arXiv subjects

Yu Sun

Publications and source records attributed to Yu Sun.

At least 289 records · Page 16Linked to original sources

arXiv2020

Boosting the Performance of Plug-and-Play Priors via Denoiser Scaling

Plug-and-play priors (PnP) is an image reconstruction framework that uses an image denoiser as an imaging prior. Unlike traditional regularized inversion, PnP does not require the prior to be expressible in the form of a regularization function. This flexibility enables PnP algorithms to exploit the most effective image denoisers, leading to their state-of-the-art performance in various imaging tasks. In this paper, we propose a new denoiser scaling technique to explicitly control the amount of PnP regularization. Traditionally, the performance of PnP algorithms is controlled via intrinsic parameters of the denoiser related to the noise variance. However, many powerful denoisers, such as the ones based on convolutional neural networks (CNNs), do not have tunable parameters that would allow controlling their influence within PnP. To address this issue, we introduce a scaling parameter that adjusts the magnitude of the denoiser input and output. We theoretical justify the denoiser scaling from the perspectives of proximal optimization, statistical estimation, and consensus equilibrium. Finally, we provide numerical experiments demonstrating the ability of denoiser scaling to systematically improve the performance of PnP for denoising CNN priors that do not have explicitly tunable parameters.

eess.IV↗

arXiv2020

Measurement of Liquid Flow Rate among the Annular Flow in Vertical Tee Junction

Since the liquid flow rate of the annular flow is closely related to the heat exchange efficiency, it has great significance to measure the liquid flow rate of the annular flow in vertical tee junction. In order to acquire the liquid flow rate of the annular flow in vertical tee junction, a measurement method has been designed, which implements the digital subtraction method to measure the thickness of the liquid film under the visible light and to apply the image feature matching algorithm to obtain the liquid velocity field. Moreover, the accuracy of the liquid film velocity field as well as the spatial and temporal stability of the mass flow rate is tested by proposed algorithms in this study. Experimental results show that the measurement error of our method is approximately 5% in the lower section of the main pipe and the branch pipe, and lower than 15% in the upper section of the main pipe. Therefore, this method has a high accuracy in comparison with other measurement approaches. Our method can be applied to measure and analyse the shape and property of the annular flow in the vertical tee junction.

physics.ins-det↗

arXiv2019

ERNIE 2.0: A Continual Pre-training Framework for Language Understanding

Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing. Current pre-training procedures usually focus on training the model with several simple tasks to grasp the co-occurrence of words or sentences. However, besides co-occurring, there exists other valuable lexical, syntactic and semantic information in training corpora, such as named entity, semantic closeness and discourse relations. In order to extract to the fullest extent, the lexical, syntactic and semantic information from training corpora, we propose a continual pre-training framework named ERNIE 2.0 which builds and learns incrementally pre-training tasks through constant multi-task learning. Experimental results demonstrate that ERNIE 2.0 outperforms BERT and XLNet on 16 tasks including English tasks on GLUE benchmarks and several common tasks in Chinese. The source codes and pre-trained models have been released at https://github.com/PaddlePaddle/ERNIE.

cs.CL↗

arXiv2019

Indoor microbiome, environmental characteristics and asthma among junior high school students in Johor Bahru, Malaysia

Indoor microbial diversity and composition are suggested to affect the prevalence and severity of asthma. In this study, we collected floor dust and environmental characteristics from 21 classrooms, and health data related to asthma symptoms from 309 students, in junior high schools in Johor Bahru, Malaysia. Bacterial and fungal composition was characterized by sequencing 16s rRNA gene and internal transcribed spacer (ITS) region, and the absolute microbial concentration was quantified by qPCR. In total, 326 bacterial and 255 fungal genera were characterized. Five bacterial (Sphingobium, Rhodomicrobium, Shimwellia, Solirubrobacter, Pleurocapsa) and two fungal (Torulaspora and Leptosphaeriaceae) taxa were protective for asthma severity. Two bacterial taxa, Izhakiella and Robinsoniella, were positively associated with asthma severity. Several protective bacterial taxa including Rhodomicrobium, Shimwellia and Sphingobium has been reported as protective microbes in previous studies, whereas other taxa were first time reported. Environmental characteristics, such as age of building, size of textile curtain per room volume, occurrence of cockroaches, concentration of house dust mite allergens transferred from homes by the occupants, were involved in shaping the overall microbial community but not asthma-associated taxa; whereas visible dampness and mold, which did not change the overall microbial community for floor dust, decreased the concentration of protective bacteria Rhodomicrobium (\b{eta}=-2.86, p=0.021) of asthma, indicating complex interactions between microbes, environmental characteristics and asthma symptoms. Overall, this is the first indoor microbiome study to characterize the asthma-associated microbes and their environmental determinant in tropical area, promoting the understanding of microbial exposure and respiratory health in this region.

q-bio.GN↗

arXiv2019

Unsupervised Domain Adaptation through Self-Supervision

This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data. Like much of previous work, we seek to align the learned representations of the source and target domains while preserving discriminability. The way we accomplish alignment is by learning to perform auxiliary self-supervised task(s) on both domains simultaneously. Each self-supervised task brings the two domains closer together along the direction relevant to that task. Training this jointly with the main task classifier on the source domain is shown to successfully generalize to the unlabeled target domain. The presented objective is straightforward to implement and easy to optimize. We achieve state-of-the-art results on four out of seven standard benchmarks, and competitive results on segmentation adaptation. We also demonstrate that our method composes well with another popular pixel-level adaptation method.

cs.LG↗

arXiv2019

Infusing Learned Priors into Model-Based Multispectral Imaging

We introduce a new algorithm for regularized reconstruction of multispectral (MS) images from noisy linear measurements. Unlike traditional approaches, the proposed algorithm regularizes the recovery problem by using a prior specified \emph{only} through a learned denoising function. More specifically, we propose a new accelerated gradient method (AGM) variant of regularization by denoising (RED) for model-based MS image reconstruction. The key ingredient of our approach is the three-dimensional (3D) deep neural net (DNN) denoiser that can fully leverage spationspectral correlations within MS images. Our results suggest the generalizability of our MS-RED algorithm, where a single trained DNN can be used to solve several different MS imaging problems.

eess.IV↗

arXiv2019

Block Coordinate Regularization by Denoising

We consider the problem of estimating a vector from its noisy measurements using a prior specified only through a denoising function. Recent work on plug-and-play priors (PnP) and regularization-by-denoising (RED) has shown the state-of-the-art performance of estimators under such priors in a range of imaging tasks. In this work, we develop a new block coordinate RED algorithm that decomposes a large-scale estimation problem into a sequence of updates over a small subset of the unknown variables. We theoretically analyze the convergence of the algorithm and discuss its relationship to the traditional proximal optimization. Our analysis complements and extends recent theoretical results for RED-based estimation methods. We numerically validate our method using several denoiser priors, including those based on convolutional neural network (CNN) denoisers.

cs.CV↗

arXiv2019

Harnessing the Power of Deep Learning Methods in Healthcare: Neonatal Pain Assessment from Crying Sound

Neonatal pain assessment in clinical environments is challenging as it is discontinuous and biased. Facial/body occlusion can occur in such settings due to clinical condition, developmental delays, prone position, or other external factors. In such cases, crying sound can be used to effectively assess neonatal pain. In this paper, we investigate the use of a novel CNN architecture (N-CNN) along with other CNN architectures (VGG16 and ResNet50) for assessing pain from crying sounds of neonates. The experimental results demonstrate that using our novel N-CNN for assessing pain from the sounds of neonates has a strong clinical potential and provides a viable alternative to the current assessment practice.

cs.CV↗

arXiv2019

Online Regularization by Denoising with Applications to Phase Retrieval

Regularization by denoising (RED) is a powerful framework for solving imaging inverse problems. Most RED algorithms are iterative batch procedures, which limits their applicability to very large datasets. In this paper, we address this limitation by introducing a novel online RED (On-RED) algorithm, which processes a small subset of the data at a time. We establish the theoretical convergence of On-RED in convex settings and empirically discuss its effectiveness in non-convex ones by illustrating its applicability to phase retrieval. Our results suggest that On-RED is an effective alternative to the traditional RED algorithms when dealing with large datasets.

eess.IV↗

arXiv2019

Multi-Channel Neural Network for Assessing Neonatal Pain from Videos

Neonates do not have the ability to either articulate pain or communicate it non-verbally by pointing. The current clinical standard for assessing neonatal pain is intermittent and highly subjective. This discontinuity and subjectivity can lead to inconsistent assessment, and therefore, inadequate treatment. In this paper, we propose a multi-channel deep learning framework for assessing neonatal pain from videos. The proposed framework integrates information from two pain indicators or channels, namely facial expression and body movement, using convolutional neural network (CNN). It also integrates temporal information using a recurrent neural network (LSTM). The experimental results prove the efficiency and superiority of the proposed temporal and multi-channel framework as compared to existing similar methods.

cs.CV↗

arXiv2019

RLTM: An Efficient Neural IR Framework for Long Documents

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural ranking framework called Reinforced Long Text Matching (RLTM) which matches a query with long documents efficiently and effectively. The core idea behind the framework can be analogous to the human judgment process which firstly locates the relevance parts quickly from the whole document and then matches these parts with the query carefully to obtain the final label. Firstly, we select relevant sentences from the long documents by a coarse and efficient matching model. Secondly, we generate a relevance score by a more sophisticated matching model based on the sentence selected. The whole model is trained jointly with reinforcement learning in a pairwise manner by maximizing the expected score gaps between positive and negative examples. Experimental results demonstrate that RLTM has greatly improved the efficiency and effectiveness of the state-of-the-art models.

cs.CL↗

arXiv2019

CARL: Aggregated Search with Context-Aware Module Embedding Learning

Aggregated search aims to construct search result pages (SERPs) from blue-links and heterogeneous modules (such as news, images, and videos). Existing studies have largely ignored the correlations between blue-links and heterogeneous modules when selecting the heterogeneous modules to be presented. We observe that the top ranked blue-links, which we refer to as the \emph{context}, can provide important information about query intent and helps identify the relevant heterogeneous modules. For example, informative terms like "streamed" and "recorded" in the context imply that a video module may better satisfy the query. To model and utilize the context information for aggregated search, we propose a model with context attention and representation learning (CARL). Our model applies a recurrent neural network with an attention mechanism to encode the context, and incorporates the encoded context information into module embeddings. The context-aware module embeddings together with the ranking policy are jointly optimized under the Markov decision process (MDP) formulation. To achieve a more effective joint learning, we further propose an optimization function with self-supervision loss to provide auxiliary supervision signals. Experimental results based on two public datasets demonstrate the superiority of CARL over multiple baseline approaches, and confirm the effectiveness of the proposed optimization function in boosting the joint learning process.

cs.IR↗

arXiv2019

A New Recurrent Plug-and-Play Prior Based on the Multiple Self-Similarity Network

Recent work has shown the effectiveness of the plug-and-play priors (PnP) framework for regularized image reconstruction. However, the performance of PnP depends on the quality of the denoisers used as priors. In this letter, we design a novel PnP denoising prior, called multiple self-similarity net (MSSN), based on the recurrent neural network (RNN) with self-similarity matching using multi-head attention mechanism. Unlike traditional neural net denoisers, MSSN exploits different types of relationships among non-local and repeating features to remove the noise in the input image. We numerically evaluate the performance of MSSN as a module within PnP for solving magnetic resonance (MR) image reconstruction. Experimental results show the stable convergence and excellent performance of MSSN for reconstructing images from highly compressive Fourier measurements.

eess.IV↗

arXiv2019

Accurate Robotic Pouring for Serving Drinks

Pouring is the second most frequently executed motion in cooking scenarios. In this work, we present our system of accurate pouring that generates the angular velocities of the source container using recurrent neural networks. We collected demonstrations of human pouring water. We made a physical system on which the velocities of the source container were generated at each time step and executed by a motor. We tested our system on pouring water from containers that are not used for training and achieved an error of as low as 4 milliliters. We also used the system to pour oil and syrup. The accuracy achieved with oil is slightly lower than but comparable with that of water.

cs.RO↗

arXiv2019

Joint Object and State Recognition using Language Knowledge

The state of an object is an important piece of knowledge in robotics applications. States and objects are intertwined together, meaning that object information can help recognize the state of an image and vice versa. This paper addresses the state identification problem in cooking related images and uses state and object predictions together to improve the classification accuracy of objects and their states from a single image. The pipeline presented in this paper includes a CNN with a double classification layer and the Concept-Net language knowledge graph on top. The language knowledge creates a semantic likelihood between objects and states. The resulting object and state confidences from the deep architecture are used together with object and state relatedness estimates from a language knowledge graph to produce marginal probabilities for objects and states. The marginal probabilities and confidences of objects (or states) are fused together to improve the final object (or state) classification results. Experiments on a dataset of cooking objects show that using a language knowledge graph on top of a deep neural network effectively enhances object and state classification.

cs.CV↗

arXiv2019

ERNIE: Enhanced Representation through Knowledge Integration

We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration). Inspired by the masking strategy of BERT, ERNIE is designed to learn language representation enhanced by knowledge masking strategies, which includes entity-level masking and phrase-level masking. Entity-level strategy masks entities which are usually composed of multiple words.Phrase-level strategy masks the whole phrase which is composed of several words standing together as a conceptual unit.Experimental results show that ERNIE outperforms other baseline methods, achieving new state-of-the-art results on five Chinese natural language processing tasks including natural language inference, semantic similarity, named entity recognition, sentiment analysis and question answering. We also demonstrate that ERNIE has more powerful knowledge inference capacity on a cloze test.

cs.CL↗

arXiv2019

Machine-based Multimodal Pain Assessment Tool for Infants: A Review

Bedside caregivers assess infants' pain at constant intervals by observing specific behavioral and physiological signs of pain. This standard has two main limitations. The first limitation is the intermittent assessment of pain, which might lead to missing pain when the infants are left unattended. Second, it is inconsistent since it depends on the observer's subjective judgment and differs between observers. The intermittent and inconsistent assessment can induce poor treatment and, therefore, cause serious long-term consequences. To mitigate these limitations, the current standard can be augmented by an automated system that monitors infants continuously and provides quantitative and consistent assessment of pain. Several automated methods have been introduced to assess infants' pain automatically based on analysis of behavioral or physiological pain indicators. This paper comprehensively reviews the automated approaches (i.e., approaches to feature extraction) for analyzing infants' pain and the current efforts in automatic pain recognition. In addition, it reviews the databases available to the research community and discusses the current limitations of the automated pain assessment.

cs.CV↗

arXiv2018

Stability of Scattering Decoder For Nonlinear Diffractive Imaging

The problem of image reconstruction under multiple light scattering is usually formulated as a regularized non-convex optimization. A deep learning architecture, Scattering Decoder (ScaDec), was recently proposed to solve this problem in a purely data-driven fashion. The proposed method was shown to substantially outperform optimization-based baselines and achieve state-of-the-art results. In this paper, we thoroughly test the robustness of ScaDec to different permittivity contrasts, number of transmissions, and input signal-to-noise ratios. The results on high-fidelity simulated datasets show that the performance of ScaDec is stable in different settings.

cs.CV↗