arXiv subjects

Jing Qin

Publications and source records attributed to Jing Qin.

At least 181 records · Page 10Linked to original sources

arXiv2019

Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully convolutional deep neural networks, we develop an end-to-end network that removes the extremely high-level s&p noise without performing any non-trivial preprocessing tasks, which is different from all the existing literature in s&p noise removal. Experiments show that inserting median layers into a simple fully-convolutional network with the L2 loss significantly boosts the signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data. The source code has been released for public evaluation and use (https://github.com/llmpass/medianDenoise).

cs.CV↗

arXiv2019

Full-semiparametric-likelihood-based inference for non-ignorable missing data

During the past few decades, missing-data problems have been studied extensively, with a focus on the ignorable missing case, where the missing probability depends only on observable quantities. By contrast, research into non-ignorable missing data problems is quite limited. The main difficulty in solving such problems is that the missing probability and the regression likelihood function are tangled together in the likelihood presentation, and the model parameters may not be identifiable even under strong parametric model assumptions. In this paper we discuss a semiparametric model for non-ignorable missing data and propose a maximum full semiparametric likelihood estimation method, which is an efficient combination of the parametric conditional likelihood and the marginal nonparametric biased sampling likelihood. The extra marginal likelihood contribution can not only produce efficiency gain but also identify the underlying model parameters without additional assumptions. We further show that the proposed estimators for the underlying parameters and the response mean are semiparametrically efficient. Extensive simulations and a real data analysis demonstrate the advantage of the proposed method over competing methods.

stat.ME↗

arXiv2019

Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis

Surgical tool presence detection and surgical phase recognition are two fundamental yet challenging tasks in surgical video analysis and also very essential components in various applications in modern operating rooms. While these two analysis tasks are highly correlated in clinical practice as the surgical process is well-defined, most previous methods tackled them separately, without making full use of their relatedness. In this paper, we present a novel method by developing a multi-task recurrent convolutional network with correlation loss (MTRCNet-CL) to exploit their relatedness to simultaneously boost the performance of both tasks. Specifically, our proposed MTRCNet-CL model has an end-to-end architecture with two branches, which share earlier feature encoders to extract general visual features while holding respective higher layers targeting for specific tasks. Given that temporal information is crucial for phase recognition, long-short term memory (LSTM) is explored to model the sequential dependencies in the phase recognition branch. More importantly, a novel and effective correlation loss is designed to model the relatedness between tool presence and phase identification of each video frame, by minimizing the divergence of predictions from the two branches. Mutually leveraging both low-level feature sharing and high-level prediction correlating, our MTRCNet-CL method can encourage the interactions between the two tasks to a large extent, and hence can bring about benefits to each other. Extensive experiments on a large surgical video dataset (Cholec80) demonstrate outstanding performance of our proposed method, consistently exceeding the state-of-the-art methods by a large margin (e.g., 89.1% v.s. 81.0% for the mAP in tool presence detection and 87.4% v.s. 84.5% for F1 score in phase recognition). The code can be found on our project website.

cs.CV↗

arXiv2019

Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation

This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in recent studies on deep learning, aiming to recover performance degradation when applying the neural networks to new testing domains. Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives. In particular, we simultaneously transform the appearance of images across domains and enhance domain-invariance of the extracted features towards the segmentation task. The feature encoder layers are shared by both perspectives to grasp their mutual benefits during the end-to-end learning procedure. Without using any annotation from the target domain, the learning of our unified model is guided by adversarial losses, with multiple discriminators employed from various aspects. We have extensively validated our method with a challenging application of cross-modality medical image segmentation of cardiac structures. Experimental results demonstrate that our SIFA model recovers the degraded performance from 17.2% to 73.0%, and outperforms the state-of-the-art methods by a significant margin.

cs.CV↗

arXiv2019

Direction-aware Spatial Context Features for Shadow Detection and Removal

Shadow detection and shadow removal are fundamental and challenging tasks, requiring an understanding of the global image semantics. This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting and removing shadows. This design is developed into the DSC module and embedded in a convolutional neural network (CNN) to learn the DSC features at different levels. Moreover, we design a weighted cross entropy loss to make effective the training for shadow detection and further adopt the network for shadow removal by using a Euclidean loss function and formulating a color transfer function to address the color and luminosity inconsistencies in the training pairs. We employed two shadow detection benchmark datasets and two shadow removal benchmark datasets, and performed various experiments to evaluate our method. Experimental results show that our method performs favorably against the state-of-the-art methods for both shadow detection and shadow removal.

cs.CV↗

arXiv2019

Test for homogeneity with unordered paired observations

In some applications, an experimental unit is composed of two distinct but related subunits. The response from such a unit is $(X_{1}, X_{2})$ but we observe only $Y_1 = \min\{X_{1},X_{2}\}$ and $Y_2 = \max\{X_{1},X_{2}\}$, i.e., the subunit identities are not observed. We call $(Y_1, Y_2)$ unordered paired observations. Based on unordered paired observations $\{(Y_{1i}, Y_{2i})\}_{i=1}^n$, we are interested in whether the marginal distributions for $X_1$ and $X_2$ are identical. Testing methods are available in the literature under the assumptions that $Var(X_1) = Var(X_2)$ and $Cov(X_1, X_2) = 0$. However, by extensive simulation studies, we observe that when one or both assumptions are violated, these methods have inflated type I errors or much lower powers. In this paper, we study the likelihood ratio test statistics for various scenarios and explore their limiting distributions without these restrictive assumptions. Furthermore, we develop Bartlett correction formulae for these statistics to enhance their precision when the sample size is not large. Simulation studies and real-data examples are used to illustrate the efficacy of the proposed methods.

math.ST↗

arXiv2019

Robust Matrix Completion via Maximum Correntropy Criterion and Half Quadratic Optimization

Robust matrix completion aims to recover a low-rank matrix from a subset of noisy entries perturbed by complex noises, where traditional methods for matrix completion may perform poorly due to utilizing $l_2$ error norm in optimization. In this paper, we propose a novel and fast robust matrix completion method based on maximum correntropy criterion (MCC). The correntropy based error measure is utilized instead of using $l_2$-based error norm to improve the robustness to noises. Using the half-quadratic optimization technique, the correntropy based optimization can be transformed to a weighted matrix factorization problem. Then, two efficient algorithms are derived, including alternating minimization based algorithm and alternating gradient descend based algorithm. The proposed algorithms do not need to calculate singular value decomposition (SVD) at each iteration. Further, the adaptive kernel selection strategy is proposed to accelerate the convergence speed as well as improve the performance. Comparison with existing robust matrix completion algorithms is provided by simulations, showing that the new methods can achieve better performance than existing state-of-the-art algorithms.

cs.IT↗

arXiv2018

Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image

In this paper, we propose a novel structure-aware 3D hourglass network for hand pose estimation from a single depth image, which achieves state-of-the-art results on MSRA and NYU datasets. Compared to existing works that perform image-to-coordination regression, our network takes 3D voxel as input and directly regresses 3D heatmap for each joint. To be specific, we use hourglass network as our backbone network and modify it into 3D form. We explicitly model tree-like finger bone into the network as well as in the loss function in an end-to-end manner, in order to take the skeleton constraints into consideration. Final estimation can then be easily obtained from voxel density map with simple post-processing. Experimental results show that the proposed structure-aware 3D hourglass network is able to achieve a mean joint error of 7.4 mm in MSRA and 8.9 mm in NYU datasets, respectively.

cs.CV↗

arXiv2018

Granger Causality Analysis Based on Quantized Minimum Error Entropy Criterion

Linear regression model (LRM) based on mean square error (MSE) criterion is widely used in Granger causality analysis (GCA), which is the most commonly used method to detect the causality between a pair of time series. However, when signals are seriously contaminated by non-Gaussian noises, the LRM coefficients will be inaccurately identified. This may cause the GCA to detect a wrong causal relationship. Minimum error entropy (MEE) criterion can be used to replace the MSE criterion to deal with the non-Gaussian noises. But its calculation requires a double summation operation, which brings computational bottlenecks to GCA especially when sizes of the signals are large. To address the aforementioned problems, in this study we propose a new method called GCA based on the quantized MEE (QMEE) criterion (GCA-QMEE), in which the QMEE criterion is applied to identify the LRM coefficients and the quantized error entropy is used to calculate the causality indexes. Compared with the traditional GCA, the proposed GCA-QMEE not only makes the results more discriminative, but also more robust. Its computational complexity is also not high because of the quantization operation. Illustrative examples on synthetic and EEG datasets are provided to verify the desirable performance and the availability of the GCA-QMEE.

stat.ME↗

arXiv2018

Compressed Anomaly Detection with Multiple Mixed Observations

We consider a collection of independent random variables that are identically distributed, except for a small subset which follows a different, anomalous distribution. We study the problem of detecting which random variables in the collection are governed by the anomalous distribution. Recent work proposes to solve this problem by conducting hypothesis tests based on mixed observations (e.g. linear combinations) of the random variables. Recognizing the connection between taking mixed observations and compressed sensing, we view the problem as recovering the "support" (index set) of the anomalous random variables from multiple measurement vectors (MMVs). Many algorithms have been developed for recovering jointly sparse signals and their support from MMVs. We establish the theoretical and empirical effectiveness of these algorithms at detecting anomalies. We also extend the LASSO algorithm to an MMV version for our purpose. Further, we perform experiments on synthetic data, consisting of samples from the random variables, to explore the trade-off between the number of mixed observations per sample and the number of samples required to detect anomalies.

cs.IT↗

arXiv2018

Sparse Randomized Kaczmarz for Support Recovery of Jointly Sparse Corrupted Multiple Measurement Vectors

While single measurement vector (SMV) models have been widely studied in signal processing, there is a surging interest in addressing the multiple measurement vectors (MMV) problem. In the MMV setting, more than one measurement vector is available and the multiple signals to be recovered share some commonalities such as a common support. Applications in which MMV is a naturally occurring phenomenon include online streaming, medical imaging, and video recovery. This work presents a stochastic iterative algorithm for the support recovery of jointly sparse corrupted MMV. We present a variant of the Sparse Randomized Kaczmarz algorithm for corrupted MMV and compare our proposed method with an existing Kaczmarz type algorithm for MMV problems. We also showcase the usefulness of our approach in the online (streaming) setting and provide empirical evidence that suggests the robustness of the proposed method to the distribution of the corruption and the number of corruptions occurring.

eess.SP↗

arXiv2018

Direction-aware Spatial Context Features for Shadow Detection

Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting shadows. This design is developed into the DSC module and embedded in a CNN to learn DSC features at different levels. Moreover, a weighted cross entropy loss is designed to make the training more effective. We employ two common shadow detection benchmark datasets and perform various experiments to evaluate our network. Experimental results show that our network outperforms state-of-the-art methods and achieves 97% accuracy and 38% reduction on balance error rate.

cs.CV↗

arXiv2018

SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection

Vision-based vehicle detection approaches achieve incredible success in recent years with the development of deep convolutional neural network (CNN). However, existing CNN based algorithms suffer from the problem that the convolutional features are scale-sensitive in object detection task but it is common that traffic images and videos contain vehicles with a large variance of scales. In this paper, we delve into the source of scale sensitivity, and reveal two key issues: 1) existing RoI pooling destroys the structure of small scale objects, 2) the large intra-class distance for a large variance of scales exceeds the representation capability of a single network. Based on these findings, we present a scale-insensitive convolutional neural network (SINet) for fast detecting vehicles with a large variance of scales. First, we present a context-aware RoI pooling to maintain the contextual information and original structure of small scale objects. Second, we present a multi-branch decision network to minimize the intra-class distance of features. These lightweight techniques bring zero extra time complexity but prominent detection accuracy improvement. The proposed techniques can be equipped with any deep network architectures and keep them trained end-to-end. Our SINet achieves state-of-the-art performance in terms of accuracy and speed (up to 37 FPS) on the KITTI benchmark and a new highway dataset, which contains a large variance of scales and extremely small objects.

cs.CV↗

arXiv2018

Inference for case-control studies with incident and prevalent cases

We propose and study a fully efficient method to estimate associations of an exposure with disease incidence when both, incident cases and prevalent cases, i.e. individuals who were diagnosed with the disease at some prior time point and are alive at the time of sampling, are included in a case-control study. We extend the exponential tilting model for the relationship between exposure and case status to accommodate two case groups, and correct for the survival bias in the prevalent cases through a tilting term that depends on the parametric distribution of the backward time, i.e. the time from disease diagnosis to study enrollment. We construct an empirical likelihood that also incorporates the observed backward times for prevalent cases, obtain efficient estimates of odds ratio parameters that relate exposure to disease incidence and propose a likelihood ratio test for model parameters that has a standard chi-squared distribution. We quantify the changes in efficiency of association parameters when incident cases are supplemented with, or replaced by, prevalent cases in simulations. We illustrate our methods by estimating associations of single nucleotide polymorphisms (SNPs) with breast cancer incidence in a sample of controls and incident and prevalent cases from the U.S. Radiologic Technologists Health Study.

stat.ME↗

arXiv2017

SFCN-OPI: Detection and Fine-grained Classification of Nuclei Using Sibling FCN with Objectness Prior Interaction

Cell nuclei detection and fine-grained classification have been fundamental yet challenging problems in histopathology image analysis. Due to the nuclei tiny size, significant inter-/intra-class variances, as well as the inferior image quality, previous automated methods would easily suffer from limited accuracy and robustness. In the meanwhile, existing approaches usually deal with these two tasks independently, which would neglect the close relatedness of them. In this paper, we present a novel method of sibling fully convolutional network with prior objectness interaction (called SFCN-OPI) to tackle the two tasks simultaneously and interactively using a unified end-to-end framework. Specifically, the sibling FCN branches share features in earlier layers while holding respective higher layers for specific tasks. More importantly, the detection branch outputs the objectness prior which dynamically interacts with the fine-grained classification sibling branch during the training and testing processes. With this mechanism, the fine-grained classification successfully focuses on regions with high confidence of nuclei existence and outputs the conditional probability, which in turn benefits the detection through back propagation. Extensive experiments on colon cancer histology images have validated the effectiveness of our proposed SFCN-OPI and our method has outperformed the state-of-the-art methods by a large margin.

cs.CV↗

arXiv2017

Automated Pulmonary Nodule Detection via 3D ConvNets with Online Sample Filtering and Hybrid-Loss Residual Learning

In this paper, we propose a novel framework with 3D convolutional networks (ConvNets) for automated detection of pulmonary nodules from low-dose CT scans, which is a challenging yet crucial task for lung cancer early diagnosis and treatment. Different from previous standard ConvNets, we try to tackle the severe hard/easy sample imbalance problem in medical datasets and explore the benefits of localized annotations to regularize the learning, and hence boost the performance of ConvNets to achieve more accurate detections. Our proposed framework consists of two stages: 1) candidate screening, and 2) false positive reduction. In the first stage, we establish a 3D fully convolutional network, effectively trained with an online sample filtering scheme, to sensitively and rapidly screen the nodule candidates. In the second stage, we design a hybrid-loss residual network which harnesses the location and size information as important cues to guide the nodule recognition procedure. Experimental results on the public large-scale LUNA16 dataset demonstrate superior performance of our proposed method compared with state-of-the-art approaches for the pulmonary nodule detection task.

cs.CV↗

arXiv2017

Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets

Automatic and accurate whole-heart and great vessel segmentation from 3D cardiac magnetic resonance (MR) images plays an important role in the computer-assisted diagnosis and treatment of cardiovascular disease. However, this task is very challenging due to ambiguous cardiac borders and large anatomical variations among different subjects. In this paper, we propose a novel densely-connected volumetric convolutional neural network, referred as DenseVoxNet, to automatically segment the cardiac and vascular structures from 3D cardiac MR images. The DenseVoxNet adopts the 3D fully convolutional architecture for effective volume-to-volume prediction. From the learning perspective, our DenseVoxNet has three compelling advantages. First, it preserves the maximum information flow between layers by a densely-connected mechanism and hence eases the network training. Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data. Third, we add auxiliary side paths to strengthen the gradient propagation and stabilize the learning process. We demonstrate the effectiveness of DenseVoxNet by comparing it with the state-of-the-art approaches from HVSMR 2016 challenge in conjunction with MICCAI, and our network achieves the best dice coefficient. We also show that our network can achieve better performance than other 3D ConvNets but with fewer parameters.

cs.CV↗

arXiv2017

ScanNet: A Fast and Dense Scanning Framework for Metastatic Breast Cancer Detection from Whole-Slide Images

Lymph node metastasis is one of the most significant diagnostic indicators in breast cancer, which is traditionally observed under the microscope by pathologists. In recent years, computerized histology diagnosis has become one of the most rapidly expanding fields in medical image computing, which alleviates pathologists' workload and reduces misdiagnosis rate. However, automatic detection of lymph node metastases from whole slide images remains a challenging problem, due to the large-scale data with enormous resolutions and existence of hard mimics. In this paper, we propose a novel framework by leveraging fully convolutional networks for efficient inference to meet the speed requirement for clinical practice, while reconstructing dense predictions under different offsets for ensuring accurate detection on both micro- and macro-metastases. Incorporating with the strategies of asynchronous sample prefetching and hard negative mining, the network can be effectively trained. Extensive experiments on the benchmark dataset of 2016 Camelyon Grand Challenge corroborated the efficacy of our method. Compared with the state-of-the-art methods, our method achieved superior performance with a faster speed on the tumor localization task and surpassed human performance on the WSI classification task.

cs.CV↗