arXiv subjects

Zhe Liu

Publications and source records attributed to Zhe Liu.

At least 289 records · Page 16Linked to original sources

arXiv2021

Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks with Base Controllers

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporates the existing base controllers into stages of exploration, value learning, and policy update. Furthermore, we present a straightforward way of synthesizing different base controllers to integrate their strengths. Through experiments ranging from stacking blocks to cups, it is demonstrated that the learned state-based or image-based policies steadily outperform base controllers. Compared to previous works of learning from demonstrations, our method improves sample efficiency by orders of magnitude and improves the performance. Overall, our method bears the potential of leveraging existing industrial robot manipulation systems to build more flexible and intelligent controllers.

cs.RO↗

arXiv2021

Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning

Current approaches to Zero-Shot Learning (ZSL) struggle to learn generalizable semantic knowledge capable of capturing complex correlations. Inspired by \emph{Spiral Curriculum}, which enhances learning processes by revisiting knowledge, we propose a form of spiral learning which revisits visual representations based on a sequence of attribute groups (e.g., a combined group of \emph{color} and \emph{shape}). Spiral learning aims to learn generalized local correlations, enabling models to gradually enhance global learning and thus understand complex correlations. Our implementation is based on a 2-stage \emph{Reinforced Self-Revised (RSR)} framework: \emph{preview} and \emph{review}. RSR first previews visual information to construct diverse attribute groups in a weakly-supervised manner. Then, it spirally learns refined localities based on attribute groups and uses localities to revise global semantic correlations. Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings, which demonstrates the effectiveness of spiral learning in learning generalizable and complex correlations. We also conduct extensive analysis to show that attribute groups and reinforced decision processes can capture complementary semantic information to improve predictions and aid explainability.

cs.CV↗

arXiv2021

Predicting antimicrobial activity of conjugated oligoelectrolyte molecules via machine learning

New antibiotics are needed to battle growing antibiotic resistance, but the development process from hit, to lead, and ultimately to a useful drug, takes decades. Although progress in molecular property prediction using machine-learning methods has opened up new pathways for aiding the antibiotics development process, many existing solutions rely on large datasets and finding structural similarities to existing antibiotics. Challenges remain in modelling of unconventional antibiotics classes that are drawing increasing research attention. In response, we developed an antimicrobial activity prediction model for conjugated oligoelectrolyte molecules, a new class of antibiotics that lacks extensive prior structure-activity relationship studies. Our approach enables us to predict minimum inhibitory concentration for E. coli K12, with 21 molecular descriptors selected by recursive elimination from a set of 5,305 descriptors. This predictive model achieves an R2 of 0.65 with no prior knowledge of the underlying mechanism. We find the molecular representation optimum for the domain is the key to good predictions of antimicrobial activity. In the case of conjugated oligoelectrolytes, a representation reflecting the 3-dimensional shape of the molecules is most critical. Although it is demonstrated with a specific example of conjugated oligoelectrolytes, our proposed approach for creating the predictive model can be readily adapted to other novel antibiotic candidate domains.

physics.app-ph↗

arXiv2021

An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning

Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations. A promising strategy is to learn a global-local representation that incorporates global information with extra localities (i.e., small parts/regions of inputs). However, existing methods discover localities based on explicit features without digging into the inherent properties and relationships among regions. In this work, we propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet), which extracts and aggregates localities progressively based on semantic relevance and visual correlations without human-annotated regions. ERPCNet uses reinforced partial convolution and entropy guidance; it not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization. We conduct extensive experiments to demonstrate ERPCNet's performance through comparisons with state-of-the-art methods under ZSL and Generalized Zero-Shot Learning (GZSL) settings on four benchmark datasets. We also show ERPCNet is time efficient and explainable through visualization analysis.

cs.CV↗

arXiv2021

Observation of Geometric Heat Pump Effect in Periodic Driven Thermal Diffusion

The concept of geometry works as an overarching framework underlying a wide range of transport phenomena. Particularly, the geometric phase effect in classical and quantum heat pump has been attracting much attention in microscopic systems. Here, we formulate theoretically the geometric heat pump effect in macroscopic driven diffusive systems. Upon modulation protocols, the nontrivial geometric curvature in the parameter space universally induces an additional pumped heat, beyond the constraint of hot-to-cold flowing. Furthermore, we set up a minimum experiment and indeed observe a non-vanishing directional heat flow across the driven system, despite keeping zero thermal bias between two time-dependent thermal reservoirs at every instant. We verify that in analogy to the geometric phase effect, the geometric pumped heat during each driving cycle is independent of driving periods in the adiabatic limit and coincides with theoretical predictions, thus validating its geometric origin. These results about geometric heat pump effect could have potential implications for designing and implementing nonreciprocal and topological thermal meta-devices under spatiotemporal modulations.

cond-mat.stat-mech↗

arXiv2021

Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual Localization

Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of environmental conditions, e.g. illumination, seasonal and weather changes, retrieval-based visual localization is severely affected and becomes a challenging problem. In this work, a general architecture is first formulated probabilistically to extract domain invariant feature through multi-domain image translation. And then a novel gradient-weighted similarity activation mapping loss (Grad-SAM) is incorporated for finer localization with high accuracy. We also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised manner. The final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models without and with Grad-SAM loss. Extensive experiments have been conducted to validate the effectiveness of the proposed approach on the CMUSeasons dataset. The strong generalization ability of our approach is verified on RobotCar dataset using models pre-trained on urban part of CMU-Seasons dataset. Our performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision, especially under the challenging environments with illumination variance, vegetation and night-time images. The code and pretrained models are available on https://github.com/HanjiangHu/DISAM.

cs.CV↗

arXiv2021

Opportunities for Machine Learning to Accelerate Halide Perovskite Commercialization and Scale-Up

While halide perovskites attract significant academic attention, examples of at-scale industrial production are still sparse. In this perspective, we review practical challenges hindering the commercialization of halide perovskites, and discuss how machine-learning (ML) tools could help: (1) active-learning algorithms that blend institutional knowledge and human expertise could help stabilize and rapidly update baseline manufacturing processes; (2) ML-powered metrology, including computer imaging, could help narrow the performance gap between large- and small-area devices; and (3) inference methods could help accelerate root-cause analysis by reconciling multiple data streams and simulations, focusing research effort on areas with highest probability for improvement. We conclude that to satisfy many of these challenges, incremental -- not radical -- adaptations of existing ML and statistical methods are needed. We identify resources to help develop in-house data-science talent, and propose how industry-academic partnerships could help adapt "ready-now" ML tools to specific industry needs, further improve process control by revealing underlying mechanisms, and develop "gamechanger" discovery-oriented algorithms to better navigate vast materials combination spaces and the literature.

cond-mat.mtrl-sci↗

arXiv2021

Model-Based Approach for Measuring the Fairness in ASR

The issue of fairness arises when the automatic speech recognition (ASR) systems do not perform equally well for all subgroups of the population. In any fairness measurement studies for ASR, the open questions of how to control the nuisance factors, how to handle unobserved heterogeneity across speakers, and how to trace the source of any word error rate (WER) gap among different subgroups are especially important - if not appropriately accounted for, incorrect conclusions will be drawn. In this paper, we introduce mixed-effects Poisson regression to better measure and interpret any WER difference among subgroups of interest. Particularly, the presented method can effectively address the three problems raised above and is very flexible to use in practical disparity analyses. We demonstrate the validity of proposed model-based approach on both synthetic and real-world speech data.

stat.ML↗

arXiv2021

Life-Long Multi-Task Learning of Adaptive Path Tracking Policy for Autonomous Vehicle

This paper proposes a life-long adaptive path tracking policy learning method for autonomous vehicles that can self-evolve and self-adapt with multi-task knowledge. Firstly, the proposed method can learn a model-free control policy for path tracking directly from the historical driving experience, where the property of vehicle dynamics and corresponding control strategy can be learned simultaneously. Secondly, by utilizing the life-long learning method, the proposed method can learn the policy with task-incremental knowledge without encountering catastrophic forgetting. Thus, with continual multi-task knowledge learned, the policy can iteratively adapt to new tasks and improve its performance with knowledge from new tasks. Thirdly, a memory evaluation and updating method is applied to optimize memory structure for life-long learning which enables the policy to learn toward selected directions. Experiments are conducted using a high-fidelity vehicle dynamic model in a complex curvy road to evaluate the performance of the proposed method. Results show that the proposed method can effectively evolve with continual multi-task knowledge and adapt to the new environment, where the performance of the proposed method can also surpass two commonly used baseline methods after evolving.

cs.RO↗

arXiv2021

Efficient Medical Image Segmentation Based on Knowledge Distillation

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage.

eess.IV↗

arXiv2021

A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset.

cs.CV↗

arXiv2021

Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences

With the rapid development of measurement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets.

cs.CV↗

arXiv2021

An integrated whispering-gallery-mode resonator for solid-state coherent quantum photonics

Tailored photonic cavities allow enhancing light-matter interaction ultimately to create a fully coherent quantum interface. Here, we report on an integrated microdisk cavity containing self-assembled quantum dots to coherently route photons between different access waveguides. We measure a Purcell factor of $F_{exp}=6.9\pm0.9$ for a cavity quality factor of about 10,000, allowing us to observe clear signatures of coherent scattering of photons by the quantum dots. We show how this integrated system can coherently re-route photons between the drop and bus ports, and how this routing is controlled by detuning the quantum dot and resonator, or through the strength of the excitation beam, where a critical photon number less than one photon per lifetime is required. We discuss the strengths and limitations of this approach, focusing on how the coherent scattering and single-photon nonlinearity can be used to increase the efficiency of quantum devices such as routers or Bell-state analyzers.

quant-ph↗

arXiv2021

The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts

Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances. The use of learning-based methods in multi-robot planning holds great promise as it enables us to offload the online computational burden of expensive, yet optimal solvers, to an offline learning procedure. Simply put, the idea is to train a policy to copy an optimal pattern generated by a small-scale system, and then transfer that policy to much larger systems, in the hope that the learned strategy scales, while maintaining near-optimal performance. Yet, a number of issues impede us from leveraging this idea to its full potential. This blue-sky paper elaborates some of the key challenges that remain.

cs.RO↗

arXiv2021

OwlEyes-Online: A Fully Automated Platform for Detecting and Localizing UI Display Issues

Graphical User Interface (GUI) provides visual bridges between software apps and end users. However, due to the compatibility of software or hardware, UI display issues such as text overlap, blurred screen, image missing always occur during GUI rendering on different devices. Because these UI display issues can be found directly by human eyes, in this paper, we implement an online UI display issue detection tool OwlEyes-Online, which provides a simple and easy-to-use platform for users to realize the automatic detection and localization of UI display issues. The OwlEyes-Online can automatically run the app and get its screenshots and XML files, and then detect the existence of issues by analyzing the screenshots. In addition, OwlEyes-Online can also find the detailed area of the issue in the given screenshots to further remind developers. Finally, OwlEyes-Online will automatically generate test reports with UI display issues detected in app screenshots and send them to users. The OwlEyes-Online was evaluated and proved to be able to accurately detect UI display issues. Tool Link: http://www.owleyes.online:7476 Github Link: https://github.com/franklinbill/owleyes Demo Video Link: https://youtu.be/002nHZBxtCY

cs.SE↗

arXiv2021

Discovering Equations that Govern Experimental Materials Stability under Environmental Stress using Scientific Machine Learning

While machine learning (ML) in experimental research has demonstrated impressive predictive capabilities, inductive reasoning and knowledge extraction remain elusive tasks, in part because of the difficulty extracting fungible knowledge representations from experimental data. In this manuscript, we use ML to infer the underlying dynamical differential equation (DE) from experimental data of degrading organic-inorganic methylammonium lead iodide (MAPI) perovskite thin films under environmental stressors (elevated temperature, humidity, and light). We apply a sparse regression algorithm that automatically identifies the differential equation describing the dynamics from time-series data. We find that the underlying DE governing MAPI degradation across a broad temperature range of 35 to 85°C is described minimally with three terms (specifically, a second-order polynomial), and not a simple single-order reaction (i.e. 0th, 1st, or 2nd-order reaction). We demonstrate how computer-derived results can aid the researcher to develop profound mechanistic insights. This DE corresponds to the Verhulst logistic function, which describes reaction kinetics analogous in functional form to autocatalytic or self-propagating reactions, suggesting future strategies to suppress MAPI degradation. We examine the robustness of our conclusions to experimental luck-of-the-draw variance and Gaussian noise using a combination of experiment and simulation, and describe the experimental limits within which this methodology can be applied. Our study demonstrates the application of scientific ML in experimental chemical and materials systems, highlighting the promise and challenges associated with ML-aided scientific discovery.

cond-mat.mtrl-sci↗

arXiv2021

End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information. In this paper, we present an end-to-end deep-learning based approach to resolve the point cloud registration problem. Firstly, the revised LPD-Net is introduced to extract features and aggregate them with the graph network. Secondly, the self-attention mechanism is utilized to enhance the structure information in the point cloud and the cross-attention mechanism is designed to enhance the corresponding information between the two input point clouds. Based on which, the virtual corresponding points can be generated by a soft pointer based method, and finally, the point cloud registration problem can be solved by implementing the SVD method. Comparison results in ModelNet40 dataset validate that the proposed approach reaches the state-of-the-art in point cloud registration tasks and experiment resutls in KITTI dataset validate the effectiveness of the proposed approach in real applications.Our source code is available at \url{https://github.com/qiaozhijian/VCR-Net.git}

cs.CV↗

arXiv2021

Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion

While Electrical Impedance Tomography (EIT) has found many biomedicine applications, a better resolution is needed to provide quantitative analysis for tissue engineering and regenerative medicine. This paper proposes an impedance-optical dual-modal imaging framework, which is mainly aimed at high-quality 3D cell culture imaging and can be extended to other tissue engineering applications. The framework comprises three components, i.e., an impedance-optical dual-modal sensor, the guidance image processing algorithm, and a deep learning model named multi-scale feature cross fusion network (MSFCF-Net) for information fusion. The MSFCF-Net has two inputs, i.e., the EIT measurement and a binary mask image generated by the guidance image processing algorithm, whose input is an RGB microscopic image. The network then effectively fuses the information from the two different imaging modalities and generates the final conductivity image. We assess the performance of the proposed dual-modal framework by numerical simulation and MCF-7 cell imaging experiments. The results show that the proposed method could significantly improve image quality, indicating that impedance-optical joint imaging has the potential to reveal the structural and functional information of tissue-level targets simultaneously.

eess.IV↗