Paper Group ANR 627
Metal Artifact Reduction in Cone-Beam X-Ray CT via Ray Profile Correction. “How Was Your Weekend?” A Generative Model of Phatic Conversation. Calibration-free B0 correction of EPI data using structured low rank matrix recovery. Estimation of multivariate asymmetric power GARCH models. Domain-Adaptive Single-View 3D Reconstruction. Hierarchical Sele …
Metal Artifact Reduction in Cone-Beam X-Ray CT via Ray Profile Correction
Title | Metal Artifact Reduction in Cone-Beam X-Ray CT via Ray Profile Correction |
Authors | Sungsoo Ha, Klaus Mueller |
Abstract | In computed tomography (CT), metal implants increase the inconsistencies between the measured data and the linear attenuation assumption made by analytic CT reconstruction algorithms. The inconsistencies give rise to dark and bright bands and streaks in the reconstructed image, collectively called metal artifacts. These artifacts make it difficult for radiologists to render correct diagnostic decisions. We describe a data-driven metal artifact reduction (MAR) algorithm for image-guided spine surgery that applies to scenarios in which a prior CT scan of the patient is available. We tested the proposed method with two clinical datasets that were both obtained during spine surgery. Using the proposed method, we were not only able to remove the dark and bright streaks caused by the implanted screws but we also recovered the anatomical structures hidden by these artifacts. This results in an improved capability of surgeons to confirm the correctness of the implanted pedicle screw placements. |
Tasks | Computed Tomography (CT), Metal Artifact Reduction |
Published | 2018-08-06 |
URL | http://arxiv.org/abs/1808.01853v1 |
http://arxiv.org/pdf/1808.01853v1.pdf | |
PWC | https://paperswithcode.com/paper/metal-artifact-reduction-in-cone-beam-x-ray |
Repo | |
Framework | |
“How Was Your Weekend?” A Generative Model of Phatic Conversation
Title | “How Was Your Weekend?” A Generative Model of Phatic Conversation |
Authors | Hannah Morrison, Chris Martens |
Abstract | Unspoken social rules, such as those that govern choosing a proper discussion topic and when to change discussion topics, guide conversational behaviors. We propose a computational model of conversation that can follow or break such rules, with participant agents that respond accordingly. Additionally, we demonstrate an application of the model: the Experimental Social Tutor (EST), a first step toward a social skills training tool that generates human-readable conversation and a conversational guideline at each point in the dialogue. Finally, we discuss the design and results of a pilot study evaluating the EST. Results show that our model is capable of producing conversations that follow social norms. |
Tasks | |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04425v1 |
http://arxiv.org/pdf/1802.04425v1.pdf | |
PWC | https://paperswithcode.com/paper/how-was-your-weekend-a-generative-model-of |
Repo | |
Framework | |
Calibration-free B0 correction of EPI data using structured low rank matrix recovery
Title | Calibration-free B0 correction of EPI data using structured low rank matrix recovery |
Authors | Arvind Balachandrasekaran, Merry Mani, Mathews Jacob |
Abstract | We introduce a structured low rank algorithm for the calibration-free compensation of field inhomogeneity artifacts in Echo Planar Imaging (EPI) MRI data. We acquire the data using two EPI readouts that differ in echo-time (TE). Using time segmentation, we reformulate the field inhomogeneity compensation problem as the recovery of an image time series from highly undersampled Fourier measurements. The temporal profile at each pixel is modeled as a single exponential, which is exploited to fill in the missing entries. We show that the exponential behavior at each pixel, along with the spatial smoothness of the exponential parameters, can be exploited to derive a 3D annihilation relation in the Fourier domain. This relation translates to a low rank property on a structured multi-fold Toeplitz matrix, whose entries correspond to the measured k-space samples. We introduce a fast two-step algorithm for the completion of the Toeplitz matrix from the available samples. In the first step, we estimate the null space vectors of the Toeplitz matrix using only its fully sampled rows. The null space is then used to estimate the signal subspace, which facilitates the efficient recovery of the time series of images. We finally demonstrate the proposed approach on spherical MR phantom data and human data and show that the artifacts are significantly reduced. The proposed approach could potentially be used to compensate for time varying field map variations in dynamic applications such as functional MRI. |
Tasks | Calibration, Time Series |
Published | 2018-04-20 |
URL | http://arxiv.org/abs/1804.07436v1 |
http://arxiv.org/pdf/1804.07436v1.pdf | |
PWC | https://paperswithcode.com/paper/calibration-free-b0-correction-of-epi-data |
Repo | |
Framework | |
Estimation of multivariate asymmetric power GARCH models
Title | Estimation of multivariate asymmetric power GARCH models |
Authors | Yacouba Boubacar Maïnassara, Othman Kadmiri, Bruno Saussereau |
Abstract | It is now widely accepted that volatility models have to incorporate the so-called leverage effect in order to to model the dynamics of daily financial returns.We suggest a new class of multivariate power transformed asymmetric models. It includes several functional forms of multivariate GARCH models which are of great interest in financial modeling and time series literature. We provide an explicit necessary and sufficient condition to establish the strict stationarity of the model. We derive the asymptotic properties of the quasi-maximum likelihood estimator of the parameters. These properties are established both when the power of the transformation is known or is unknown. The asymptotic results are illustrated by Monte Carlo experiments. An application to real financial data is also proposed. |
Tasks | Time Series |
Published | 2018-12-05 |
URL | https://arxiv.org/abs/1812.02061v2 |
https://arxiv.org/pdf/1812.02061v2.pdf | |
PWC | https://paperswithcode.com/paper/estimation-of-multivariate-asymmetric-power |
Repo | |
Framework | |
Domain-Adaptive Single-View 3D Reconstruction
Title | Domain-Adaptive Single-View 3D Reconstruction |
Authors | Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn |
Abstract | Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very expensive to acquire, current methods rely on synthetic data, in which ground-truth 3D annotation is easy to obtain. However, this results in domain adaptation problem when applied to natural images. The second challenge is that there are multiple shapes that can explain a given 2D image. In this paper, we propose a framework to improve over these challenges using adversarial training. On one hand, we impose domain confusion between natural and synthetic image representations to reduce the distribution gap. On the other hand, we impose the reconstruction to be `realistic’ by forcing it to lie on a (learned) manifold of realistic object shapes. Our experiments show that these constraints improve performance by a large margin over baseline reconstruction models. We achieve results competitive with the state of the art with a much simpler architecture. | |
Tasks | 3D Reconstruction, Domain Adaptation, Single-View 3D Reconstruction |
Published | 2018-12-04 |
URL | https://arxiv.org/abs/1812.01742v2 |
https://arxiv.org/pdf/1812.01742v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-single-view-3d-reconstruction-with-1 |
Repo | |
Framework | |
Hierarchical Selective Recruitment in Linear-Threshold Brain Networks – Part II: Multi-Layer Dynamics and Top-Down Recruitment
Title | Hierarchical Selective Recruitment in Linear-Threshold Brain Networks – Part II: Multi-Layer Dynamics and Top-Down Recruitment |
Authors | Erfan Nozari, Jorge Cortés |
Abstract | Goal-driven selective attention (GDSA) is a remarkable function that allows the complex dynamical networks of the brain to support coherent perception and cognition. Part I of this two-part paper proposes a new control-theoretic framework, termed hierarchical selective recruitment (HSR), to rigorously explain the emergence of GDSA from the brain’s network structure and dynamics. This part completes the development of HSR by deriving conditions on the joint structure of the hierarchical subnetworks that guarantee top-down recruitment of the task-relevant part of each subnetwork by the subnetwork at the layer immediately above, while inhibiting the activity of task-irrelevant subnetworks at all the hierarchical layers. To further verify the merit and applicability of this framework, we carry out a comprehensive case study of selective listening in rodents and show that a small network with HSR-based structure and minimal size can explain the data with remarkable accuracy while satisfying the theoretical requirements of HSR. Our technical approach relies on the theory of switched systems and provides a novel converse Lyapunov theorem for state-dependent switched affine systems that is of independent interest. |
Tasks | |
Published | 2018-09-05 |
URL | https://arxiv.org/abs/1809.02493v3 |
https://arxiv.org/pdf/1809.02493v3.pdf | |
PWC | https://paperswithcode.com/paper/hierarchical-selective-recruitment-in-linear-1 |
Repo | |
Framework | |
Privacy-preserving Stochastic Gradual Learning
Title | Privacy-preserving Stochastic Gradual Learning |
Authors | Bo Han, Ivor W. Tsang, Xiaokui Xiao, Ling Chen, Sai-fu Fung, Celina P. Yu |
Abstract | It is challenging for stochastic optimizations to handle large-scale sensitive data safely. Recently, Duchi et al. proposed private sampling strategy to solve privacy leakage in stochastic optimizations. However, this strategy leads to robustness degeneration, since this strategy is equal to the noise injection on each gradient, which adversely affects updates of the primal variable. To address this challenge, we introduce a robust stochastic optimization under the framework of local privacy, which is called Privacy-pREserving StochasTIc Gradual lEarning (PRESTIGE). PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL). Specifically, the noise injection leads to the issue of label noise, but the robust learning process of CL can combat with label noise. Thus, PRESTIGE yields “private but robust” updates of the primal variable on the private curriculum, namely an reordered label sequence provided by CL. In theory, we reveal the convergence rate and maximum complexity of PRESTIGE. Empirical results on six datasets show that, PRESTIGE achieves a good tradeoff between privacy preservation and robustness over baselines. |
Tasks | Stochastic Optimization |
Published | 2018-09-30 |
URL | http://arxiv.org/abs/1810.00383v1 |
http://arxiv.org/pdf/1810.00383v1.pdf | |
PWC | https://paperswithcode.com/paper/privacy-preserving-stochastic-gradual |
Repo | |
Framework | |
One for All: Neural Joint Modeling of Entities and Events
Title | One for All: Neural Joint Modeling of Entities and Events |
Authors | Trung Minh Nguyen, Thien Huu Nguyen |
Abstract | The previous work for event extraction has mainly focused on the predictions for event triggers and argument roles, treating entity mentions as being provided by human annotators. This is unrealistic as entity mentions are usually predicted by some existing toolkits whose errors might be propagated to the event trigger and argument role recognition. Few of the recent work has addressed this problem by jointly predicting entity mentions, event triggers and arguments. However, such work is limited to using discrete engineering features to represent contextual information for the individual tasks and their interactions. In this work, we propose a novel model to jointly perform predictions for entity mentions, event triggers and arguments based on the shared hidden representations from deep learning. The experiments demonstrate the benefits of the proposed method, leading to the state-of-the-art performance for event extraction. |
Tasks | |
Published | 2018-12-01 |
URL | http://arxiv.org/abs/1812.00195v1 |
http://arxiv.org/pdf/1812.00195v1.pdf | |
PWC | https://paperswithcode.com/paper/one-for-all-neural-joint-modeling-of-entities |
Repo | |
Framework | |
Learning Data Dependency with Communication Cost
Title | Learning Data Dependency with Communication Cost |
Authors | Hyeryung Jang, HyungSeok Song, Yung Yi |
Abstract | In this paper, we consider the problem of recovering a graph that represents the statistical data dependency among nodes for a set of data samples generated by nodes, which provides the basic structure to perform an inference task, such as MAP (maximum a posteriori). This problem is referred to as structure learning. When nodes are spatially separated in different locations, running an inference algorithm requires a non-negligible amount of message passing, incurring some communication cost. We inevitably have the trade-off between the accuracy of structure learning and the cost we need to pay to perform a given message-passing based inference task because the learnt edge structures of data dependency and physical connectivity graph are often highly different. In this paper, we formalize this trade-off in an optimization problem which outputs the data dependency graph that jointly considers learning accuracy and message-passing costs. We focus on a distributed MAP as the target inference task, and consider two different implementations, ASYNC-MAP and SYNC-MAP that have different message-passing mechanisms and thus different cost structures. In ASYNC- MAP, we propose a polynomial time learning algorithm that is optimal, motivated by the problem of finding a maximum weight spanning tree. In SYNC-MAP, we first prove that it is NP-hard and propose a greedy heuristic. For both implementations, we then quantify how the probability that the resulting data graphs from those learning algorithms differ from the ideal data graph decays as the number of data samples grows, using the large deviation principle, where the decaying rate is characterized by some topological structures of both original data dependency and physical connectivity graphs as well as the degree of the trade-off. We validate our theoretical findings through extensive simulations, which confirms that it has a good match. |
Tasks | |
Published | 2018-04-29 |
URL | http://arxiv.org/abs/1804.10942v1 |
http://arxiv.org/pdf/1804.10942v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-data-dependency-with-communication |
Repo | |
Framework | |
Guaranteed Simultaneous Asymmetric Tensor Decomposition via Orthogonalized Alternating Least Squares
Title | Guaranteed Simultaneous Asymmetric Tensor Decomposition via Orthogonalized Alternating Least Squares |
Authors | Furong Huang, Jialin Li, Xuchen You |
Abstract | Tensor CANDECOMP/PARAFAC (CP) decomposition is an important tool that solves a wide class of machine learning problems. Existing popular approaches recover components one by one, not necessarily in the order of larger components first. Recently developed simultaneous power method obtains only a high probability recovery of top $r$ components even when the observed tensor is noiseless. We propose a Slicing Initialized Alternating Subspace Iteration (s-ASI) method that is guaranteed to recover top $r$ components ($\epsilon$-close) simultaneously for (a)symmetric tensors almost surely under the noiseless case (with high probability for a bounded noise) using $O(\log(\log \frac{1}{\epsilon}))$ steps of tensor subspace iterations. Our s-ASI method introduces a Slice-Based Initialization that runs $O(1/\log(\frac{\lambda_r}{\lambda_{r+1}}))$ steps of matrix subspace iterations, where $\lambda_r$ denotes the r-th top singular value of the tensor. We are the first to provide a theoretical guarantee on simultaneous orthogonal asymmetric tensor decomposition. Under the noiseless case, we are the first to provide an \emph{almost sure} theoretical guarantee on simultaneous orthogonal tensor decomposition. When tensor is noisy, our algorithm for asymmetric tensor is robust to noise smaller than $\min{O(\frac{(\lambda_r - \lambda_{r+1})\epsilon}{\sqrt{r}}), O(\delta_0\frac{\lambda_r -\lambda_{r+1}}{\sqrt{d}})}$, where $\delta_0$ is a small constant proportional to the probability of bad initializations in the noisy setting. |
Tasks | |
Published | 2018-05-25 |
URL | https://arxiv.org/abs/1805.10348v2 |
https://arxiv.org/pdf/1805.10348v2.pdf | |
PWC | https://paperswithcode.com/paper/guaranteed-simultaneous-asymmetric-tensor |
Repo | |
Framework | |
Entrainment profiles: Comparison by gender, role, and feature set
Title | Entrainment profiles: Comparison by gender, role, and feature set |
Authors | Uwe D. Reichel, Štefan Beňuš, Katalin Mády |
Abstract | We examine prosodic entrainment in cooperative game dialogs for new feature sets describing register, pitch accent shape, and rhythmic aspects of utterances. For these as well as for established features we present entrainment profiles to detect within- and across-dialog entrainment by the speakers’ gender and role in the game. It turned out, that feature sets undergo entrainment in different quantitative and qualitative ways, which can partly be attributed to their different functions. Furthermore, interactions between speaker gender and role (describer vs. follower) suggest gender-dependent strategies in cooperative solution-oriented interactions: female describers entrain most, male describers least. Our data suggests a slight advantage of the latter strategy on task success. |
Tasks | |
Published | 2018-05-29 |
URL | http://arxiv.org/abs/1805.11564v1 |
http://arxiv.org/pdf/1805.11564v1.pdf | |
PWC | https://paperswithcode.com/paper/entrainment-profiles-comparison-by-gender |
Repo | |
Framework | |
Automatic Detection of Cyberbullying in Social Media Text
Title | Automatic Detection of Cyberbullying in Social Media Text |
Authors | Cynthia Van Hee, Gilles Jacobs, Chris Emmery, Bart Desmet, Els Lefever, Ben Verhoeven, Guy De Pauw, Walter Daelemans, Véronique Hoste |
Abstract | While social media offer great communication opportunities, they also increase the vulnerability of young people to threatening situations online. Recent studies report that cyberbullying constitutes a growing problem among youngsters. Successful prevention depends on the adequate detection of potentially harmful messages and the information overload on the Web requires intelligent systems to identify potential risks automatically. The focus of this paper is on automatic cyberbullying detection in social media text by modelling posts written by bullies, victims, and bystanders of online bullying. We describe the collection and fine-grained annotation of a training corpus for English and Dutch and perform a series of binary classification experiments to determine the feasibility of automatic cyberbullying detection. We make use of linear support vector machines exploiting a rich feature set and investigate which information sources contribute the most for this particular task. Experiments on a holdout test set reveal promising results for the detection of cyberbullying-related posts. After optimisation of the hyperparameters, the classifier yields an F1-score of 64% and 61% for English and Dutch respectively, and considerably outperforms baseline systems based on keywords and word unigrams. |
Tasks | |
Published | 2018-01-17 |
URL | http://arxiv.org/abs/1801.05617v1 |
http://arxiv.org/pdf/1801.05617v1.pdf | |
PWC | https://paperswithcode.com/paper/automatic-detection-of-cyberbullying-in |
Repo | |
Framework | |
Model Reconstruction from Model Explanations
Title | Model Reconstruction from Model Explanations |
Authors | Smitha Milli, Ludwig Schmidt, Anca D. Dragan, Moritz Hardt |
Abstract | We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model explanations. On the theoretical side, we give an algorithm that provably learns a two-layer ReLU network in a setting where the algorithm may query the gradient of the model with respect to chosen inputs. The number of queries is independent of the dimension and nearly optimal in its dependence on the model size. Of interest not only from a learning-theoretic perspective, this result highlights the power of gradients rather than labels as a learning primitive. Complementing our theory, we give effective heuristics for reconstructing models from gradient explanations that are orders of magnitude more query-efficient than reconstruction attacks relying on prediction interfaces. |
Tasks | |
Published | 2018-07-13 |
URL | http://arxiv.org/abs/1807.05185v1 |
http://arxiv.org/pdf/1807.05185v1.pdf | |
PWC | https://paperswithcode.com/paper/model-reconstruction-from-model-explanations |
Repo | |
Framework | |
Adversarial Active Exploration for Inverse Dynamics Model Learning
Title | Adversarial Active Exploration for Inverse Dynamics Model Learning |
Authors | Zhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann, Yi-Hsiang Chang, Chun-Yi Lee |
Abstract | We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any human intervention. Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each other. The former collects training samples for the latter, with an objective to maximize the error of the latter. The latter is trained with samples collected by the former, and generates rewards for the former when it fails to predict the actual action taken by the former. In such a competitive setting, the DRL agent learns to generate samples that the inverse dynamics model fails to predict correctly, while the inverse dynamics model learns to adapt to the challenging samples. We further propose a reward structure that ensures the DRL agent to collect only moderately hard samples but not overly hard ones that prevent the inverse model from predicting effectively. We evaluate the effectiveness of our method on several robotic arm and hand manipulation tasks against multiple baseline models. Experimental results show that our method is comparable to those directly trained with expert demonstrations, and superior to the other baselines even without any human priors. |
Tasks | Imitation Learning |
Published | 2018-06-26 |
URL | https://arxiv.org/abs/1806.10019v2 |
https://arxiv.org/pdf/1806.10019v2.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-exploration-strategy-for-self |
Repo | |
Framework | |
Detecting Cyberattacks in Industrial Control Systems Using Convolutional Neural Networks
Title | Detecting Cyberattacks in Industrial Control Systems Using Convolutional Neural Networks |
Authors | Moshe Kravchik, Asaf Shabtai |
Abstract | This paper presents a study on detecting cyberattacks on industrial control systems (ICS) using unsupervised deep neural networks, specifically, convolutional neural networks. The study was performed on a SecureWater Treatment testbed (SWaT) dataset, which represents a scaled-down version of a real-world industrial water treatment plant. e suggest a method for anomaly detection based on measuring the statistical deviation of the predicted value from the observed value.We applied the proposed method by using a variety of deep neural networks architectures including different variants of convolutional and recurrent networks. The test dataset from SWaT included 36 different cyberattacks. The proposed method successfully detects the vast majority of the attacks with a low false positive rate thus improving on previous works based on this data set. The results of the study show that 1D convolutional networks can be successfully applied to anomaly detection in industrial control systems and outperform more complex recurrent networks while being much smaller and faster to train. |
Tasks | Anomaly Detection |
Published | 2018-06-21 |
URL | http://arxiv.org/abs/1806.08110v2 |
http://arxiv.org/pdf/1806.08110v2.pdf | |
PWC | https://paperswithcode.com/paper/detecting-cyberattacks-in-industrial-control |
Repo | |
Framework | |