Discussion: Bayesian Optimal Design of Experiments for Inferring the Statistical Expectation of Expensive Black-Box Functions (Pandita, P., Bilionis, I., and Panchal, J., 2019. ASME. J. Mech. Des. 141(10): 101404)

The authors of the discussed paper simplified the information-based acquisition on estimating statistical expectation and developed analytical computation for each involved quantity under uniform input distribution. In this discussion, we show that (1) the last three terms of the acquisition always add up to zero, leaving a concise form with a much more intuitive interpretation of the acquisition; (2) the analytical computation of the acquisition can be generalized to arbitrary input distribution, greatly broadening the application of the developed framework.

Numerical investigation of turbulence of surface gravity waves

In this paper, we numerically study the wave turbulence of surface gravity waves in the framework of Euler equations of the free surface. The purpose is to understand the variation of the scaling of the spectra with wavenumber $k$ and energy flux $P$ at different nonlinearity levels under different forcing/free-decay conditions. For all conditions (free decay, narrow- and broadband forcing) we consider, we find that the spectral forms approach wave turbulence theory (WTT) solution $S_etasim k^{-5/2}$ and $S_etasim P^{1/3}$ at high nonlinearity levels. With the decrease of nonlinearity level, the spectra for all cases become steeper, with the narrow-band forcing case exhibiting the most rapid deviation from WTT. To interpret these spectral variations, we further investigate two hypothetical and disputable mechanisms about bound waves and finite-size effect. Through a tri-coherence analysis, we find that the finite-size effect is present in all cases, which is responsible for the overall steepening of the spectra and reduced capacity of energy flux at lower nonlinearity levels. The fraction of bound waves in the domain generally decreases with the decrease of nonlinearity level, except for the narrow-band case, which exhibits a transition at some critical nonlinearity level below which a rapid increase is observed. This increase serves as the main reason for the fastest deviation from WTT with the decrease of nonlinearity in the narrow-band forcing case.

Energy transfer for solutions to the nonlinear Schrodinger equation on irrational tori

We analyze the energy transfer for solutions to the defocusing cubic nonlinear Schrodinger (NLS) initial value problem on 2D irrational tori. Moreover we complement the analytic study with numerical experimentation. As a biproduct of our investigation we also prove that the quasi-resonant part of the NLS initial value problem we consider, in both the focusing and defocusing case, is globally well-posed for initial data of finite mass.

AFINet: Attentive Feature Integration Networks for Image Classification

Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification. Recent advanced models in CNNs, such as ResNets, mainly focus on the skip connection to avoid gradient vanishing. DenseNet designs suggest creating additional bypasses to transfer features as an alternative strategy in network design. In this paper, we design Attentive Feature Integration (AFI) modules, which are widely applicable to most recent network architectures, leading to new architectures named AFI-Nets. AFI-Nets explicitly model the correlations among different levels of features and selectively transfer features with a little overhead.AFI-ResNet-152 obtains a 1.24% relative improvement on the ImageNet dataset while decreases the FLOPs by about 10% and the number of parameters by about 9.2% compared to ResNet-152.

Self-supervised Video Retrieval Transformer Network

Content-based video retrieval aims to find videos from a large video database that are similar to or even near-duplicate of a given query video. Video representation and similarity search algorithms are crucial to any video retrieval system. To derive effective video representation, most video retrieval systems require a large amount of manually annotated data for training, making it costly inefficient. In addition, most retrieval systems are based on frame-level features for video similarity searching, making it expensive both storage wise and search wise. We propose a novel video retrieval system, termed SVRTN, that effectively addresses the above shortcomings. It first applies self-supervised training to effectively learn video representation from unlabeled data to avoid the expensive cost of manual annotation. Then, it exploits transformer structure to aggregate frame-level features into clip-level to reduce both storage space and search complexity. It can learn the complementary and discriminative information from the interactions among clip frames, as well as acquire the frame permutation and missing invariant ability to support more flexible retrieval manners. Comprehensive experiments on two challenging video retrieval datasets, namely FIVR-200K and SVD, verify the effectiveness of our proposed SVRTN method, which achieves the best performance of video retrieval on accuracy and efficiency.

Automatic Pulmonary Artery-Vein Separation in CT Images using Twin-Pipe Network and Topology Reconstruction

With the development of medical computer-aided diagnostic systems, pulmonary artery-vein(A/V) separation plays a crucial role in assisting doctors in preoperative planning for lung cancer surgery. However, distinguishing arterial from venous irrigation in chest CT images remains a challenge due to the similarity and complex structure of the arteries and veins. We propose a novel method for automatic separation of pulmonary arteries and veins from chest CT images. The method consists of three parts. First, global connection information and local feature information are used to construct a complete topological tree and ensure the continuity of vessel reconstruction. Second, the Twin-Pipe network proposed can automatically learn the differences between arteries and veins at different levels to reduce classification errors caused by changes in terminal vessel characteristics. Finally, the topology optimizer considers interbranch and intrabranch topological relationships to maintain spatial consistency to avoid the misclassification of A/V irrigations. We validate the performance of the method on chest CT images. Compared with manual classification, the proposed method achieves an average accuracy of 96.2% on noncontrast chest CT. In addition, the method has been proven to have good generalization, that is, the accuracies of 93.8% and 94.8% are obtained for CT scans from other devices and other modes, respectively. The result of pulmonary artery-vein obtained by the proposed method can provide better assistance for preoperative planning of lung cancer surgery.

Coarse-to-fine Airway Segmentation Using Multi information Fusion Network and CNN-based Region Growing

Automatic airway segmentation from chest computed tomography (CT) scans plays an important role in pulmonary disease diagnosis and computer-assisted therapy. However, low contrast at peripheral branches and complex tree-like structures remain as two mainly challenges for airway segmentation. Recent research has illustrated that deep learning methods perform well in segmentation tasks. Motivated by these works, a coarse-to-fine segmentation framework is proposed to obtain a complete airway tree. Our framework segments the overall airway and small branches via the multi-information fusion convolution neural network (Mif-CNN) and the CNN-based region growing, respectively. In Mif-CNN, atrous spatial pyramid pooling (ASPP) is integrated into a u-shaped network, and it can expend the receptive field and capture multi-scale information. Meanwhile, boundary and location information are incorporated into semantic information. These information are fused to help Mif-CNN utilize additional context knowledge and useful features. To improve the performance of the segmentation result, the CNN-based region growing method is designed to focus on obtaining small branches. A voxel classification network (VCN), which can entirely capture the rich information around each voxel, is applied to classify the voxels into airway and non-airway. In addition, a shape reconstruction method is used to refine the airway tree.

Sequential Bayesian experimental design for estimation of extreme-event probability in stochastic dynamical systems

We consider a dynamical system with two sources of uncertainties: (1) parameterized input with a known probability distribution and (2) stochastic input-to-response (ItR) function with heteroscedastic randomness. Our purpose is to efficiently quantify the extreme response probability when the ItR function is expensive to evaluate. The problem setup arises often in physics and engineering problems, with randomness in ItR coming from either intrinsic uncertainties (say, as a solution to a stochastic equation) or additional (critical) uncertainties that are not incorporated in the input parameter space. To reduce the required sampling numbers, we develop a sequential Bayesian experimental design method leveraging the variational heteroscedastic Gaussian process regression (VHGPR) to account for the stochastic ItR, along with a new criterion to select the next-best samples sequentially. The validity of our new method is first tested in two synthetic problems with the stochastic ItR functions defined artificially. Finally, we demonstrate the application of our method to an engineering problem of estimating the extreme ship motion probability in ensemble of wave groups, where the uncertainty in ItR naturally originates from the uncertain initial condition of ship motion in each wave group.

RegNet: Self-Regulated Network for Image Classification

The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the simple shortcut connection mechanism limits the ability of re-exploring new potentially complementary features due to the additive function. To address this issue, in this paper, we propose to introduce a regulator module as a memory mechanism to extract complementary features, which are further fed to the ResNet. In particular, the regulator module is composed of convolutional RNNs (e.g., Convolutional LSTMs or Convolutional GRUs), which are shown to be good at extracting Spatio-temporal information. We named the new regulated networks as RegNet. The regulator module can be easily implemented and appended to any ResNet architecture. We also apply the regulator module for improving the Squeeze-and-Excitation ResNet to show the generalization ability of our method. Experimental results on three image classification datasets have demonstrated the promising performance of the proposed architecture compared with the standard ResNet, SE-ResNet, and other state-of-the-art architectures.

Phase-resolved ocean wave forecast with ensemble-based data assimilation

Through ensemble-based data assimilation (DA), we address one of the most notorious difficulties in phase-resolved ocean wave forecast, regarding the deviation of numerical solution from the true surface elevation due to the chaotic nature of and underrepresented physics in the nonlinear wave models. In particular, we develop a coupled approach of the high-order spectral (HOS) method with the ensemble Kalman filter (EnKF), through which the measurement data can be incorporated into the simulation to improve the forecast performance. A unique feature in this coupling is the mismatch between the predictable zone and measurement region, which is accounted for through a special algorithm to modify the analysis equation in EnKF. We test the performance of the new EnKF-HOS method using both synthetic data and real radar measurements. For both cases (though differing in details), it is shown that the new method achieves much higher accuracy than the HOS-only method, and can retain the phase information of an irregular wave field for arbitrarily long forecast time with sequentially assimilated data.