January 30, 2020

3218 words 16 mins read

Paper Group ANR 458

Using Videos to Evaluate Image Model Robustness. Sub-pixel matching method for low-resolution thermal stereo images. Neural Architecture based on Fuzzy Perceptual Representation For Online Multilingual Handwriting Recognition. A Collaborative Framework for High-Definition Mapping. Separating Argument Structure from Logical Structure in AMR. Taking …

Using Videos to Evaluate Image Model Robustness


Title	Using Videos to Evaluate Image Model Robustness
Authors	Keren Gu, Brandon Yang, Jiquan Ngiam, Quoc Le, Jonathon Shlens
Abstract	Human visual systems are robust to a wide range of image transformations that are challenging for artificial networks. We present the first study of image model robustness to the minute transformations found across video frames, which we term “natural robustness”. Compared to previous studies on adversarial examples and synthetic distortions, natural robustness captures a more diverse set of common image transformations that occur in the natural environment. Our study across a dozen model architectures shows that more accurate models are more robust to natural transformations, and that robustness to synthetic color distortions is a good proxy for natural robustness. In examining brittleness in videos, we find that majority of the brittleness found in videos lies outside the typical definition of adversarial examples (99.9%). Finally, we investigate training techniques to reduce brittleness and find that no single technique systematically improves natural robustness across twelve tested architectures.
Tasks
Published	2019-04-22
URL	https://arxiv.org/abs/1904.10076v3
PDF	https://arxiv.org/pdf/1904.10076v3.pdf
PWC	https://paperswithcode.com/paper/using-videos-to-evaluate-image-model
Repo
Framework

Sub-pixel matching method for low-resolution thermal stereo images


Title	Sub-pixel matching method for low-resolution thermal stereo images
Authors	Yannick Wend Kuni Zoetgnande, Geoffroy Cormier, Alain-Jérôme Fougères, Jean-Louis Dillenseger
Abstract	In the context of a localization and tracking application, we developed a stereo vision system based on cheap low-resolution 80x60 pixels thermal cameras. We proposed a threefold sub-pixel stereo matching framework (called ST for Subpixel Thermal): 1) robust features extraction method based on phase congruency, 2) rough matching of these features in pixel precision, and 3) refined matching in sub-pixel accuracy based on local phase coherence. We performed experiments on our very low-resolution thermal images (acquired using a stereo system we manufactured) as for high-resolution images from a benchmark dataset. Even if phase congruency computation time is high, it was able to extract two times more features than state-of-the-art methods such as ORB or SURF. We proposed a modified version of the phase correlation applied in the phase congruency feature space for sub-pixel matching. Using simulated stereo, we investigated how the phase congruency threshold and the sub-image size of sub-pixel matching can influence the accuracy. We then proved that given our stereo setup and the resolution of our images, being wrong of 1 pixel leads to a 500 mm error in the Z position of the point. Finally, we showed that our method could extract four times more matches than a baseline method ORB + OpenCV KNN matching on low-resolution images. Moreover, our matches were more robust. More precisely, when projecting points of a standing person, ST got a standard deviation of 300 mm when ORB + OpenCV KNN gave more than 1000 mm.
Tasks	Stereo Matching
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00138v1
PDF	https://arxiv.org/pdf/1912.00138v1.pdf
PWC	https://paperswithcode.com/paper/sub-pixel-matching-method-for-low-resolution
Repo
Framework

Neural Architecture based on Fuzzy Perceptual Representation For Online Multilingual Handwriting Recognition


Title	Neural Architecture based on Fuzzy Perceptual Representation For Online Multilingual Handwriting Recognition
Authors	Hanen Akouaydi, Sourour Njah, Wael Ouarda, Anis Samet, Thameur Dhieb, Mourad Zaied, Adel M. Alimi
Abstract	Due to the omnipresence of mobile devices, online handwritten scripts have become the most important feeding input to smartphones and tablet devices. To increase online handwriting recognition performance, deeper neural networks have extensively been used. In this context, our paper handles the problem of online handwritten script recognition based on extraction features system and deep approach system for sequences classification. Many solutions have appeared in order to facilitate the recognition of handwriting. Accordingly, we used an existent method and combined with new classifiers in order to get a flexible system. Good results are achieved compared to online characters and words recognition system on Latin and Arabic scripts. The performance of our two proposed systems is assessed by using five databases. Indeed, the recognition rate exceeds 98%.
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00634v1
PDF	https://arxiv.org/pdf/1908.00634v1.pdf
PWC	https://paperswithcode.com/paper/neural-architecture-based-on-fuzzy-perceptual
Repo
Framework

A Collaborative Framework for High-Definition Mapping


Title	A Collaborative Framework for High-Definition Mapping
Authors	Alexis Stoven-Dubois, Kuntima Kiala Miguel, Aziz Dziri, Bertrand Leroy, Roland Chapuis
Abstract	For connected vehicles to have a substantial effect on road safety, it is required that accurate positions and trajectories can be shared. To this end, all vehicles must be accurately geo-localized in a common frame. This can be achieved by merging GNSS (Global Navigation Satellite System) information and visual observations matched with a map of geo-positioned landmarks. Building such a map remains a challenge, and current solutions are facing strong cost-related limitations. We present a collaborative framework for high-definition mapping, in which vehicles equipped with standard sensors, such as a GNSS receiver and a mono-visual camera, update a map of geo-localized landmarks. Our system is composed of two processing blocks: the first one is embedded in each vehicle, and aims at geo-localizing the vehicle and the detected feature marks. The second is operated on cloud servers, and uses observations from all the vehicles to compute updates for the map of geo-positioned landmarks. As the map’s landmarks are detected and positioned by more and more vehicles, the accuracy of the map increases, eventually converging in probability towards a null error. The landmarks’ geo-positions are estimated in a stable and scalable way, enabling to provide dynamic map updates in an automatic manner.
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06014v1
PDF	https://arxiv.org/pdf/1910.06014v1.pdf
PWC	https://paperswithcode.com/paper/a-collaborative-framework-for-high-definition
Repo
Framework

Separating Argument Structure from Logical Structure in AMR


Title	Separating Argument Structure from Logical Structure in AMR
Authors	Johan Bos
Abstract	The AMR (Abstract Meaning Representation) formalism for representing meaning of natural language sentences was not designed to deal with scope and quantifiers. By extending AMR with indices for contexts and formulating constraints on these contexts, a formalism is derived that makes correct prediction for inferences involving negation and bound variables. The attractive core predicate-argument structure of AMR is preserved. The resulting framework is similar to that of Discourse Representation Theory.
Tasks
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01355v1
PDF	https://arxiv.org/pdf/1908.01355v1.pdf
PWC	https://paperswithcode.com/paper/separating-argument-structure-from-logical
Repo
Framework

Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection


Title	Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection
Authors	Chris Dulhanty, Jason L. Deglint, Ibrahim Ben Daya, Alexander Wong
Abstract	The exponential rise of social media and digital news in the past decade has had the unfortunate consequence of escalating what the United Nations has called a global topic of concern: the growing prevalence of disinformation. Given the complexity and time-consuming nature of combating disinformation through human assessment, one is motivated to explore harnessing AI solutions to automatically assess news articles for the presence of disinformation. A valuable first step towards automatic identification of disinformation is stance detection, where given a claim and a news article, the aim is to predict if the article agrees, disagrees, takes no position, or is unrelated to the claim. Existing approaches in literature have largely relied on hand-engineered features or shallow learned representations (e.g., word embeddings) to encode the claim-article pairs, which can limit the level of representational expressiveness needed to tackle the high complexity of disinformation identification. In this work, we explore the notion of harnessing large-scale deep bidirectional transformer language models for encoding claim-article pairs in an effort to construct state-of-the-art stance detection geared for identifying disinformation. Taking advantage of bidirectional cross-attention between claim-article pairs via pair encoding with self-attention, we construct a large-scale language model for stance detection by performing transfer learning on a RoBERTa deep bidirectional transformer language model, and were able to achieve state-of-the-art performance (weighted accuracy of 90.01%) on the Fake News Challenge Stage 1 (FNC-I) benchmark. These promising results serve as motivation for harnessing such large-scale language models as powerful building blocks for creating effective AI solutions to combat disinformation.
Tasks	Language Modelling, Stance Detection, Transfer Learning, Word Embeddings
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11951v1
PDF	https://arxiv.org/pdf/1911.11951v1.pdf
PWC	https://paperswithcode.com/paper/taking-a-stance-on-fake-news-towards
Repo
Framework

Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter


Title	Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter
Authors	Wenshuo Guo, Nhat Ho, Michael I. Jordan
Abstract	We provide theoretical complexity analysis for new algorithms to compute the optimal transport (OT) distance between two discrete probability distributions, and demonstrate their favorable practical performance over state-of-art primal-dual algorithms and their capability in solving other problems in large-scale, such as the Wasserstein barycenter problem for multiple probability distributions. First, we introduce the \emph{accelerated primal-dual randomized coordinate descent} (APDRCD) algorithm for computing the OT distance. We provide its complexity upper bound $\bigOtil(\frac{n^{5/2}}{\varepsilon})$ where $n$ stands for the number of atoms of these probability measures and $\varepsilon > 0$ is the desired accuracy. This complexity bound matches the best known complexities of primal-dual algorithms for the OT problems, including the adaptive primal-dual accelerated gradient descent (APDAGD) and the adaptive primal-dual accelerated mirror descent (APDAMD) algorithms. Then, we demonstrate the better performance of the APDRCD algorithm over the APDAGD and APDAMD algorithms through extensive experimental studies, and further improve its practical performance by proposing a greedy version of it, which we refer to as \emph{accelerated primal-dual greedy coordinate descent} (APDGCD). Finally, we generalize the APDRCD and APDGCD algorithms to distributed algorithms for computing the Wasserstein barycenter for multiple probability distributions.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09952v3
PDF	https://arxiv.org/pdf/1905.09952v3.pdf
PWC	https://paperswithcode.com/paper/accelerated-primal-dual-coordinate-descent
Repo
Framework

Deep Ritz revisited


Title	Deep Ritz revisited
Authors	Johannes Müller, Marius Zeinhofer
Abstract	Recently, progress has been made in the application of neural networks to the numerical analysis of partial differential equations (PDEs). In the latter the variational formulation of the Poisson problem is used in order to obtain an objective function - a regularised Dirichlet energy - that was used for the optimisation of some neural networks. In this notes we use the notion of $\Gamma$-convergence to show that ReLU networks of growing architecture that are trained with respect to suitably regularised Dirichlet energies converge to the true solution of the Poisson problem. We discuss how this approach generalises to arbitrary variational problems under certain universality assumptions of neural networks and see that this covers some nonlinear stationary PDEs like the $p$-Laplace.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03937v2
PDF	https://arxiv.org/pdf/1912.03937v2.pdf
PWC	https://paperswithcode.com/paper/deep-ritz-revisited
Repo
Framework

Data augmentation approaches for improving animal audio classification


Title	Data augmentation approaches for improving animal audio classification
Authors	Loris Nanni, Gianluca Maguolo, Michelangelo Paci
Abstract	In this paper we present ensembles of classifiers for automated animal audio classification, exploiting different data augmentation techniques for training Convolutional Neural Networks (CNNs). The specific animal audio classification problems are i) birds and ii) cat sounds, whose datasets are freely available. We train five different CNNs on the original datasets and on their versions augmented by four augmentation protocols, working on the raw audio signals or their representations as spectrograms. We compared our best approaches with the state of the art, showing that we obtain the best recognition rate on the same datasets, without ad hoc parameter optimization. Our study shows that different CNNs can be trained for the purpose of animal audio classification and that their fusion works better than the stand-alone classifiers. To the best of our knowledge this is the largest study on data augmentation for CNNs in animal audio classification audio datasets using the same set of classifiers and parameters. Our MATLAB code is available at https://github.com/LorisNanni.
Tasks	Audio Classification, Data Augmentation
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07756v2
PDF	https://arxiv.org/pdf/1912.07756v2.pdf
PWC	https://paperswithcode.com/paper/data-augmentation-approaches-for-improving
Repo
Framework

Adversarially Robust Learning Could Leverage Computational Hardness


Title	Adversarially Robust Learning Could Leverage Computational Hardness
Authors	Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody
Abstract	Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test instances. However, the line of work in provable robustness, so far, has been focused on information-theoretic robustness, ruling out even the existence of any adversarial examples. In this work, we study whether there is a hope to benefit from algorithmic nature of an attacker that searches for adversarial examples, and ask whether there is any learning task for which it is possible to design classifiers that are only robust against polynomial-time adversaries. Indeed, numerous cryptographic tasks can only be secure against computationally bounded adversaries, and are indeed impossible for computationally unbounded attackers. Thus, it is natural to ask if the same strategy could help robust learning. We show that computational limitation of attackers can indeed be useful in robust learning by demonstrating the possibility of a classifier for some learning task for which computational and information theoretic adversaries of bounded perturbations have very different power. Namely, while computationally unbounded adversaries can attack successfully and find adversarial examples with small perturbation, polynomial time adversaries are unable to do so unless they can break standard cryptographic hardness assumptions. Our results, therefore, indicate that perhaps a similar approach to cryptography (relying on computational hardness) holds promise for achieving computationally robust machine learning. On the reverse directions, we also show that the existence of such learning task in which computational robustness beats information theoretic robustness requires computational hardness by implying (average-case) hardness of NP.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11564v2
PDF	https://arxiv.org/pdf/1905.11564v2.pdf
PWC	https://paperswithcode.com/paper/adversarially-robust-learning-could-leverage
Repo
Framework

Architecture and evolution of semantic networks in mathematics texts


Title	Architecture and evolution of semantic networks in mathematics texts
Authors	Nicolas H. Christianson, Ann Sizemore Blevins, Danielle S. Bassett
Abstract	Knowledge is a network of interconnected concepts. Yet, precisely how the topological structure of knowledge constrains its acquisition remains unknown, hampering the development of learning enhancement strategies. Here we study the topological structure of semantic networks reflecting mathematical concepts and their relations in college-level linear algebra texts. We hypothesize that these networks will exhibit structural order, reflecting the logical sequence of topics that ensures accessibility. We find that the networks exhibit strong core-periphery architecture, where a dense core of concepts presented early is complemented with a sparse periphery presented evenly throughout the exposition; the latter is composed of many small modules each reflecting more narrow domains. Using tools from applied topology, we find that the expositional evolution of the semantic networks produces and subsequently fills knowledge gaps, and that the density of these gaps tracks negatively with community ratings of each textbook. Broadly, our study lays the groundwork for future efforts developing optimal design principles for textbook exposition and teaching in a classroom setting.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.04911v2
PDF	https://arxiv.org/pdf/1908.04911v2.pdf
PWC	https://paperswithcode.com/paper/architecture-and-evolution-of-semantic
Repo
Framework

Deep Ensemble Learning for News Stance Detection


Title	Deep Ensemble Learning for News Stance Detection
Authors	Wenjun Liao, Chenghua Lin
Abstract	Stance detection in fake news is an important component in news veracity assessment because this process helps fact-checking by understanding stance to a central claim from different information sources. The Fake News Challenge Stage 1 (FNC-1) held in 2017 was setup for this purpose, which involves estimating the stance of a news article body relative to a given headline. This thesis starts from the error analysis for the three top-performing systems in FNC-1. Based on the analysis, a simple but tough-to-beat Multilayer Perceptron system is chosen as the baseline. Afterwards, three approaches are explored to improve baseline.The first approach explores the possibility of improving the prediction accuracy by adding extra keywords features when training a model, where keywords are converted to an indicator vector and then concatenated to the baseline features. A list of keywords is manually selected based on the error analysis, which may best reflect some characteristics of fake news titles and bodies. To make this selection process automatically, three algorithms are created based on Mutual Information (MI) theory: keywords generator based on MI stance class, MI customised class, and Pointwise MI algorithm. The second approach is based on word embedding, where word2vec model is introduced and two document similarities calculation algorithms are implemented: wor2vec cosine similarity and WMD distance. The third approach is ensemble learning. Different models are configured together with two continuous outputs combining algorithms. The 10-fold cross validation reveals that the ensemble of three neural network models trained from simple bag-of-words features gives the best performance. It is therefore selected to compete in FNC-1. After hyperparameters fine tuning, the selected deep ensemble model beats the FNC-1 winner team by a remarkable 34.25 marks under FNC-1’s evaluation metric.
Tasks	Stance Detection
Published	2019-09-13
URL	https://arxiv.org/abs/1909.12233v1
PDF	https://arxiv.org/pdf/1909.12233v1.pdf
PWC	https://paperswithcode.com/paper/deep-ensemble-learning-for-news-stance
Repo
Framework

Empirical Evaluations of Preprocessing Parameters’ Impact on Predictive Coding’s Effectiveness


Title	Empirical Evaluations of Preprocessing Parameters’ Impact on Predictive Coding’s Effectiveness
Authors	Rishi Chhatwal, Nathaniel Huber-Fliflet, Robert Keeling, Jianping Zhang, Haozhen Zhao
Abstract	Predictive coding, once used in only a small fraction of legal and business matters, is now widely deployed to quickly cull through increasingly vast amounts of data and reduce the need for costly and inefficient human document review. Previously, the sole front-end input used to create a predictive model was the exemplar documents (training data) chosen by subject-matter experts. Many predictive coding tools require users to rely on static preprocessing parameters and a single machine learning algorithm to develop the predictive model. Little research has been published discussing the impact preprocessing parameters and learning algorithms have on the effectiveness of the technology. A deeper dive into the generation of a predictive model shows that the settings and algorithm can have a strong effect on the accuracy and efficacy of a predictive coding tool. Understanding how these input parameters affect the output will empower legal teams with the information they need to implement predictive coding as efficiently and effectively as possible. This paper outlines different preprocessing parameters and algorithms as applied to multiple real-world data sets to understand the influence of various approaches.
Tasks
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01718v1
PDF	http://arxiv.org/pdf/1904.01718v1.pdf
PWC	https://paperswithcode.com/paper/empirical-evaluations-of-preprocessing
Repo
Framework

Analyzing Cyber-Physical Systems from the Perspective of Artificial Intelligence


Title	Analyzing Cyber-Physical Systems from the Perspective of Artificial Intelligence
Authors	Eric M. S. P. Veith, Lars Fischer, Martin Tröschel, Astrid Nieße
Abstract	Principles of modern cyber-physical system (CPS) analysis are based on analytical methods that depend on whether safety or liveness requirements are considered. Complexity is abstracted through different techniques, ranging from stochastic modelling to contracts. However, both distributed heuristics and Artificial Intelligence (AI)-based approaches as well as the user perspective or unpredictable effects, such as accidents or the weather, introduce enough uncertainty to warrant reinforcement-learning-based approaches. This paper compares traditional approaches in the domain of CPS modelling and analysis with the AI researcher perspective to exploring unknown complex systems.
Tasks
Published	2019-08-21
URL	https://arxiv.org/abs/1908.11779v1
PDF	https://arxiv.org/pdf/1908.11779v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-cyber-physical-systems-from-the
Repo
Framework

tsmp: An R Package for Time Series with Matrix Profile


Title	tsmp: An R Package for Time Series with Matrix Profile
Authors	Francisco Bischoff, Pedro Pereira Rodrigues
Abstract	This article describes tsmp, an R package that implements the matrix profile concept for time series. The tsmp package is a toolkit that allows all-pairs similarity joins, motif, discords and chains discovery, semantic segmentation, etc. Here we describe how the tsmp package may be used by showing some of the use-cases from the original articles and evaluate the algorithm speed in the R environment. This package can be downloaded at https://CRAN.R-project.org/package=tsmp.
Tasks	Semantic Segmentation, Time Series
Published	2019-04-18
URL	http://arxiv.org/abs/1904.12626v1
PDF	http://arxiv.org/pdf/1904.12626v1.pdf
PWC	https://paperswithcode.com/paper/190412626
Repo
Framework