiv2021

Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning

Reward decomposition is a critical problem in centralized training with decentralized execution~(CTDE) paradigm for multi-agent reinforcement learning. To take full advantage of global information, which exploits the states from all agents and the related environment for decomposing Q values into individual credits, we propose a general meta-learning-based Mixing Network with Meta Policy Gradient~(MNMPG) framework to distill the global hierarchy for delicate reward decomposition. The excitation signal for learning global hierarchy is deduced from the episode reward difference between before and after "exercise updates" through the utility network. Our method is generally applicable to the CTDE method using a monotonic mixing network. Experiments on the StarCraft II micromanagement benchmark demonstrate that our method just with a simple utility network is able to outperform the current state-of-the-art MARL algorithms on 4 of 5 super hard scenarios. Better performance can be further achieved when combined with a role-based utility network.

cs.LG↗

arXiv2020

Deep learning for video game genre classification

Video game genre classification based on its cover and textual description would be utterly beneficial to many modern identification, collocation, and retrieval systems. At the same time, it is also an extremely challenging task due to the following reasons: First, there exists a wide variety of video game genres, many of which are not concretely defined. Second, video game covers vary in many different ways such as colors, styles, textual information, etc, even for games of the same genre. Third, cover designs and textual descriptions may vary due to many external factors such as country, culture, target reader populations, etc. With the growing competitiveness in the video game industry, the cover designers and typographers push the cover designs to its limit in the hope of attracting sales. The computer-based automatic video game genre classification systems become a particularly exciting research topic in recent years. In this paper, we propose a multi-modal deep learning framework to solve this problem. The contribution of this paper is four-fold. First, we compiles a large dataset consisting of 50,000 video games from 21 genres made of cover images, description text, and title text and the genre information. Second, image-based and text-based, state-of-the-art models are evaluated thoroughly for the task of genre classification for video games. Third, we developed an efficient and salable multi-modal framework based on both images and texts. Fourth, a thorough analysis of the experimental results is given and future works to improve the performance is suggested. The results show that the multi-modal framework outperforms the current state-of-the-art image-based or text-based models. Several challenges are outlined for this task. More efforts and resources are needed for this classification task in order to reach a satisfactory level.

cs.CV↗

arXiv2020

Evidence of Flat Bands and Correlated States in Buckled Graphene Superlattices

Two-dimensional atomic crystals can radically change their properties in response to external influences such as substrate orientation or strain, resulting in essentially new materials in terms of the electronic structure. A striking example is the creation of flat-bands in bilayer-graphene for certain 'magic' twist-angles between the orientations of the two layers. The quenched kinetic-energy in these flat-bands promotes electron-electron interactions and facilitates the emergence of strongly-correlated phases such as superconductivity and correlated-insulators. However, the exquisite fine-tuning required for finding the magic-angle where flat-bands appear in twisted-bilayer graphene, poses challenges to fabrication and scalability. Here we present an alternative route to creating flat-bands that does not involve fine tuning. Using scanning tunneling microscopy and spectroscopy, together with numerical simulations, we demonstrate that graphene monolayers placed on an atomically-flat substrate can be forced to undergo a buckling-transition, resulting in a periodically modulated pseudo-magnetic field, which in turn creates a post-graphene material with flat electronic bands. Bringing the Fermi-level into these flat-bands by electrostatic doping, we observe a pseudogap-like depletion in the density-of-states, which signals the emergence of a correlated-state. The described approach of 2D crystal buckling offers a strategy for creating other superlattice systems and, in particular, for exploring interaction phenomena characteristic of flat-bands.

cond-mat.mes-hall↗

arXiv2020

Fast Hardware-Aware Neural Architecture Search

Designing accurate and efficient convolutional neural architectures for vast amount of hardware is challenging because hardware designs are complex and diverse. This paper addresses the hardware diversity challenge in Neural Architecture Search (NAS). Unlike previous approaches that apply search algorithms on a small, human-designed search space without considering hardware diversity, we propose HURRICANE that explores the automatic hardware-aware search over a much larger search space and a two-stage search algorithm, to efficiently generate tailored models for different types of hardware. Extensive experiments on ImageNet demonstrate that our algorithm outperforms state-of-the-art hardware-aware NAS methods under the same latency constraint on three types of hardware. Moreover, the discovered architectures achieve much lower latency and higher accuracy than current state-of-the-art efficient models. Remarkably, HURRICANE achieves a 76.67% top-1 accuracy on ImageNet with a inference latency of only 16.5 ms for DSP, which is a 3.47% higher accuracy and a 6.35x inference speedup than FBNet-iPhoneX, respectively. For VPU, we achieve a 0.53% higher top-1 accuracy than Proxyless-mobile with a 1.49x speedup. Even for well-studied mobile CPU, we achieve a 1.63% higher top-1 accuracy than FBNet-iPhoneX with a comparable inference latency. HURRICANE also reduces the training time by 30.4% compared to SPOS.

cs.CV↗

arXiv2020

Reversible Single Spin Control of Individual Magnetic Molecule by Hydrogen Atom Adsorption

The reversible control of a single spin of an atom or a molecule is of great interest in Kondo physics and a potential application in spin based electronics.Here we demonstrate that the Kondo resonance of manganese phthalocyanine molecules on an Au(111) substrate have been reversibly switched off and on via a robust route through attachment and detachment of single hydrogen atom to the magnetic core of the molecule. As further revealed by density functional theory calculations, even though the total number of electrons of the Mn ion remains almost the same in the process, gaining one single hydrogen atom leads to redistribution of charges within 3d orbitals with a reduction of the molecular spin state from S = 3/2 to S = 1 that directly contributes to the Kondo resonance disappearance. This process is reversed by a local voltage pulse or thermal annealing to desorb the hydrogen atom.

cond-mat.mes-hall↗

arXiv2020

Revealing the Atomic Site-Dependent g Factor within a Single Magnetic Molecule via the Extended Kondo Effect

The site-dependent g factor of a single magnetic molecule, with intramolecular resolution, is demonstrated for the first time by low-temperature, high-magnetic-field scanning tunneling microscopy of dehydrogenated Mn-phthalocyanine molecules on Au(111). This is achieved by exploring the magneticfield dependence of the extended Kondo effect at different atomic sites of the molecule. Importantly, an inhomogeneous distribution of the g factor inside a single molecule is revealed. Our results open up a new route to access local spin properties within a single molecule.

cond-mat.mes-hall↗

arXiv2019

Charge-Order and Broken Rotational Symmetry in Magic Angle Twisted Bilayer Graphene

The discovery of correlated electronic phases, including Mott-like insulators and superconductivity, in twisted bilayer graphene (TBLG) near the magic angle, and the intriguing similarity of their phenomenology to that of the high-temperature superconductors, has spurred a surge of research to uncover the underlying physical mechanism. Local spectroscopy, which is capable of accessing the symmetry and spatial distribution of the spectral function, can provide essential clues towards unraveling this puzzle. Here we use scanning tunneling microscopy (STM) and spectroscopy (STS) in magic angle TBLG to visualize the local density of states (DOS) and charge distribution. Doping the sample to partially fill the flat band, where low temperature transport measurements revealed the emergence of correlated electronic phases, we find a pseudogap phase accompanied by a global stripe charge-order whose similarity to high-temperature superconductors provides new evidence of a deeper link underlying the phenomenology of these systems.

cond-mat.mes-hall↗

arXiv2019

Flat Bands in Buckled Graphene Superlattices

Interactions between stacked two-dimensional (2D) atomic crystals can radically change their properties, leading to essentially new materials in terms of the electronic structure. Here we show that monolayers placed on an atomically flat substrate can be forced to undergo a buckling transition, which results in periodically strained superlattices. By using scanning tunneling microscopy and spectroscopy and support from numerical simulations, we show that such lateral superlattices in graphene lead to a periodically modulated pseudo-magnetic field, which in turn creates a post-graphene material with flat electronic bands. The described approach of controllable buckling of 2D crystals offers a venue for creating other superlattice systems and, in particular, for exploring interaction phenomena characteristic of flat bands.

cond-mat.mes-hall↗

arXiv2018

Modeling of gate controlled Kondo effect at carbon point-defects in graphene

We study the magnetic properties in the vicinity of a single carbon defect in a monolayer of graphene. We include the unbound $σ$ orbital and the vacancy induced bound $π$ state in an effective two-orbital single impurity model. The local magnetic moments are stabilized by the Coulomb interaction as well as a significant ferromagnetic Hund's rule coupling between the orbitals predicted by a density functional theory calculation. A hybridization between the orbitals and the Dirac fermions is generated by the curvature of the graphene sheet in the vicinity of the vacancy. We present results for the local spectral function calculated using Wilson's numerical renormalization group approach for a realistic graphene band structure and find three different regimes depending on the filling, the controlling chemical potential, and the hybridization strength. These different regions are characterized by different magnetic properties. The calculated spectral functions qualitatively agree with recent scanning tunneling spectra on graphene vacancies.

cond-mat.mes-hall↗

arXiv2018

Quantum Critical Transition and Kondo Screening of Magnetic Moments in Graphene

In normal metals, the magnetic moment of impurity spins disappears below a characteristic Kondo temperature, TK, where coupling with the conduction-band electrons produces an entangled state that screens the local moment. In contrast, moments embedded in insulators remain unscreened at all temperatures. This raises the question about the fate of magnetic moments in intermediate, pseudogap systems, such as graphene. In these systems theory predicts a quantum phase-transition at a critical coupling strength which separates a local magnetic-moment phase from a Kondo screened phase. However, attempts to experimentally confirm these predictions and their intriguing consequences such as the ability to electrostatically control magnetic moments, have thus far been elusive. Here we report the observation of Kondo screening and the quantum phase-transition between screened and unscreened phases of vacancy magnetic-moments in graphene. Using scanning tunneling microscopy (STM), spectroscopy (STS) and numerical renormalization group (NRG) calculations, we identified Kondo screening by its spectroscopic signature and mapped the phase-transition as a function of coupling strength and chemical potential. We show that this transition makes it possible to turn the magnetic-moment on and off electrostatically through a gate voltage or mechanically through variations in local curvature.

cond-mat.mes-hall↗

arXiv2017

Observing a scale anomaly and a universal quantum phase transition in graphene

One of the most interesting predictions resulting from quantum physics, is the violation of classical symmetries, collectively referred to as anomalies. A remarkable class of anomalies occurs when the continuous scale symmetry of a scale free quantum system is broken into a discrete scale symmetry for a critical value of a control parameter. This is an example of a (zero temperature) quantum phase transition. Such an anomaly takes place for the quantum inverse square potential known to describe 'Efimov physics'. Broken continuous scale symmetry into discrete scale symmetry also appears for a charged and massless Dirac fermion in an attractive $1/r$ Coulomb potential. The purpose of this article is to demonstrate the universality of this quantum phase transition and to present convincing experimental evidence of its existence for a charged and massless fermion in an attractive Coulomb potential as realised in graphene.

cond-mat.mes-hall↗

arXiv2017

Tuning a Circular p-n Junction in Graphene from Quantum Confinement to Optical Guiding

The motion of massless Dirac-electrons in graphene mimics the propagation of photons. This makes it possible to control the charge-carriers with components based on geometrical-optics and has led to proposals for an all-graphene electron-optics platform. An open question arising from the possibility of reducing the component-size to the nanometer-scale is how to access and understand the transition from optical-transport to quantum-confinement. Here we report on the realization of a circular p-n junction that can be continuously tuned from the nanometer-scale, where quantum effects are dominant, to the micrometer scale where optical-guiding takes over. We find that in the nanometer-scale junction electrons are trapped in states that resemble atomic-collapse at a supercritical charge. As the junction-size increases, the transition to optical-guiding is signaled by the emergence of whispering-gallery modes and Fabry-Perot interference. The creation of tunable junctions that straddle the crossover between quantum-confinement and optical-guiding, paves the way to novel design-architectures for controlling electronic transport.

cond-mat.mes-hall↗