October 19, 2019

2954 words 14 mins read

Paper Group ANR 313

Paper Group ANR 313

Learning to quantify emphysema extent: What labels do we need?. Proxy Fairness. Unifying Gaussian LWF and AMP Chain Graphs to Model Interference. Nonlinear Robust Filtering of Sampled-Data Dynamical Systems. Mathematical Analysis of Adversarial Attacks. Quantization for Rapid Deployment of Deep Neural Networks. The algorithm of formation of a train …

Learning to quantify emphysema extent: What labels do we need?

Title Learning to quantify emphysema extent: What labels do we need?
Authors Silas Nyboe Ørting, Jens Petersen, Laura H. Thomsen, Mathilde M. W. Wille, Marleen de Bruijne
Abstract Accurate assessment of pulmonary emphysema is crucial to assess disease severity and subtype, to monitor disease progression and to predict lung cancer risk. However, visual assessment is time-consuming and subject to substantial inter-rater variability and standard densitometry approaches to quantify emphysema remain inferior to visual scoring. We explore if machine learning methods that learn from a large dataset of visually assessed CT scans can provide accurate estimates of emphysema extent. We further investigate if machine learning algorithms that learn from a scoring of emphysema extent can outperform algorithms that learn only from a scoring of emphysema presence. We compare four Multiple Instance Learning classifiers that are trained on emphysema presence labels, and five Learning with Label Proportions classifiers that are trained on emphysema extent labels. We evaluate performance on 600 low-dose CT scans from the Danish Lung Cancer Screening Trial and find that learning from emphysema presence labels, which are much easier to obtain, gives equally good performance to learning from emphysema extent labels. The best classifiers achieve intra-class correlation coefficients around 0.90 and average overall agreement with raters of 78% and 79% on six emphysema extent classes versus inter-rater agreement of 83%.
Tasks Multiple Instance Learning
Published 2018-10-17
URL http://arxiv.org/abs/1810.07433v1
PDF http://arxiv.org/pdf/1810.07433v1.pdf
PWC https://paperswithcode.com/paper/learning-to-quantify-emphysema-extent-what
Repo
Framework

Proxy Fairness

Title Proxy Fairness
Authors Maya Gupta, Andrew Cotter, Mahdi Milani Fard, Serena Wang
Abstract We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for proxy groups, and test whether doing so results in improved fairness for the true sensitive groups. Results on benchmark and real-world datasets demonstrate that such a proxy fairness strategy can work well in practice. However, we caution that the effectiveness likely depends on the choice of fairness metric, as well as how aligned the proxy groups are with the true protected groups in terms of the constrained model parameters.
Tasks
Published 2018-06-28
URL http://arxiv.org/abs/1806.11212v1
PDF http://arxiv.org/pdf/1806.11212v1.pdf
PWC https://paperswithcode.com/paper/proxy-fairness
Repo
Framework

Unifying Gaussian LWF and AMP Chain Graphs to Model Interference

Title Unifying Gaussian LWF and AMP Chain Graphs to Model Interference
Authors Jose M. Peña
Abstract An intervention may have an effect on units other than those to which it was administered. This phenomenon is called interference and it usually goes unmodeled. In this paper, we propose to combine Lauritzen-Wermuth-Frydenberg and Andersson-Madigan-Perlman chain graphs to create a new class of causal models that can represent both interference and non-interference relationships for Gaussian distributions. Specifically, we define the new class of models, introduce global and local and pairwise Markov properties for them, and prove their equivalence. We also propose an algorithm for maximum likelihood parameter estimation for the new models, and report experimental results. Finally, we show how to compute the effects of interventions in the new models.
Tasks
Published 2018-11-11
URL https://arxiv.org/abs/1811.04477v9
PDF https://arxiv.org/pdf/1811.04477v9.pdf
PWC https://paperswithcode.com/paper/unifying-gaussian-lwf-and-amp-chain-graphs-to
Repo
Framework

Nonlinear Robust Filtering of Sampled-Data Dynamical Systems

Title Nonlinear Robust Filtering of Sampled-Data Dynamical Systems
Authors Masoud Abbaszadeh, Horacio J. Marquez
Abstract This work is concerned with robust filtering of nonlinear sampled-data systems with and without exact discrete-time models. A linear matrix inequality (LMI) based approach is proposed for the design of robust $H_{\infty}$ observers for a class of Lipschitz nonlinear systems. Two type of systems are considered, Lipschitz nonlinear discrete-time systems and Lipschitz nonlinear sampled-data systems with Euler approximate discrete-time models. Observer convergence when the exact discrete-time model of the system is available is shown. Then, practical convergence of the proposed observer is proved using the Euler approximate discrete-time model. As an additional feature, maximizing the admissible Lipschitz constant, the solution of the proposed LMI optimization problem guaranties robustness against some nonlinear uncertainty. The robust H_infty observer synthesis problem is solved for both cases. The maximum disturbance attenuation level is achieved through LMI optimization. At the end, a path to extending the results to higher-order approximate discretizations is provided.
Tasks
Published 2018-12-23
URL http://arxiv.org/abs/1812.09701v1
PDF http://arxiv.org/pdf/1812.09701v1.pdf
PWC https://paperswithcode.com/paper/nonlinear-robust-filtering-of-sampled-data
Repo
Framework

Mathematical Analysis of Adversarial Attacks

Title Mathematical Analysis of Adversarial Attacks
Authors Zehao Dou, Stanley J. Osher, Bao Wang
Abstract In this paper, we analyze efficacy of the fast gradient sign method (FGSM) and the Carlini-Wagner’s L2 (CW-L2) attack. We prove that, within a certain regime, the untargeted FGSM can fool any convolutional neural nets (CNNs) with ReLU activation; the targeted FGSM can mislead any CNNs with ReLU activation to classify any given image into any prescribed class. For a special two-layer neural network: a linear layer followed by the softmax output activation, we show that the CW-L2 attack increases the ratio of the classification probability between the target and ground truth classes. Moreover, we provide numerical results to verify all our theoretical results.
Tasks
Published 2018-11-15
URL http://arxiv.org/abs/1811.06492v2
PDF http://arxiv.org/pdf/1811.06492v2.pdf
PWC https://paperswithcode.com/paper/mathematical-analysis-of-adversarial-attacks
Repo
Framework

Quantization for Rapid Deployment of Deep Neural Networks

Title Quantization for Rapid Deployment of Deep Neural Networks
Authors Jun Haeng Lee, Sangwon Ha, Saerom Choi, Won-Jo Lee, Seungwon Lee
Abstract This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to limited precision is essential in taking advantage of the accelerators with reduced memory footprint and computation power. However, such a task is not trivial since it often requires the full training and validation datasets for profiling the network statistics and fine tuning the networks to recover the accuracy lost after quantization. To address these issues, we propose a simple method recognizing channel-level distribution to reduce the quantization-induced accuracy loss and minimize the required image samples for profiling. We evaluated our method on eleven networks trained on the ImageNet classification benchmark and a network trained on the Pascal VOC object detection benchmark. The results prove that the networks can be quantized into 8-bit integer precision without fine tuning.
Tasks Object Detection, Quantization
Published 2018-10-12
URL http://arxiv.org/abs/1810.05488v1
PDF http://arxiv.org/pdf/1810.05488v1.pdf
PWC https://paperswithcode.com/paper/quantization-for-rapid-deployment-of-deep
Repo
Framework

The algorithm of formation of a training set for an artificial neural network for image segmentation

Title The algorithm of formation of a training set for an artificial neural network for image segmentation
Authors S. V. Belim, S. B. Larionov
Abstract This article suggests an algorithm of formation a training set for artificial neural network in case of image segmentation. The distinctive feature of this algorithm is that it using only one image for segmentation. The segmentation performs using three-layer perceptron. The main method of the segmentation is a method of region growing. Neural network is using for get a decision to include pixel into an area or not. Impulse noise is using for generation of a training set. Pixels damaged by noise are not related to the same region. Suggested method has been tested with help of computer experiment in automatic and interactive modes.
Tasks Semantic Segmentation
Published 2018-12-22
URL http://arxiv.org/abs/1812.09569v1
PDF http://arxiv.org/pdf/1812.09569v1.pdf
PWC https://paperswithcode.com/paper/the-algorithm-of-formation-of-a-training-set
Repo
Framework

Left Ventricle Segmentation in Cardiac MR Images Using Fully Convolutional Network

Title Left Ventricle Segmentation in Cardiac MR Images Using Fully Convolutional Network
Authors Mina Nasr-Esfahani, Majid Mohrekesh, Mojtaba Akbari, S. M. Reza Soroushmehr, Ebrahim Nasr-Esfahani, Nader Karimi, Shadrokh Samavi, Kayvan Najarian
Abstract Medical image analysis, especially segmenting a specific organ, has an important role in developing clinical decision support systems. In cardiac magnetic resonance (MR) imaging, segmenting the left and right ventricles helps physicians diagnose different heart abnormalities. There are challenges for this task, including the intensity and shape similarity between left ventricle and other organs, inaccurate boundaries and presence of noise in most of the images. In this paper we propose an automated method for segmenting the left ventricle in cardiac MR images. We first automatically extract the region of interest, and then employ it as an input of a fully convolutional network. We train the network accurately despite the small number of left ventricle pixels in comparison with the whole image. Thresholding on the output map of the fully convolutional network and selection of regions based on their roundness are performed in our proposed post-processing phase. The Dice score of our method reaches 87.24% by applying this algorithm on the York dataset of heart images.
Tasks
Published 2018-02-21
URL http://arxiv.org/abs/1802.07778v1
PDF http://arxiv.org/pdf/1802.07778v1.pdf
PWC https://paperswithcode.com/paper/left-ventricle-segmentation-in-cardiac-mr
Repo
Framework

Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation

Title Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation
Authors Andre Freitas, Siamak Barzegar, Juliano Efson Sales, Siegfried Handschuh, Brian Davis
Abstract This paper provides a comparative analysis of the performance of four state-of-the-art distributional semantic models (DSMs) over 11 languages, contrasting the native language-specific models with the use of machine translation over English-based DSMs. The experimental results show that there is a significant improvement (average of 16.7% for the Spearman correlation) by using state-of-the-art machine translation approaches. The results also show that the benefit of using the most informative corpus outweighs the possible errors introduced by the machine translation. For all languages, the combination of machine translation over the Word2Vec English distributional model provided the best results consistently (average Spearman correlation of 0.68).
Tasks Machine Translation
Published 2018-05-16
URL http://arxiv.org/abs/1805.06522v1
PDF http://arxiv.org/pdf/1805.06522v1.pdf
PWC https://paperswithcode.com/paper/semantic-relatedness-for-all-languages-a
Repo
Framework

Real-time Indoor Scene Reconstruction with RGBD and Inertia Input

Title Real-time Indoor Scene Reconstruction with RGBD and Inertia Input
Authors Zunjie Zhu, Feng Xu
Abstract Camera motion estimation is a key technique for 3D scene reconstruction and Simultaneous localization and mapping (SLAM). To make it be feasibly achieved, previous works usually assume slow camera motions, which limits its usage in many real cases. We propose an end-to-end 3D reconstruction system which combines color, depth and inertial measurements to achieve robust reconstruction with fast sensor motions. Our framework extends Kalman filter to fuse the three kinds of information and involve an iterative method to jointly optimize feature correspondences, camera poses and scene geometry. We also propose a novel geometry-aware patch deformation technique to adapt the feature appearance in image domain, leading to a more accurate feature matching under fast camera motions. Experiments show that our patch deformation method improves the accuracy of feature tracking, and our 3D reconstruction outperforms the state-of-the-art solutions under fast camera motions.
Tasks 3D Reconstruction, 3D Scene Reconstruction, Indoor Scene Reconstruction, Motion Estimation, Simultaneous Localization and Mapping
Published 2018-12-07
URL http://arxiv.org/abs/1812.03015v1
PDF http://arxiv.org/pdf/1812.03015v1.pdf
PWC https://paperswithcode.com/paper/real-time-indoor-scene-reconstruction-with
Repo
Framework

Quantum-chemical insights from interpretable atomistic neural networks

Title Quantum-chemical insights from interpretable atomistic neural networks
Authors Kristof T. Schütt, Michael Gastegger, Alexandre Tkatchenko, Klaus-Robert Müller
Abstract With the rise of deep neural networks for quantum chemistry applications, there is a pressing need for architectures that, beyond delivering accurate predictions of chemical properties, are readily interpretable by researchers. Here, we describe interpretation techniques for atomistic neural networks on the example of Behler-Parrinello networks as well as the end-to-end model SchNet. Both models obtain predictions of chemical properties by aggregating atom-wise contributions. These latent variables can serve as local explanations of a prediction and are obtained during training without additional cost. Due to their correspondence to well-known chemical concepts such as atomic energies and partial charges, these atom-wise explanations enable insights not only about the model but more importantly about the underlying quantum-chemical regularities. We generalize from atomistic explanations to 3d space, thus obtaining spatially resolved visualizations which further improve interpretability. Finally, we analyze learned embeddings of chemical elements that exhibit a partial ordering that resembles the order of the periodic table. As the examined neural networks show excellent agreement with chemical knowledge, the presented techniques open up new venues for data-driven research in chemistry, physics and materials science.
Tasks
Published 2018-06-27
URL http://arxiv.org/abs/1806.10349v1
PDF http://arxiv.org/pdf/1806.10349v1.pdf
PWC https://paperswithcode.com/paper/quantum-chemical-insights-from-interpretable
Repo
Framework

CNN based dense underwater 3D scene reconstruction by transfer learning using bubble database

Title CNN based dense underwater 3D scene reconstruction by transfer learning using bubble database
Authors Kazuto Ichimaru, Ryo Furukawa, Hiroshi Kawasaki
Abstract Dense 3D shape acquisition of swimming human or live fish is an important research topic for sports, biological science and so on. For this purpose, active stereo sensor is usually used in the air, however it cannot be applied to the underwater environment because of refraction, strong light attenuation and severe interference of bubbles. Passive stereo is a simple solution for capturing dynamic scenes at underwater environment, however the shape with textureless surfaces or irregular reflections cannot be recovered. Recently, the stereo camera pair with a pattern projector for adding artificial textures on the objects is proposed. However, to use the system for underwater environment, several problems should be compensated, i.e., disturbance by fluctuation and bubbles. Simple solution is to use convolutional neural network for stereo to cancel the effects of bubbles and/or water fluctuation. Since it is not easy to train CNN with small size of database with large variation, we develop a special bubble generation device to efficiently create real bubble database of multiple size and density. In addition, we propose a transfer learning technique for multi-scale CNN to effectively remove bubbles and projected-patterns on the object. Further, we develop a real system and actually captured live swimming human, which has not been done before. Experiments are conducted to show the effectiveness of our method compared with the state of the art techniques.
Tasks 3D Scene Reconstruction, Transfer Learning, Underwater 3D Scene Reconstruction
Published 2018-11-21
URL http://arxiv.org/abs/1811.09675v1
PDF http://arxiv.org/pdf/1811.09675v1.pdf
PWC https://paperswithcode.com/paper/cnn-based-dense-underwater-3d-scene
Repo
Framework

Minimizing Regret in Bandit Online Optimization in Unconstrained and Constrained Action Spaces

Title Minimizing Regret in Bandit Online Optimization in Unconstrained and Constrained Action Spaces
Authors Tatiana Tatarenko, Maryam Kamgarpour
Abstract We consider online convex optimization with a zero-order oracle feedback. In particular, the decision maker does not know the explicit representation of the time-varying cost functions, or their gradients. At each time step, she observes the value of the cost function evaluated at her chosen action. The objective is to minimize the regret, that is, the difference between the sum of the costs she accumulates and that of the static optimal action had she known the sequence of cost functions a priori. We present a novel algorithm to minimize the regret in both unconstrained and constrained action spaces. Our algorithm hinges on a classical idea of one-point estimation of the gradients of the cost functions based on their observed values. However, our choice of the randomization introduced and consequently the proof techniques differ from those of past work. Letting T denote the number of queries of the zero-order oracle and n the problem dimension, the regret rate achieved is O(nT^{2/3}) for both constrained and unconstrained action spaces. Moreover, we adapt the presented algorithm to the setting with two-point feedback and demonstrate that the adapted procedure achieves the theoretical lower bound on the regret.
Tasks
Published 2018-06-13
URL http://arxiv.org/abs/1806.05069v2
PDF http://arxiv.org/pdf/1806.05069v2.pdf
PWC https://paperswithcode.com/paper/minimizing-regret-in-bandit-online
Repo
Framework

Consistent Generative Query Networks

Title Consistent Generative Query Networks
Authors Ananya Kumar, S. M. Ali Eslami, Danilo J. Rezende, Marta Garnelo, Fabio Viola, Edward Lockhart, Murray Shanahan
Abstract Stochastic video prediction models take in a sequence of image frames, and generate a sequence of consecutive future image frames. These models typically generate future frames in an autoregressive fashion, which is slow and requires the input and output frames to be consecutive. We introduce a model that overcomes these drawbacks by generating a latent representation from an arbitrary set of frames that can then be used to simultaneously and efficiently sample temporally consistent frames at arbitrary time-points. For example, our model can “jump” and directly sample frames at the end of the video, without sampling intermediate frames. Synthetic video evaluations confirm substantial gains in speed and functionality without loss in fidelity. We also apply our framework to a 3D scene reconstruction dataset. Here, our model is conditioned on camera location and can sample consistent sets of images for what an occluded region of a 3D scene might look like, even if there are multiple possibilities for what that region might contain. Reconstructions and videos are available at https://bit.ly/2O4Pc4R.
Tasks 3D Scene Reconstruction, Video Prediction
Published 2018-07-05
URL http://arxiv.org/abs/1807.02033v3
PDF http://arxiv.org/pdf/1807.02033v3.pdf
PWC https://paperswithcode.com/paper/consistent-jumpy-predictions-for-videos-and
Repo
Framework

Robot_gym: accelerated robot training through simulation in the cloud with ROS and Gazebo

Title Robot_gym: accelerated robot training through simulation in the cloud with ROS and Gazebo
Authors Víctor Mayoral Vilches, Alejandro Hernández Cordero, Asier Bilbao Calvo, Irati Zamalloa Ugarte, Risto Kojcev
Abstract Rather than programming, training allows robots to achieve behaviors that generalize better and are capable to respond to real-world needs. However, such training requires a big amount of experimentation which is not always feasible for a physical robot. In this work, we present robot_gym, a framework to accelerate robot training through simulation in the cloud that makes use of roboticists’ tools, simplifying the development and deployment processes on real robots. We unveil that, for simple tasks, simple 3DoF robots require more than 140 attempts to learn. For more complex, 6DoF robots, the number of attempts increases to more than 900 for the same task. We demonstrate that our framework, for simple tasks, accelerates the robot training time by more than 33% while maintaining similar levels of accuracy and repeatability.
Tasks
Published 2018-08-30
URL http://arxiv.org/abs/1808.10369v1
PDF http://arxiv.org/pdf/1808.10369v1.pdf
PWC https://paperswithcode.com/paper/robot_gym-accelerated-robot-training-through
Repo
Framework
comments powered by Disqus