January 27, 2020

2798 words 14 mins read

Paper Group ANR 1228

Adaptive surrogate models for parametric studies. Signed Link Prediction with Sparse Data: The Role of Personality Information. AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures. Fault-Tolerant Routing in Hypercube Networks by Avoiding Faulty Nodes. FARSA: Fully Automated Roadway Safety Assessment. Efficient Identif …

Adaptive surrogate models for parametric studies


Title	Adaptive surrogate models for parametric studies
Authors	Jan N. Fuhg
Abstract	The computational effort for the evaluation of numerical simulations based on e.g. the finite-element method is high. Metamodels can be utilized to create a low-cost alternative. However the number of required samples for the creation of a sufficient metamodel should be kept low, which can be achieved by using adaptive sampling techniques. In this Master thesis adaptive sampling techniques are investigated for their use in creating metamodels with the Kriging technique, which interpolates values by a Gaussian process governed by prior covariances. The Kriging framework with extension to multifidelity problems is presented and utilized to compare adaptive sampling techniques found in the literature for benchmark problems as well as applications for contact mechanics. This thesis offers the first comprehensive comparison of a large spectrum of adaptive techniques for the Kriging framework. Furthermore a multitude of adaptive techniques is introduced to multifidelity Kriging as well as well as to a Kriging model with reduced hyperparameter dimension called partial least squares Kriging. In addition, an innovative adaptive scheme for binary classification is presented and tested for identifying chaotic motion of a Duffing’s type oscillator.
Tasks
Published	2019-05-12
URL	https://arxiv.org/abs/1905.05345v1
PDF	https://arxiv.org/pdf/1905.05345v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-surrogate-models-for-parametric
Repo
Framework

Signed Link Prediction with Sparse Data: The Role of Personality Information


Title	Signed Link Prediction with Sparse Data: The Role of Personality Information
Authors	Ghazaleh Beigi, Suhas Ranganath, Huan Liu
Abstract	Predicting signed links in social networks often faces the problem of signed link data sparsity, i.e., only a small percentage of signed links are given. The problem is exacerbated when the number of negative links is much smaller than that of positive links. Boosting signed link prediction necessitates additional information to compensate for data sparsity. According to psychology theories, one rich source of such information is user’s personality such as optimism and pessimism that can help determine her propensity in establishing positive and negative links. In this study, we investigate how personality information can be obtained, and if personality information can help alleviate the data sparsity problem for signed link prediction. We propose a novel signed link prediction model that enables empirical exploration of user personality via social media data. We evaluate our proposed model on two datasets of real-world signed link networks. The results demonstrate the complementary role of personality information in the signed link prediction problem. Experimental results also indicate the effectiveness of different levels of personality information for signed link data sparsity problem.
Tasks	Link Prediction
Published	2019-03-06
URL	http://arxiv.org/abs/1903.02125v1
PDF	http://arxiv.org/pdf/1903.02125v1.pdf
PWC	https://paperswithcode.com/paper/signed-link-prediction-with-sparse-data-the
Repo
Framework

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures


Title	AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
Authors	Michael S. Ryoo, AJ Piergiovanni, Mingxing Tan, Anelia Angelova
Abstract	Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time dimension, using modules such as 3D convolutions, or by using two-stream design to capture both appearance and motion in videos. We interpret a video CNN as a collection of multi-stream convolutional blocks connected to each other, and propose the approach of automatically finding neural architectures with better connectivity and spatio-temporal interactions for video understanding. This is done by evolving a population of overly-connected architectures guided by connection weight learning. Architectures combining representations that abstract different input types (i.e., RGB and optical flow) at multiple temporal resolutions are searched for, allowing different types or sources of information to interact with each other. Our method, referred to as AssembleNet, outperforms prior approaches on public video datasets, in some cases by a great margin. We obtain 58.6% mAP on Charades and 34.27% accuracy on Moments-in-Time.
Tasks	Action Classification, Action Recognition In Videos, Multimodal Activity Recognition, Optical Flow Estimation, Video Classification, Video Understanding
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13209v2
PDF	https://arxiv.org/pdf/1905.13209v2.pdf
PWC	https://paperswithcode.com/paper/assemblenet-searching-for-multi-stream-neural
Repo
Framework

Fault-Tolerant Routing in Hypercube Networks by Avoiding Faulty Nodes


Title	Fault-Tolerant Routing in Hypercube Networks by Avoiding Faulty Nodes
Authors	Shadrokh Samavi, Pejman Khadivi
Abstract	Next to the high performance, the essential feature of the multiprocessor systems is their fault-tolerant capability. In this regard, fault-tolerant interconnection networks and especially fault-tolerant routing methods are crucial parts of these systems. Hypercube is a popular interconnection network that is used in many multiprocessors. There are several suggested practices for fault tolerant routing in these systems. In this paper, a neural routing method is introduced which is named as Fault Avoidance Routing (FAR). This method keeps the message as far from the faulty nodes as possible. The proposed method employs the Hopfield neural network. In comparison with other neural routing methods, FAR requires a small number of neurons. The simulation results show that FAR has excellent performance in larger interconnection networks and networks with a high density of faulty nodes.
Tasks
Published	2019-05-01
URL	http://arxiv.org/abs/1905.03086v1
PDF	http://arxiv.org/pdf/1905.03086v1.pdf
PWC	https://paperswithcode.com/paper/190503086
Repo
Framework

FARSA: Fully Automated Roadway Safety Assessment


Title	FARSA: Fully Automated Roadway Safety Assessment
Authors	Weilian Song, Scott Workman, Armin Hadzic, Xu Zhang, Eric Green, Mei Chen, Reginald Souleyrette, Nathan Jacobs
Abstract	This paper addresses the task of road safety assessment. An emerging approach for conducting such assessments in the United States is through the US Road Assessment Program (usRAP), which rates roads from highest risk (1 star) to lowest (5 stars). Obtaining these ratings requires manual, fine-grained labeling of roadway features in street-level panoramas, a slow and costly process. We propose to automate this process using a deep convolutional neural network that directly estimates the star rating from a street-level panorama, requiring milliseconds per image at test time. Our network also estimates many other road-level attributes, including curvature, roadside hazards, and the type of median. To support this, we incorporate task-specific attention layers so the network can focus on the panorama regions that are most useful for a particular task. We evaluated our approach on a large dataset of real-world images from two US states. We found that incorporating additional tasks, and using a semi-supervised training approach, significantly reduced overfitting problems, allowed us to optimize more layers of the network, and resulted in higher accuracy.
Tasks
Published	2019-01-17
URL	http://arxiv.org/abs/1901.06013v1
PDF	http://arxiv.org/pdf/1901.06013v1.pdf
PWC	https://paperswithcode.com/paper/farsa-fully-automated-roadway-safety
Repo
Framework

Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets


Title	Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets
Authors	Daniel Kumor, Bryant Chen, Elias Bareinboim
Abstract	One of the most common mistakes made when performing data analysis is attributing causal meaning to regression coefficients. Formally, a causal effect can only be computed if it is identifiable from a combination of observational data and structural knowledge about the domain under investigation (Pearl, 2000, Ch. 5). Building on the literature of instrumental variables (IVs), a plethora of methods has been developed to identify causal effects in linear systems. Almost invariably, however, the most powerful such methods rely on exponential-time procedures. In this paper, we investigate graphical conditions to allow efficient identification in arbitrary linear structural causal models (SCMs). In particular, we develop a method to efficiently find unconditioned instrumental subsets, which are generalizations of IVs that can be used to tame the complexity of many canonical algorithms found in the literature. Further, we prove that determining whether an effect can be identified with TSID (Weihs et al., 2017), a method more powerful than unconditioned instrumental sets and other efficient identification algorithms, is NP-Complete. Finally, building on the idea of flow constraints, we introduce a new and efficient criterion called Instrumental Cutsets (IC), which is able to solve for parameters missed by all other existing polynomial-time algorithms.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13493v1
PDF	https://arxiv.org/pdf/1910.13493v1.pdf
PWC	https://paperswithcode.com/paper/efficient-identification-in-linear-structural
Repo
Framework

Large Deviation Analysis of Function Sensitivity in Random Deep Neural Networks


Title	Large Deviation Analysis of Function Sensitivity in Random Deep Neural Networks
Authors	Bo Li, David Saad
Abstract	Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation of functions represented by DNN from their typical mean field solutions. The parameter perturbations investigated include weight sparsification (dilution) and binarization, which are commonly used in model simplification, for both ReLU and sign activation functions. We find that random networks with ReLU activation are more robust to parameter perturbations with respect to their counterparts with sign activation, which arguably is reflected in the simplicity of the functions they generate.
Tasks
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05769v2
PDF	https://arxiv.org/pdf/1910.05769v2.pdf
PWC	https://paperswithcode.com/paper/large-deviation-analysis-of-function
Repo
Framework

Disentangling Video with Independent Prediction


Title	Disentangling Video with Independent Prediction
Authors	William F. Whitney, Rob Fergus
Abstract	We propose an unsupervised variational model for disentangling video into independent factors, i.e. each factor’s future can be predicted from its past without considering the others. We show that our approach often learns factors which are interpretable as objects in a scene.
Tasks
Published	2019-01-17
URL	http://arxiv.org/abs/1901.05590v1
PDF	http://arxiv.org/pdf/1901.05590v1.pdf
PWC	https://paperswithcode.com/paper/disentangling-video-with-independent
Repo
Framework

Neural Networks with Cheap Differential Operators


Title	Neural Networks with Cheap Differential Operators
Authors	Ricky T. Q. Chen, David Duvenaud
Abstract	Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise derivatives, used in cases such as computing the divergence. Our proposed architecture has a Jacobian matrix composed of diagonal and hollow (non-diagonal) components. We can then modify the backward computation graph to extract dimension-wise derivatives efficiently with automatic differentiation. We demonstrate these cheap differential operators for solving root-finding subproblems in implicit ODE solvers, exact density evaluation for continuous normalizing flows, and evaluating the Fokker–Planck equation for training stochastic differential equation models.
Tasks
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03579v1
PDF	https://arxiv.org/pdf/1912.03579v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-with-cheap-differential-1
Repo
Framework

Compressed MRI Reconstruction Exploiting a Rotation-Invariant Total Variation Discretization


Title	Compressed MRI Reconstruction Exploiting a Rotation-Invariant Total Variation Discretization
Authors	Erfan Ebrahim Esfahani, Alireza Hosseini
Abstract	Inspired by the first-order method of Malitsky and Pock, we propose a novel variational framework for compressed MR image reconstruction which introduces the application of a rotation-invariant discretization of total variation functional into MR imaging while exploiting BM3D frame as a sparsifying transform. In the first step, we provide theoretical and numerical analysis establishing the exceptional rotation-invariance property of this total variation functional and observe its superiority over other well-known variational regularization terms in both upright and rotated imaging setups. Then, the proposed MRI reconstruction model is presented as a constrained optimization problem, however, we do not use conventional ADMM-type algorithms designed for constrained problems to obtain a solution, but rather we tailor the linesearch-equipped method of Malitsky and Pock to our model, which was originally proposed for unconstrained problems. As attested by numerical experiments, this framework significantly outperforms various state-of-the-art algorithms from variational methods to adaptive and learning approaches and in particular, it eliminates the stagnating behavior of a previous work on BM3D-MRI which compromised the solution beyond a certain iteration.
Tasks	Image Reconstruction
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11854v3
PDF	https://arxiv.org/pdf/1911.11854v3.pdf
PWC	https://paperswithcode.com/paper/compressed-mri-reconstruction-exploiting-a
Repo
Framework

Unified Adversarial Invariance


Title	Unified Adversarial Invariance
Authors	Ayush Jaiswal, Yue Wu, Wael AbdAlmageed, Premkumar Natarajan
Abstract	We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions. Invariance to nuisance is achieved by learning a split representation of data through competitive training between the prediction task and a reconstruction task coupled with disentanglement, whereas that to biasing factors is brought about by penalizing the network if the latent embedding contains any information about them. We describe an adversarial instantiation of this framework and provide analysis of its working. Our model outperforms previous works at inducing invariance to nuisance factors without using any labeled information about such variables, and achieves state-of-the-art performance at learning independence to biasing factors in fairness settings.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.03629v2
PDF	https://arxiv.org/pdf/1905.03629v2.pdf
PWC	https://paperswithcode.com/paper/190503629
Repo
Framework

Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction


Title	Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction
Authors	Christopher M. Sandino, Peng Lai, Shreyas S. Vasanawala, Joseph Y. Cheng
Abstract	A novel neural network architecture, known as DL-ESPIRiT, is proposed to reconstruct rapidly acquired cardiac MRI data without field-of-view limitations which are present in previously proposed deep learning-based reconstruction frameworks. Additionally, a novel convolutional neural network based on separable 3D convolutions is integrated into DL-ESPIRiT to more efficiently learn spatiotemporal priors for dynamic image reconstruction. The network is trained on fully-sampled 2D cardiac cine datasets collected from eleven healthy volunteers with IRB approval. DL-ESPIRiT is compared against a state-of-the-art parallel imaging and compressed sensing method known as $l_1$-ESPIRiT. The reconstruction accuracy of both methods is evaluated on retrospectively undersampled datasets (R=12) with respect to standard image quality metrics as well as automatic deep learning-based segmentations of left ventricular volumes. Feasibility of this approach is demonstrated in reconstructions of prospectively undersampled data which were acquired in a single heartbeat per slice.
Tasks	Image Reconstruction
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05845v2
PDF	https://arxiv.org/pdf/1911.05845v2.pdf
PWC	https://paperswithcode.com/paper/accelerating-cardiac-cine-mri-beyond
Repo
Framework

Rain O’er Me: Synthesizing real rain to derain with data distillation


Title	Rain O’er Me: Synthesizing real rain to derain with data distillation
Authors	Huangxing Lin, Yanlong Li, Xinghao Ding, Weihong Zeng, Yue Huang, John Paisley
Abstract	We present a supervised technique for learning to remove rain from images without using synthetic rain software. The method is based on a two-stage data distillation approach: 1) A rainy image is first paired with a coarsely derained version using on a simple filtering technique (“rain-to-clean”). 2) Then a clean image is randomly matched with the rainy soft-labeled pair. Through a shared deep neural network, the rain that is removed from the first image is then added to the clean image to generate a second pair (“clean-to-rain”). The neural network simultaneously learns to map both images such that high resolution structure in the clean images can inform the deraining of the rainy images. Demonstrations show that this approach can address those visual characteristics of rain not easily synthesized by software in the usual way.
Tasks	Rain Removal
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04605v2
PDF	http://arxiv.org/pdf/1904.04605v2.pdf
PWC	https://paperswithcode.com/paper/rain-oer-me-synthesizing-real-rain-to-derain
Repo
Framework

This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity


Title	This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
Authors	David Haldimann, Hermann Blum, Roland Siegwart, Cesar Cadena
Abstract	There has been a remarkable progress in the accuracy of semantic segmentation due to the capabilities of deep learning. Unfortunately, these methods are not able to generalize much further than the distribution of their training data and fail to handle out-of-distribution classes appropriately. This limits the applicability to autonomous or safety critical systems. We propose a novel method leveraging generative models to detect wrongly segmented or out-of-distribution instances. Conditioned on the predicted semantic segmentation, an RGB image is generated. We then learn a dissimilarity metric that compares the generated image with the original input and detects inconsistencies introduced by the semantic segmentation. We present test cases for outlier and misclassification detection and evaluate our method qualitatively and quantitatively on multiple datasets.
Tasks	Semantic Segmentation
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00676v1
PDF	https://arxiv.org/pdf/1909.00676v1.pdf
PWC	https://paperswithcode.com/paper/this-is-not-what-i-imagined-error-detection
Repo
Framework

Recursive Filter for Space-Variant Variance Reduction


Title	Recursive Filter for Space-Variant Variance Reduction
Authors	Alexander Zamyatin
Abstract	We propose a method to reduce non-uniform sample variance to a predetermined target level. The proposed space-variant filter can equalize variance of the non-stationary signal, or vary filtering strength based on image features, such as edges, etc., as shown by applications in this work. This approach computes variance reduction ratio at each point of the image, based on the given target variance. Then, a space-variant filter with matching variance reduction power is applied. A mathematical framework of atomic kernels is developed to facilitate stable and fast computation of the filter bank kernels. Recursive formulation allows using small kernel size, which makes the space-variant filter more suitable for fast parallel implementation. Despite the small kernel size, the recursive filter possesses strong variance reduction power. Filter accuracy is measured by the variance reduction against the target variance; testing demonstrated high accuracy of variance reduction of the recursive filter compared to the fixed-size filter. The proposed filter was applied to adaptive filtering in image reconstruction and edge-preserving denoising.
Tasks	Denoising, Image Reconstruction
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04992v2
PDF	https://arxiv.org/pdf/1911.04992v2.pdf
PWC	https://paperswithcode.com/paper/recursive-filter-for-space-variant-variance
Repo
Framework