October 17, 2019

2684 words 13 mins read

Paper Group ANR 845

Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT. Antifragility for Intelligent Autonomous Systems. Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations. Non-Oscillatory Pattern Learning for Non-Stationary Signals. Improving Face Detection Performance with 3D-Rendered Synthetic Data. …

Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT


Title	Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT
Authors	Julia M. H. Noothout, Bob D. de Vos, Jelmer M. Wolterink, Ivana Isgum
Abstract	Morphological analysis and identification of pathologies in the aorta are important for cardiovascular diagnosis and risk assessment in patients. Manual annotation is time-consuming and cumbersome in CT scans acquired without contrast enhancement and with low radiation dose. Hence, we propose an automatic method to segment the ascending aorta, the aortic arch and the thoracic descending aorta in low-dose chest CT without contrast enhancement. Segmentation was performed using a dilated convolutional neural network (CNN), with a receptive field of 131X131 voxels, that classified voxels in axial, coronal and sagittal image slices. To obtain a final segmentation, the obtained probabilities of the three planes were averaged per class, and voxels were subsequently assigned to the class with the highest class probability. Two-fold cross-validation experiments were performed where ten scans were used to train the network and another ten to evaluate the performance. Dice coefficients of 0.83, 0.86 and 0.88, and Average Symmetrical Surface Distances (ASSDs) of 2.44, 1.56 and 1.87 mm were obtained for the ascending aorta, the aortic arch, and the descending aorta, respectively. The results indicate that the proposed method could be used in large-scale studies analyzing the anatomical location of pathology and morphology of the thoracic aorta.
Tasks	Morphological Analysis
Published	2018-10-09
URL	http://arxiv.org/abs/1810.05727v1
PDF	http://arxiv.org/pdf/1810.05727v1.pdf
PWC	https://paperswithcode.com/paper/automatic-segmentation-of-thoracic-aorta
Repo
Framework

Antifragility for Intelligent Autonomous Systems


Title	Antifragility for Intelligent Autonomous Systems
Authors	Anusha Mujumdar, Swarup Kumar Mohalik, Ramamurthy Badrinath
Abstract	Antifragile systems grow measurably better in the presence of hazards. This is in contrast to fragile systems which break down in the presence of hazards, robust systems that tolerate hazards up to a certain degree, and resilient systems that – like self-healing systems – revert to their earlier expected behavior after a period of convalescence. The notion of antifragility was introduced by Taleb for economics systems, but its applicability has been illustrated in biological and engineering domains as well. In this paper, we propose an architecture that imparts antifragility to intelligent autonomous systems, specifically those that are goal-driven and based on AI-planning. We argue that this architecture allows the system to self-improve by uncovering new capabilities obtained either through the hazards themselves (opportunistic) or through deliberation (strategic). An AI planning-based case study of an autonomous wheeled robot is presented. We show that with the proposed architecture, the robot develops antifragile behaviour with respect to an oil spill hazard.
Tasks
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09159v1
PDF	http://arxiv.org/pdf/1802.09159v1.pdf
PWC	https://paperswithcode.com/paper/antifragility-for-intelligent-autonomous
Repo
Framework

Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations


Title	Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations
Authors	Hiroki Shimanaka, Tomoyuki Kajiwara, Mamoru Komachi
Abstract	Sentence representations can capture a wide range of information that cannot be captured by local features based on character or word N-grams. This paper examines the usefulness of universal sentence representations for evaluating the quality of machine translation. Although it is difficult to train sentence representations using small-scale translation datasets with manual evaluation, sentence representations trained from large-scale data in other tasks can improve the automatic evaluation of machine translation. Experimental results of the WMT-2016 dataset show that the proposed method achieves state-of-the-art performance with sentence representation features only.
Tasks	Machine Translation
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07469v1
PDF	http://arxiv.org/pdf/1805.07469v1.pdf
PWC	https://paperswithcode.com/paper/metric-for-automatic-machine-translation
Repo
Framework

Non-Oscillatory Pattern Learning for Non-Stationary Signals


Title	Non-Oscillatory Pattern Learning for Non-Stationary Signals
Authors	Jieren Xu, Yitong Li, David Dunson, Ingrid Daubechies, Haizhao Yang
Abstract	This paper proposes a novel non-oscillatory pattern (NOP) learning scheme for several oscillatory data analysis problems including signal decomposition, super-resolution, and signal sub-sampling. To the best of our knowledge, the proposed NOP is the first algorithm for these problems with fully non-stationary oscillatory data with close and crossover frequencies, and general oscillatory patterns. NOP is capable of handling complicated situations while existing algorithms fail; even in simple cases, e.g., stationary cases with trigonometric patterns, numerical examples show that NOP admits competitive or better performance in terms of accuracy and robustness than several state-of-the-art algorithms.
Tasks	Super-Resolution
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08102v2
PDF	http://arxiv.org/pdf/1805.08102v2.pdf
PWC	https://paperswithcode.com/paper/non-oscillatory-pattern-learning-for-non
Repo
Framework

Improving Face Detection Performance with 3D-Rendered Synthetic Data


Title	Improving Face Detection Performance with 3D-Rendered Synthetic Data
Authors	Jian Han, Sezer Karaoglu, Hoang-An Le, Theo Gevers
Abstract	In this paper, we provide a synthetic data generator methodology with fully controlled, multifaceted variations based on a new 3D face dataset (3DU-Face). We customized synthetic datasets to address specific types of variations (scale, pose, occlusion, blur, etc.), and systematically investigate the influence of different variations on face detection performances. We examine whether and how these factors contribute to better face detection performances. We validate our synthetic data augmentation for different face detectors (Faster RCNN, SSH and HR) on various face datasets (MAFA, UFDD and Wider Face).
Tasks	Data Augmentation, Face Detection
Published	2018-12-18
URL	https://arxiv.org/abs/1812.07363v3
PDF	https://arxiv.org/pdf/1812.07363v3.pdf
PWC	https://paperswithcode.com/paper/improving-face-detection-performance-with-3d
Repo
Framework

Neural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced from Comparable Corpora


Title	Neural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced from Comparable Corpora
Authors	Sree Harsha Ramesh, Krishna Prasad Sankaranarayanan
Abstract	Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In this paper, we have used an end-to-end Siamese bidirectional recurrent neural network to generate parallel sentences from comparable multilingual articles in Wikipedia. Subsequently, we have showed that using the harvested dataset improved BLEU scores on both NMT and phrase-based SMT systems for the low-resource language pairs: English–Hindi and English–Tamil, when compared to training exclusively on the limited bilingual corpora collected for these language pairs.
Tasks	Machine Translation
Published	2018-06-25
URL	http://arxiv.org/abs/1806.09652v1
PDF	http://arxiv.org/pdf/1806.09652v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-for-low-resource
Repo
Framework

Finding Options that Minimize Planning Time


Title	Finding Options that Minimize Planning Time
Authors	Yuu Jinnai, David Abel, D Ellis Hershkowitz, Michael Littman, George Konidaris
Abstract	We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes. We first show that the problem is NP-hard, even if the task is constrained to be deterministic—the first such complexity result for option discovery. We then present the first polynomial-time boundedly suboptimal approximation algorithm for this setting, and empirically evaluate it against both the optimal options and a representative collection of heuristic approaches in simple grid-based domains including the classic four-rooms problem.
Tasks
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07311v3
PDF	http://arxiv.org/pdf/1810.07311v3.pdf
PWC	https://paperswithcode.com/paper/finding-options-that-minimize-planning-time
Repo
Framework

Modeling Spatiotemporal Factors Associated With Sentiment on Twitter: Synthesis and Suggestions for Improving the Identification of Localized Deviations


Title	Modeling Spatiotemporal Factors Associated With Sentiment on Twitter: Synthesis and Suggestions for Improving the Identification of Localized Deviations
Authors	Zubair Shah, Paige Martin, Enrico Coiera, Kenneth D. Mandl, Adam G. Dunn
Abstract	Background: Studies examining how sentiment on social media varies depending on timing and location appear to produce inconsistent results, making it hard to design systems that use sentiment to detect localized events for public health applications. Objective: The aim of this study was to measure how common timing and location confounders explain variation in sentiment on Twitter. Methods: Using a dataset of 16.54 million English-language tweets from 100 cities posted between July 13 and November 30, 2017, we estimated the positive and negative sentiment for each of the cities using a dictionary-based sentiment analysis and constructed models to explain the differences in sentiment using time of day, day of week, weather, city, and interaction type (conversations or broadcasting) as factors and found that all factors were independently associated with sentiment. Results: In the full multivariable model of positive (Pearson r in test data 0.236; 95% CI 0.231-0.241) and negative (Pearson r in test data 0.306; 95% CI 0.301-0.310) sentiment, the city and time of day explained more of the variance than weather and day of week. Models that account for these confounders produce a different distribution and ranking of important events compared with models that do not account for these confounders. Conclusions: In public health applications that aim to detect localized events by aggregating sentiment across populations of Twitter users, it is worthwhile accounting for baseline differences before looking for unexpected changes.
Tasks	Sentiment Analysis
Published	2018-02-22
URL	https://arxiv.org/abs/1802.07859v2
PDF	https://arxiv.org/pdf/1802.07859v2.pdf
PWC	https://paperswithcode.com/paper/modelling-spatiotemporal-variation-of
Repo
Framework

Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics


Title	Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics
Authors	Ajinkya Jain, Scott Niekum
Abstract	Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot motion planning. By decomposing nonlinear dynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden discontinuities in dynamics due to factors such as contacts. We propose a hierarchical POMDP planner that develops cost-optimized motion plans for hybrid dynamics models. The hierarchical planner first develops a high-level motion plan to sequence the local dynamics models to be visited and then converts it into a detailed continuous state plan. This hierarchical planning approach results in a decomposition of the POMDP planning problem into smaller sub-parts that can be solved with significantly lower computational costs. The ability to sequence the visitation of local dynamics models also provides a powerful way to leverage the hybrid dynamics to reduce state uncertainty. We evaluate the proposed planner on a navigation task in the simulated domain and on an assembly task with a robotic manipulator, showing that our approach can solve tasks having high observation noise and nonlinear dynamics effectively with significantly lower computational costs compared to direct planning approaches.
Tasks	Motion Planning
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04205v4
PDF	http://arxiv.org/pdf/1802.04205v4.pdf
PWC	https://paperswithcode.com/paper/efficient-hierarchical-robot-motion-planning
Repo
Framework

Proactive Intervention to Downtrend Employee Attrition using Artificial Intelligence Techniques


Title	Proactive Intervention to Downtrend Employee Attrition using Artificial Intelligence Techniques
Authors	Aasheesh Barvey, Jitin Kapila, Kumarjit Pathak
Abstract	To predict the employee attrition beforehand and to enable management to take individualized preventive action. Using Ensemble classification modeling techniques and Linear Regression. Model could predict over 91% accurate employee prediction, lead-time in separation and individual reasons causing attrition. Prior intimation of employee attrition enables manager to take preventive actions to retain employee or to manage the business consequences of attrition. Once deployed this will model can help in downtrend Employee Attrition, will help manager to manage team more effectively. Model does not cover the natural calamities, and unforeseen events occurring at an individual level like accident, death etc.
Tasks
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04081v1
PDF	http://arxiv.org/pdf/1807.04081v1.pdf
PWC	https://paperswithcode.com/paper/proactive-intervention-to-downtrend-employee
Repo
Framework

LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization


Title	LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization
Authors	Marcin Dymczyk, Igor Gilitschenski, Juan Nieto, Simon Lynen, Bernhard Zeisl, Roland Siegwart
Abstract	The growing popularity of autonomous systems creates a need for reliable and efficient metric pose retrieval algorithms. Currently used approaches tend to rely on nearest neighbor search of binary descriptors to perform the 2D-3D matching and guarantee realtime capabilities on mobile platforms. These methods struggle, however, with the growing size of the map, changes in viewpoint or appearance, and visual aliasing present in the environment. The rigidly defined descriptor patterns only capture a limited neighborhood of the keypoint and completely ignore the overall visual context. We propose LandmarkBoost - an approach that, in contrast to the conventional 2D-3D matching methods, casts the search problem as a landmark classification task. We use a boosted classifier to classify landmark observations and directly obtain correspondences as classifier scores. We also introduce a formulation of visual context that is flexible, efficient to compute, and can capture relationships in the entire image plane. The original binary descriptors are augmented with contextual information and informative features are selected by the boosting framework. Through detailed experiments, we evaluate the retrieval quality and performance of LandmarkBoost, demonstrating that it outperforms common state-of-the-art descriptor matching methods.
Tasks
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04702v2
PDF	http://arxiv.org/pdf/1807.04702v2.pdf
PWC	https://paperswithcode.com/paper/landmarkboost-efficient-visual-context
Repo
Framework

Distributed learning with compressed gradients


Title	Distributed learning with compressed gradients
Authors	Sarit Khirirat, Hamid Reza Feyzmahdavian, Mikael Johansson
Abstract	Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This paper presents a unified analysis framework for distributed gradient methods operating with staled and compressed gradients. Non-asymptotic bounds on convergence rates and information exchange are derived for several optimization algorithms. These bounds give explicit expressions for step-sizes and characterize how the amount of asynchrony and the compression accuracy affect iteration and communication complexity guarantees. Numerical results highlight convergence properties of different gradient compression algorithms and confirm that fast convergence under limited information exchange is indeed possible.
Tasks	Distributed Optimization
Published	2018-06-18
URL	http://arxiv.org/abs/1806.06573v2
PDF	http://arxiv.org/pdf/1806.06573v2.pdf
PWC	https://paperswithcode.com/paper/distributed-learning-with-compressed
Repo
Framework

Label Noise Filtering Techniques to Improve Monotonic Classification


Title	Label Noise Filtering Techniques to Improve Monotonic Classification
Authors	José-Ramón Cano, Julián Luengo, Salvador García
Abstract	The monotonic ordinal classification has increased the interest of researchers and practitioners within machine learning community in the last years. In real applications, the problems with monotonicity constraints are very frequent. To construct predictive monotone models from those problems, many classifiers require as input a data set satisfying the monotonicity relationships among all samples. Changing the class labels of the data set (relabelling) is useful for this. Relabelling is assumed to be an important building block for the construction of monotone classifiers and it is proved that it can improve the predictive performance. In this paper, we will address the construction of monotone datasets considering as noise the cases that do not meet the monotonicity restrictions. For the first time in the specialized literature, we propose the use of noise filtering algorithms in a preprocessing stage with a double goal: to increase both the monotonicity index of the models and the accuracy of the predictions for different monotonic classifiers. The experiments are performed over 12 datasets coming from classification and regression problems and show that our scheme improves the prediction capabilities of the monotonic classifiers instead of being applied to original and relabeled datasets. In addition, we have included the analysis of noise filtering process in the particular case of wine quality classification to understand its effect in the predictive models generated.
Tasks
Published	2018-10-21
URL	http://arxiv.org/abs/1810.08914v1
PDF	http://arxiv.org/pdf/1810.08914v1.pdf
PWC	https://paperswithcode.com/paper/label-noise-filtering-techniques-to-improve
Repo
Framework

Training on Art Composition Attributes to Influence CycleGAN Art Generation


Title	Training on Art Composition Attributes to Influence CycleGAN Art Generation
Authors	Holly Grimm
Abstract	I consider how to influence CycleGAN, image-to-image translation, by using additional constraints from a neural network trained on art composition attributes. I show how I trained the the Art Composition Attributes Network (ACAN) by incorporating domain knowledge based on the rules of art evaluation and the result of applying each art composition attribute to apple2orange image translation.
Tasks	Image-to-Image Translation
Published	2018-12-19
URL	http://arxiv.org/abs/1812.07710v1
PDF	http://arxiv.org/pdf/1812.07710v1.pdf
PWC	https://paperswithcode.com/paper/training-on-art-composition-attributes-to
Repo
Framework

Local Conditioning: Exact Message Passing for Cyclic Undirected Distributed Networks


Title	Local Conditioning: Exact Message Passing for Cyclic Undirected Distributed Networks
Authors	Matthew G. Reyes
Abstract	This paper addresses practical implementation of summing out, expanding, and reordering of messages in Local Conditioning (LC) for undirected networks. In particular, incoming messages conditioned on potentially different subsets of the receiving node’s relevant set must be expanded to be conditioned on this relevant set, then reordered so that corresponding columns of the conditioned matrices can be fused through element-wise multiplication. An outgoing message is then reduced by summing out loop cutset nodes that are upstream of the outgoing edge. The emphasis on implementation is the primary contribution over the theoretical justification of LC given in Fay et al. Nevertheless, the complexity of Local Conditioning in grid networks is still no better than that of Clustering.
Tasks
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02641v1
PDF	http://arxiv.org/pdf/1812.02641v1.pdf
PWC	https://paperswithcode.com/paper/local-conditioning-exact-message-passing-for
Repo
Framework