arXiv subjects

Qi Zhao

Publications and source records attributed to Qi Zhao.

At least 199 records · Page 11Linked to original sources

arXiv2021

Multiobjective Bilevel Evolutionary Approach for Off-Grid Direction-of-Arrival Estimation

The source number identification is an essential step in direction-of-arrival (DOA) estimation. Existing methods may provide a wrong source number due to inferior statistical properties (in low SNR or limited snapshots) or modeling errors (caused by relaxing sparse penalties), especially in impulsive noise. To address this issue, we propose a novel idea of simultaneous source number identification and DOA estimation. We formulate a multiobjective off-grid DOA estimation model to realize this idea, by which the source number can be automatically identified together with DOA estimation. In particular, the source number is properly exploited by the $l_0$ norm of impinging signals without relaxations, guaranteeing accuracy. Furthermore, we design a multiobjective bilevel evolutionary algorithm to solve the proposed model. The source number identification and sparse recovery are simultaneously optimized at the on-grid (lower) level. A forward search strategy is developed to further refine the grid at the off-grid (upper) level. This strategy does not need linear approximations and can eliminate the off-grid gap with low computational complexity. Simulation results demonstrate the outperformance of our method in terms of source number and root mean square error.

cs.NE↗

arXiv2021

Evolutionary Robust Clustering Over Time for Temporal Data

In many clustering scenes, data samples' attribute values change over time. For such data, we are often interested in obtaining a partition for each time step and tracking the dynamic change of partitions. Normally, a smooth change is assumed for data to have a temporal smooth nature. Existing algorithms consider the temporal smoothness as an a priori preference and bias the search towards the preferred direction. This a priori manner leads to a risk of converging to an unexpected region because it is not always the case that a reasonable preference can be elicited given the little prior knowledge about the data. To address this issue, this paper proposes a new clustering framework called evolutionary robust clustering over time. One significant innovation of the proposed framework is processing the temporal smoothness in an a posteriori manner, which avoids unexpected convergence that occurs in existing algorithms. Furthermore, the proposed framework automatically tunes the weight of smoothness without data's affinity matrix and predefined parameters, which holds better applicability and scalability. The effectiveness and efficiency of the proposed framework are confirmed by comparing with state-of-the-art algorithms on both synthetic and real datasets.

cs.NE↗

arXiv2021

Gridless Evolutionary Approach for Line Spectral Estimation with Unknown Model Order

Gridless methods show great superiority in line spectral estimation. These methods need to solve an atomic $l_0$ norm (i.e., the continuous analog of $l_0$ norm) minimization problem to estimate frequencies and model order. Since this problem is NP-hard to compute, relaxations of atomic $l_0$ norm, such as nuclear norm and reweighted atomic norm, have been employed for promoting sparsity. However, the relaxations give rise to a resolution limit, subsequently leading to biased model order and convergence error. To overcome the above shortcomings of relaxation, we propose a novel idea of simultaneously estimating the frequencies and model order by means of the atomic $l_0$ norm. To accomplish this idea, we build a multiobjective optimization model. The measurment error and the atomic $l_0$ norm are taken as the two optimization objectives. The proposed model directly exploits the model order via the atomic $l_0$ norm, thus breaking the resolution limit. We further design a variable-length evolutionary algorithm to solve the proposed model, which includes two innovations. One is a variable-length coding and search strategy. It flexibly codes and interactively searches diverse solutions with different model orders. These solutions act as steppingstones that help fully exploring the variable and open-ended frequency search space and provide extensive potentials towards the optima. Another innovation is a model order pruning mechanism, which heuristically prunes less contributive frequencies within the solutions, thus significantly enhancing convergence and diversity. Simulation results confirm the superiority of our approach in both frequency estimation and model order selection.

math.OC↗

arXiv2021

Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene Classification

Remote sensing (RS) image scene classification task faces many challenges due to the interference from different characteristics of different geographical elements. To solve this problem, we propose a multi-branch ensemble network to enhance the feature representation ability by fusing features in final output logits and intermediate feature maps. However, simply adding branches will increase the complexity of models and decline the inference efficiency. On this issue, we embed self-distillation (SD) method to transfer knowledge from ensemble network to main-branch in it. Through optimizing with SD, main-branch will have close performance as ensemble network. During inference, we can cut other branches to simplify the whole model. In this paper, we first design compact multi-branch ensemble network, which can be trained in an end-to-end manner. Then, we insert SD method on output logits and feature maps. Compared to previous methods, our proposed architecture (ESD-MBENet) performs strongly on classification accuracy with compact design. Extensive experiments are applied on three benchmark RS datasets AID, NWPU-RESISC45 and UC-Merced with three classic baseline models, VGG16, ResNet50 and DenseNet121. Results prove that our proposed ESD-MBENet can achieve better accuracy than previous state-of-the-art (SOTA) complex models. Moreover, abundant visualization analysis make our method more convincing and interpretable.

cs.CV↗

arXiv2021

A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control

Objective: Deep learning-based neural decoders have emerged as the prominent approach to enable dexterous and intuitive control of neuroprosthetic hands. Yet few studies have materialized the use of deep learning in clinical settings due to its high computational requirements. Methods: Recent advancements of edge computing devices bring the potential to alleviate this problem. Here we present the implementation of a neuroprosthetic hand with embedded deep learning-based control. The neural decoder is designed based on the recurrent neural network (RNN) architecture and deployed on the NVIDIA Jetson Nano - a compacted yet powerful edge computing platform for deep learning inference. This enables the implementation of the neuroprosthetic hand as a portable and self-contained unit with real-time control of individual finger movements. Results: The proposed system is evaluated on a transradial amputee using peripheral nerve signals (ENG) with implanted intrafascicular microelectrodes. The experiment results demonstrate the system's capabilities of providing robust, high-accuracy (95-99%) and low-latency (50-120 msec) control of individual finger movements in various laboratory and real-world environments. Conclusion: Modern edge computing platforms enable the effective use of deep learning-based neural decoders for neuroprosthesis control as an autonomous system. Significance: This work helps pioneer the deployment of deep neural networks in clinical applications underlying a new class of wearable biomedical devices with embedded artificial intelligence.

cs.RO↗

arXiv2021

BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks

Deploying convolutional neural networks (CNNs) for embedded applications presents many challenges in balancing resource-efficiency and task-related accuracy. These two aspects have been well-researched in the field of CNN compression. In real-world applications, a third important aspect comes into play, namely the robustness of the CNN. In this paper, we thoroughly study the robustness of uncompressed, distilled, pruned and binarized neural networks against white-box and black-box adversarial attacks (FGSM, PGD, C&W, DeepFool, LocalSearch and GenAttack). These new insights facilitate defensive training schemes or reactive filtering methods, where the attack is detected and the input is discarded and/or cleaned. Experimental results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks (BNNs) such as XNOR-Net and ABC-Net, trained on CIFAR-10 and ImageNet datasets. We present evaluation methods to simplify the comparison between CNNs under different attack schemes using loss/accuracy levels, stress-strain graphs, box-plots and class activation mapping (CAM). Our analysis reveals susceptible behavior of uncompressed and pruned CNNs against all kinds of attacks. The distilled models exhibit their strength against all white box attacks with an exception of C&W. Furthermore, binary neural networks exhibit resilient behavior compared to their baselines and other compressed variants.

cs.LG↗

arXiv2021

Experimental Realization of Device-Independent Quantum Randomness Expansion

Randomness expansion where one generates a longer sequence of random numbers from a short one is viable in quantum mechanics but not allowed classically. Device-independent quantum randomness expansion provides a randomness resource of the highest security level. Here, we report the first experimental realization of device-independent quantum randomness expansion secure against quantum side information established through quantum probability estimation. We generate $5.47\times10^8$ quantum-proof random bits while consuming $4.39\times10^8$ bits of entropy, expanding our store of randomness by $1.08\times10^8$ bits at a latency of about $13.1$ h, with a total soundness error $4.6\times10^{-10}$. Device-independent quantum randomness expansion not only enriches our understanding of randomness but also sets a solid base to bring quantum-certifiable random bits into realistic applications.

quant-ph↗

arXiv2021

Experimental exploration of five-qubit quantum error correcting code with superconducting qubits

Quantum error correction is an essential ingredient for universal quantum computing. Despite tremendous experimental efforts in the study of quantum error correction, to date, there has been no demonstration in the realisation of universal quantum error correcting code, with the subsequent verification of all key features including the identification of an arbitrary physical error, the capability for transversal manipulation of the logical state, and state decoding. To address this challenge, we experimentally realise the $[\![5,1,3]\!]$ code, the so-called smallest perfect code that permits corrections of generic single-qubit errors. In the experiment, having optimised the encoding circuit, we employ an array of superconducting qubits to realise the $[\![5,1,3]\!]$ code for several typical logical states including the magic state, an indispensable resource for realising non-Clifford gates. The encoded states are prepared with an average fidelity of $57.1(3)\%$ while with a high fidelity of $98.6(1)\%$ in the code space. Then, the arbitrary single-qubit errors introduced manually are identified by measuring the stabilizers. We further implement logical Pauli operations with a fidelity of $97.2(2)\%$ within the code space. Finally, we realise the decoding circuit and recover the input state with an overall fidelity of $74.5(6)\%$, in total with $92$ gates. Our work demonstrates each key aspect of the $[\![5,1,3]\!]$ code and verifies the viability of experimental realization of quantum error correcting codes with superconducting qubits.

quant-ph↗

arXiv2020

MM-FSOD: Meta and metric integrated few-shot object detection

In the object detection task, CNN (Convolutional neural networks) models always need a large amount of annotated examples in the training process. To reduce the dependency of expensive annotations, few-shot object detection has become an increasing research focus. In this paper, we present an effective object detection framework (MM-FSOD) that integrates metric learning and meta-learning to tackle the few-shot object detection task. Our model is a class-agnostic detection model that can accurately recognize new categories, which are not appearing in training samples. Specifically, to fast learn the features of new categories without a fine-tuning process, we propose a meta-representation module (MR module) to learn intra-class mean prototypes. MR module is trained with a meta-learning method to obtain the ability to reconstruct high-level features. To further conduct similarity of features between support prototype with query RoIs features, we propose a Pearson metric module (PR module) which serves as a classifier. Compared to the previous commonly used metric method, cosine distance metric. PR module enables the model to align features into discriminative embedding space. We conduct extensive experiments on benchmark datasets FSOD, MS COCO, and PASCAL VOC to demonstrate the feasibility and efficiency of our model. Comparing with the previous method, MM-FSOD achieves state-of-the-art (SOTA) results.

cs.CV↗

arXiv2020

MGML: Multi-Granularity Multi-Level Feature Ensemble Network for Remote Sensing Scene Classification

Remote sensing (RS) scene classification is a challenging task to predict scene categories of RS images. RS images have two main characters: large intra-class variance caused by large resolution variance and confusing information from large geographic covering area. To ease the negative influence from the above two characters. We propose a Multi-granularity Multi-Level Feature Ensemble Network (MGML-FENet) to efficiently tackle RS scene classification task in this paper. Specifically, we propose Multi-granularity Multi-Level Feature Fusion Branch (MGML-FFB) to extract multi-granularity features in different levels of network by channel-separate feature generator (CS-FG). To avoid the interference from confusing information, we propose Multi-granularity Multi-Level Feature Ensemble Module (MGML-FEM) which can provide diverse predictions by full-channel feature generator (FC-FG). Compared to previous methods, our proposed networks have ability to use structure information and abundant fine-grained features. Furthermore, through ensemble learning method, our proposed MGML-FENets can obtain more convincing final predictions. Extensive classification experiments on multiple RS datasets (AID, NWPU-RESISC45, UC-Merced and VGoogle) demonstrate that our proposed networks achieve better performance than previous state-of-the-art (SOTA) networks. The visualization analysis also shows the good interpretability of MGML-FENet.

cs.CV↗

arXiv2020

Generation and propagation of an open vortex beam

We theoretically and experimentally studied a novel class of vortex beams named open vortex beams (OVBs). Such beams are generated using Gaussian beams diffracted by partially blocked fork-shaped gratings (PB-FSGs).The analytical model of OVBs in the near field and far field is given by superpositions of Hypergeometric (HyG) modes. Unlike conventional integer and fractional vortex beams, the OVBs can have both an open ring structure and an integer topological charge (TC). The TC is decided by the circumference covered by the open ring. It is also quantitatively shown that a $π/2$ rotation of the open ring occurs in the propagation of an OVB due to the Gouy phase shift. Futhermore, we demonstrate experimental generation and detection of OVBs. Our experimental results are in very good agreement with the theory. We believe that the OVB can be the potential candidate for numerous applications, such as particle manipulation, quantum information and optical metrology.

physics.optics↗

arXiv2020

One-shot dynamical resource theory

A fundamental problem in resource theory is to study the manipulation of the resource. Focusing on a general dynamical resource theory of quantum channels, here we consider tasks of one-shot resource distillation and dilution with a single copy of the resource. For any target of unitary channel or pure state preparation channel, we establish a universal strategy to determine upper and lower bounds on rates that convert between any given resource and the target. We show that the rates are related to resource measures based on the channel robustness and the channel hypothesis testing entropy, with regularization factors of the target resource measures. The strategy becomes optimal with converged bounds when the channel robustness is finite and measures of the target resource collapse to the same value. The single-shot result also applies to asymptotic parallel manipulation of channels to obtain asymptotic resource conversion rates. We give several examples of dynamical resources, including the purity, classical capacity, quantum capacity, non-uniformity, coherence, and entanglement of quantum channels. Our results are applicable to general dynamical resource theories with potential applications in quantum communication, fault-tolerant quantum computing, and quantum thermodynamics.

quant-ph↗

arXiv2020

A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data

This paper presents a deep learning framework based on Long Short-term Memory Network(LSTM) that predicts price movement of cryptocurrencies from trade-by-trade data. The main focus of this study is on predicting short-term price changes in a fixed time horizon from a looking back period. By carefully designing features and detailed searching for best hyper-parameters, the model is trained to achieve high performance on nearly a year of trade-by-trade data. The optimal model delivers stable high performance(over 60% accuracy) on out-of-sample test periods. In a realistic trading simulation setting, the prediction made by the model could be easily monetized. Moreover, this study shows that the LSTM model could extract universal features from trade-by-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data. This study exceeds existing researches in term of the scale and precision of data used, as well as the high prediction accuracy achieved.

q-fin.ST↗

arXiv2020

Quantum teleportation of physical qubits into logical code-spaces

Quantum error correction is an essential tool for reliably performing tasks for processing quantum information on a large scale. However, integration into quantum circuits to achieve these tasks is problematic when one realizes that non-transverse operations, which are essential for universal quantum computation, lead to the spread of errors. Quantum gate teleportation has been proposed as an elegant solution for this. Here, one replaces these fragile, non-transverse inline gates with the generation of specific, highly entangled offline resource states that can be teleported into the circuit to implement the non-transverse gate. As the first important step, we create a maximally entangled state between a physical and an error-correctable logical qubit and use it as a teleportation resource. We then demonstrate the teleportation of quantum information encoded on the physical qubit into the error-corrected logical qubit with fidelities up to 0.786. Our scheme can be designed to be fully fault-tolerant so that it can be used in future large-scale quantum technologies.

quant-ph↗

arXiv2020

Review of Machine-Learning Methods for RNA Secondary Structure Prediction

Secondary structure plays an important role in determining the function of non-coding RNAs. Hence, identifying RNA secondary structures is of great value to research. Computational prediction is a mainstream approach for predicting RNA secondary structure. Unfortunately, even though new methods have been proposed over the past 40 years, the performance of computational prediction methods has stagnated in the last decade. Recently, with the increasing availability of RNA structure data, new methods based on machine-learning technologies, especially deep learning, have alleviated the issue. In this review, we provide a comprehensive overview of RNA secondary structure prediction methods based on machine-learning technologies and a tabularized summary of the most important methods in this field. The current pending issues in the field of RNA secondary structure prediction and future trends are also discussed.

q-bio.BM↗

arXiv2020

AiR: Attention with Reasoning Capability

While attention has been an increasingly popular component in deep neural networks to both interpret and boost performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes. We first define an evaluation metric based on a sequence of atomic reasoning operations, enabling quantitative measurement of attention that considers the reasoning process. We then collect human eye-tracking and answer correctness data, and analyze various machine and human attentions on their reasoning capability and how they impact task performance. Furthermore, we propose a supervision method to jointly and progressively optimize attention, reasoning, and task performance so that models learn to look at regions of interests by following a reasoning process. We demonstrate the effectiveness of the proposed framework in analyzing and modeling attention with better reasoning capability and task performance. The code and data are available at https://github.com/szzexpoi/AiR

cs.CV↗

arXiv2020

Saliency Prediction with External Knowledge

The last decades have seen great progress in saliency prediction, with the success of deep neural networks that are able to encode high-level semantics. Yet, while humans have the innate capability in leveraging their knowledge to decide where to look (e.g. people pay more attention to familiar faces such as celebrities), saliency prediction models have only been trained with large eye-tracking datasets. This work proposes to bridge this gap by explicitly incorporating external knowledge for saliency models as humans do. We develop networks that learn to highlight regions by incorporating prior knowledge of semantic relationships, be it general or domain-specific, depending on the task of interest. At the core of the method is a new Graph Semantic Saliency Network (GraSSNet) that constructs a graph that encodes semantic relationships learned from external knowledge. A Spatial Graph Attention Network is then developed to update saliency features based on the learned graph. Experiments show that the proposed model learns to predict saliency from the external knowledge and outperforms the state-of-the-art on four saliency benchmarks.

cs.CV↗

arXiv2020

Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection

Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down attention mechanisms in object detection and other vision tasks. The top-down attention, however, is less effective at improving the performance of few-shot detectors. Due to the insufficient training data, object detectors cannot effectively generate attention maps for few-shot examples. To improve the performance and interpretability of few-shot object detectors, we propose an attentive few-shot object detection network (AttFDNet) that takes the advantages of both top-down and bottom-up attention. Being task-agnostic, the bottom-up attention serves as a prior that helps detect and localize naturally salient objects. We further address specific challenges in few-shot object detection by introducing two novel loss terms and a hybrid few-shot learning strategy. Experimental results and visualization demonstrate the complementary nature of the two types of attention and their roles in few-shot object detection. Codes are available at https://github.com/chenxy99/AttFDNet.

cs.CV↗