arXiv subjects

Ye Wang

Publications and source records attributed to Ye Wang.

At least 307 records · Page 17Linked to original sources

arXiv2021

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models

Despite the remarkable performance of deep learning methods on various tasks, most cutting-edge models rely heavily on large-scale annotated training examples, which are often unavailable for clinical and health care tasks. The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling. Therefore, the strong capability of learning and generalizing from limited supervision, including a limited amount of annotations, sparse annotations, and inaccurate annotations, is crucial for the successful application of deep learning models in medical image segmentation. However, due to its intrinsic difficulty, segmentation with limited supervision is challenging and specific model design and/or learning strategies are needed. In this paper, we provide a systematic and up-to-date review of the solutions above, with summaries and comments about the methodologies. We also highlight several problems in this field, discussed future directions observing further investigations.

cs.CV↗

arXiv2021

Protograph-Based Design for QC Polar Codes

We propose a new family of polar coding which realizes high coding gain, low complexity, and high throughput by introducing a protograph-based design. The proposed technique called as quasi-cyclic (QC) polar codes can be highly parallelized without sacrificing decoding complexity. We analyze short cycles in the protograph polar codes and develop a design method to increase the girth. Our approach can resolve the long-standing unsolved problem that belief propagation (BP) decoding does not work well for polar codes due to the inherently short cycles. We demonstrate that a high lifting factor of QC polar codes can improve the performance and that QC polar codes with BP decoding can outperform conventional polar codes with state-of-the-art list decoding. Moreover, we show that a greedy pruning method can improve the performance-complexity trade-off.

cs.IT↗

arXiv2020

AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference

Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Bayesian inference framework, called AutoBayes, that explores different graphical models linking classifier, encoder, decoder, estimator and adversarial network blocks to optimize nuisance-invariant machine learning pipelines. AutoBayes also enables learning disentangled representations, where the latent variable is split into multiple pieces to impose various relationships with the nuisance variation and task labels. We benchmark the framework on several public datasets, and provide analysis of its capability for subject-transfer learning with/without variational modeling and adversarial training. We demonstrate a significant performance improvement with ensemble learning across explored graphical models.

cs.LG↗

arXiv2020

Real-time Distributed MPC for Multiple Underwater Vehicles with Limited Communication Data-rates

Controlling a fleet of autonomous underwater vehicles can be challenging due to low bandwidth communication between agents. This paper proposes to address this challenge by optimizing the quantization design of the communications between agents for use in distributed algorithms. The proposed approach considers two stages for the problem of multi-AUV control: an off-line stage where the quantization design is optimized; and an on-line stage based on a distributed model predictive control formulation and a distributed optimization algorithm with quantization. The standard properties of recursive feasibility and stability of the closed loop systems are analyzed, and simulations used to demonstrate the overall behaviour of the proposed approach.

eess.SY↗

arXiv2020

THCluster: herb supplements categorization for precision traditional Chinese medicine

There has been a continuing demand for traditional and complementary medicine worldwide. A fundamental and important topic in Traditional Chinese Medicine (TCM) is to optimize the prescription and to detect herb regularities from TCM data. In this paper, we propose a novel clustering model to solve this general problem of herb categorization, a pivotal task of prescription optimization and herb regularities. The model utilizes Random Walks method, Bayesian rules and Expectation Maximization(EM) models to complete a clustering analysis effectively on a heterogeneous information network. We performed extensive experiments on the real-world datasets and compared our method with other algorithms and experts. Experimental results have demonstrated the effectiveness of the proposed model for discovering useful categorization of herbs and its potential clinical manifestations.

q-bio.QM↗

arXiv2020

Universal Physiological Representation Learning with Soft-Disentangled Rateless Autoencoders

Human computer interaction (HCI) involves a multidisciplinary fusion of technologies, through which the control of external devices could be achieved by monitoring physiological status of users. However, physiological biosignals often vary across users and recording sessions due to unstable physical/mental conditions and task-irrelevant activities. To deal with this challenge, we propose a method of adversarial feature encoding with the concept of a Rateless Autoencoder (RAE), in order to exploit disentangled, nuisance-robust, and universal representations. We achieve a good trade-off between user-specific and task-relevant features by making use of the stochastic disentanglement of the latent representations by adopting additional adversarial networks. The proposed model is applicable to a wider range of unknown users and tasks as well as different classifiers. Results on cross-subject transfer evaluations show the advantages of the proposed framework, with up to an 11.6% improvement in the average subject-transfer classification accuracy.

eess.SP↗

arXiv2020

Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extraction

Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major challenge of physiological sensing lies in the variability of biosignals across different users and tasks. To address this issue, we propose an adversarial feature extractor for transfer learning to exploit disentangled universal representations. We consider the trade-off between task-relevant features and user-discriminative information by introducing additional adversary and nuisance networks in order to manipulate the latent representations such that the learned feature extractor is applicable to unknown users and various tasks. Results on cross-subject transfer evaluations exhibit the benefits of the proposed framework, with up to 8.8% improvement in average accuracy of classification, and demonstrate adaptability to a broader range of subjects.

cs.LG↗

arXiv2020

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing

Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond. These use cases, however, have very diverse network resource demands, e.g., communication and computation, and various performance metrics such as latency and throughput. To effectively allocate network resources to slices, we propose DeepSlicing that integrates the alternating direction method of multipliers (ADMM) and deep reinforcement learning (DRL). DeepSlicing decomposes the network slicing problem into a master problem and several slave problems. The master problem is solved based on convex optimization and the slave problem is handled by DRL method which learns the optimal resource allocation policy. The performance of the proposed algorithm is validated through network simulations.

eess.SP↗

arXiv2020

High-fidelity Two-qubit Gates Using a MEMS-based Beam Steering System for Individual Qubit Addressing

In a large scale trapped atomic ion quantum computer, high-fidelity two-qubit gates need to be extended over all qubits with individual control. We realize and characterize high-fidelity two-qubit gates in a system with up to 4 ions using radial modes. The ions are individually addressed by two tightly focused beams steered using micro-electromechanical system (MEMS) mirrors. We deduce a gate fidelity of 99.49(7)% in a two-ion chain and 99.30(6)% in a four-ion chain by applying a sequence of up to 21 two-qubit gates and measuring the final state fidelity. We characterize the residual errors and discuss methods to further improve the gate fidelity towards values that are compatible with fault-tolerant quantum computation.

quant-ph↗

arXiv2020

Single ion-qubit exceeding one hour coherence time

Realizing a long coherence time quantum memory is a major challenge of current quantum technology. Here, we report a single \Yb ion-qubit memory with over one hour coherence time, an order of improvement compared to the state-of-the-art record. The long coherence time memory is realized by addressing various technical challenges such as ambient magnetic-field noise, phase noise and leakage of the microwave oscillator. Moreover, systematically study the decoherence process of our quantum memory by quantum process tomography, which enables to apply the strict criteria of quantum coherence, relative entropy of coherence. We also benchmark our quantum memory by its ability in preserving quantum information, i.e., the robustness of quantum memory, which clearly shows that over 6000 s, our quantum memory preserves non-classical quantum information. Our results verify the stability of the quantum memory in hours level and indicate its versatile applicability in various scenarios.

quant-ph↗

arXiv2020

Deep Graph Random Process for Relational-Thinking-Based Speech Recognition

Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation of these percepts. Such mental processes are difficult to model in real-world problems such as in conversational automatic speech recognition (ASR), as the percepts (if they are modelled as graphs indicating relationships among utterances) are supposed to be innumerable and not directly observable. In this paper, we present a Bayesian nonparametric deep learning method called deep graph random process (DGP) that can generate an infinite number of probabilistic graphs representing percepts. We further provide a closed-form solution for coupling and transformation of these percept graphs for acoustic modeling. Our approach is able to successfully infer relations among utterances without using any relational data during training. Experimental evaluations on ASR tasks including CHiME-2 and CHiME-5 demonstrate the effectiveness and benefits of our method.

cs.LG↗

arXiv2020

Lattice PUF: A Strong Physical Unclonable Function Provably Secure against Machine Learning Attacks

We propose a strong physical unclonable function (PUF) provably secure against machine learning (ML) attacks with both classical and quantum computers. Its security is derived from cryptographic hardness of learning decryption functions of public-key cryptosystems. Our design compactly realizes the decryption function of the learning-with-errors (LWE) cryptosystem. Due to the fundamental connection of LWE to lattice problems, we call the construction the lattice PUF. Lattice PUF is constructed using a physically obfuscated key (POK), an LWE decryption function block, and a linear-feedback shift register (LFSR) as a pseudo-random number generator. The POK provides the secret key of the LWE decryption function; its stability is ensured by a fuzzy extractor (FE). To reduce the challenge size, we exploit distributional relaxations of space-efficient LWEs. That allows only a small challenge-seed to be transmitted with the full-length challenge generated by the LFSR, resulting in a 100X reduction of communication cost. To prevent an active challenge-manipulation attack, a self-incrementing counter is embedded into the challenge seed. We prototyped the lattice PUF with 2^136 challenge-response pairs (CRPs) on a Spartan 6 FPGA, which required 45 slices for the PUF logic proper and 233 slices for the FE. Simulation-based evaluation shows the mean (std) of uniformity to be 49.98% (1.58%), of uniqueness to be 50.00% (1.58%), and of reliability to be 1.26% (2.88%). The LWE concrete hardness estimator guarantees that a successful ML attack of the lattice PUF will require the infeasible 2^128 CPU operations. Several classes of empirical ML attacks, including support vector machine, logistic regression, and deep neural networks, are used: in all attacks, the prediction error remains above 49.76% after 1 million training CRPs.

cs.CR↗

arXiv2020

Asynchronous Byzantine Agreement in Incomplete Networks [Technical Report]

The Byzantine agreement problem is considered to be a core problem in distributed systems. For example, Byzantine agreement is needed to build a blockchain, a totally ordered log of records. Blockchains are asynchronous distributed systems, fault-tolerant against Byzantine nodes. In the literature, the asynchronous byzantine agreement problem is studied in a fully connected network model where every node can directly send messages to every other node. This assumption is questionable in many real-world environments. In the reality, nodes might need to communicate by means of an incomplete network, and Byzantine nodes might not forward messages. Furthermore, Byzantine nodes might not behave correctly and, for example, corrupt messages. Therefore, in order to truly understand Byzantine Agreement, we need both ingredients: asynchrony and incomplete communication networks. In this paper, we study the asynchronous Byzantine agreement problem in incomplete networks. A classic result by Danny Dolev proved that in a distributed system with n nodes in the presence of f Byzantine nodes, the vertex connectivity of the system communication graph should be at least (2f+1). While Dolev's result was for synchronous deterministic systems, we demonstrate that the same bound also holds for asynchronous randomized systems. We show that the bound is tight by presenting a randomized algorithm, and a matching lower bound.

cs.DC↗

arXiv2020

Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction

We propose a new concept of rateless auto-encoders (RL-AEs) that enable a flexible latent dimensionality, which can be seamlessly adjusted for varying distortion and dimensionality requirements. In the proposed RL-AEs, instead of a deterministic bottleneck architecture, we use an over-complete representation that is stochastically regularized with weighted dropouts, in a manner analogous to sparse AE (SAE). Unlike SAEs, our RL-AEs employ monotonically increasing dropout rates across the latent representation nodes such that the latent variables become sorted by importance like in principal component analysis (PCA). This is motivated by the rateless property of conventional PCA, where the least important principal components can be discarded to realize variable rate dimensionality reduction that gracefully degrades the distortion. In contrast, since the latent variables of conventional AEs are equally important for data reconstruction, they cannot be simply discarded to further reduce the dimensionality after the AE model is trained. Our proposed stochastic bottleneck framework enables seamless rate adaptation with high reconstruction performance, without requiring predetermined latent dimensionality at training. We experimentally demonstrate that the proposed RL-AEs can achieve variable dimensionality reduction while achieving low distortion compared to conventional AEs.

cs.LG↗

arXiv2020

Disentangled Adversarial Transfer Learning for Physiological Biosignals

Recent developments in wearable sensors demonstrate promising results for monitoring physiological status in effective and comfortable ways. One major challenge of physiological status assessment is the problem of transfer learning caused by the domain inconsistency of biosignals across users or different recording sessions from the same user. We propose an adversarial inference approach for transfer learning to extract disentangled nuisance-robust representations from physiological biosignal data in stress status level assessment. We exploit the trade-off between task-related features and person-discriminative information by using both an adversary network and a nuisance network to jointly manipulate and disentangle the learned latent representations by the encoder, which are then input to a discriminative classifier. Results on cross-subjects transfer evaluations demonstrate the benefits of the proposed adversarial framework, and thus show its capabilities to adapt to a broader range of subjects. Finally we highlight that our proposed adversarial transfer learning approach is also applicable to other deep feature learning frameworks.

eess.SP↗

arXiv2020

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted locations nor predict whether landmarks are visible. In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities. We model these as mixed random variables and estimate them using a deep network trained with our proposed Location, Uncertainty, and Visibility Likelihood (LUVLi) loss. In addition, we release an entirely new labeling of a large face alignment dataset with over 19,000 face images in a full range of head poses. Each face is manually labeled with the ground-truth locations of 68 landmarks, with the additional information of whether each landmark is unoccluded, self-occluded (due to extreme head poses), or externally occluded. Not only does our joint estimation yield accurate estimates of the uncertainty of predicted landmark locations, but it also yields state-of-the-art estimates for the landmark locations themselves on multiple standard face alignment datasets. Our method's estimates of the uncertainty of predicted landmark locations could be used to automatically identify input images on which face alignment fails, which can be critical for downstream tasks.

cs.CV↗

arXiv2020

Generative Deep Learning Model for a Multi-level Nano-Optic Broadband Power Splitter

We propose a novel Conditional Variational Autoencoder (CVAE) model, enhanced with adversarial censoring and active learning, for the generation of 550 nm broad bandwidth (1250 nm to 1800 nm) power splitters with arbitrary splitting ratio. The device footprint is 2.25 x 2.25 μ m2 with a 20 x 20 etched hole combination. It is the first demonstration to apply the CVAE model and the adversarial censoring for the photonics problems. We confirm that the optimized device has an overall performance close to 90% across all bandwidths from 1250 nm to 1800 nm. To the best of our knowledge, this is the smallest broadband power splitter with arbitrary ratio.

physics.optics↗

arXiv2020

Fake News Detection with Different Models

This is a paper for exploring various different models aiming at developing fake news detection models and we had used certain machine learning algorithms and we had used pretrained algorithms such as TFIDF and CV and W2V as features for processing textual data.

cs.CL↗