October 20, 2019

3250 words 16 mins read

Paper Group ANR 71

When Names Are Not Commonly Known: Epistemic Logic with Assignments. MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks. Gray-box Adversarial Testing for Control Systems with Machine Learning Component. Shannon entropy for intuitionistic fuzzy information. Pixels, voxels, and views: A study of shape representations f …

When Names Are Not Commonly Known: Epistemic Logic with Assignments


Title	When Names Are Not Commonly Known: Epistemic Logic with Assignments
Authors	Yanjing Wang, Jeremy Seligman
Abstract	In standard epistemic logic, agent names are usually assumed to be common knowledge implicitly. This is unreasonable for various applications. Inspired by term modal logic and assignment operators in dynamic logic, we introduce a lightweight modal predicate logic where names can be non-rigid. The language can handle various de dicto and de re distinctions in a natural way. The main technical result is a complete axiomatisation of this logic over S5 models.
Tasks
Published	2018-05-10
URL	http://arxiv.org/abs/1805.03852v2
PDF	http://arxiv.org/pdf/1805.03852v2.pdf
PWC	https://paperswithcode.com/paper/when-names-are-not-commonly-known-epistemic
Repo
Framework

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks


Title	MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
Authors	Siwakorn Srisakaokul, Yuhao Zhang, Zexuan Zhong, Wei Yang, Tao Xie, Bo Li
Abstract	Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing defense approaches are still vulnerable to attacks, especially in a white-box attack scenario. To address this issue, we propose a new defense approach, named MulDef, based on robustness diversity. Our approach consists of (1) a general defense framework based on multiple models and (2) a technique for generating these multiple models to achieve high defense capability. In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family. The model family is designed to achieve robustness diversity (i.e., an adversarial example successfully attacking one model cannot succeed in attacking other models in the family). At runtime, a model is randomly selected from the family to be applied on each input example. Our general framework can inspire rich future research to construct a desirable model family achieving higher robustness diversity. Our evaluation results show that MulDef (with only up to 5 models in the family) can substantially improve the target model’s accuracy on adversarial examples by 22-74% in a white-box attack scenario, while maintaining similar accuracy on legitimate examples.
Tasks
Published	2018-08-31
URL	https://arxiv.org/abs/1809.00065v3
PDF	https://arxiv.org/pdf/1809.00065v3.pdf
PWC	https://paperswithcode.com/paper/muldef-multi-model-based-defense-against
Repo
Framework

Gray-box Adversarial Testing for Control Systems with Machine Learning Component


Title	Gray-box Adversarial Testing for Control Systems with Machine Learning Component
Authors	Shakiba Yaghoubi, Georgios Fainekos
Abstract	Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the industry for safety critical systems. The primary reason is that systems with learning based controllers are notoriously hard to test and verify. Even harder is the analysis of such systems against system-level specifications. In this paper, we provide a gradient based method for searching the input space of a closed-loop control system in order to find adversarial samples against some system-level requirements. Our experimental results show that combined with randomized search, our method outperforms Simulated Annealing optimization.
Tasks
Published	2018-12-31
URL	http://arxiv.org/abs/1812.11958v1
PDF	http://arxiv.org/pdf/1812.11958v1.pdf
PWC	https://paperswithcode.com/paper/gray-box-adversarial-testing-for-control
Repo
Framework

Shannon entropy for intuitionistic fuzzy information


Title	Shannon entropy for intuitionistic fuzzy information
Authors	Vasile Patrascu
Abstract	The paper presents an extension of Shannon fuzzy entropy for intuitionistic fuzzy one. Firstly, we presented a new formula for calculating the distance and similarity of intuitionistic fuzzy information. Then, we constructed measures for information features like score, certainty and uncertainty. Also, a new concept was introduced, namely escort fuzzy information. Then, using the escort fuzzy information, Shannon’s formula for intuitionistic fuzzy information was obtained. It should be underlined that Shannon’s entropy for intuitionistic fuzzy information verifies the four defining conditions of intuitionistic fuzzy uncertainty. The measures of its two components were also identified: fuzziness (ambiguity) and incompleteness (ignorance).
Tasks
Published	2018-07-02
URL	http://arxiv.org/abs/1807.01747v2
PDF	http://arxiv.org/pdf/1807.01747v2.pdf
PWC	https://paperswithcode.com/paper/shannon-entropy-for-intuitionistic-fuzzy
Repo
Framework

Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction


Title	Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
Authors	Daeyun Shin, Charless C. Fowlkes, Derek Hoiem
Abstract	The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction. We propose a new algorithm for predicting depth maps from multiple viewpoints, with a single depth or RGB image as input. By modifying the network and the way models are evaluated, we can directly compare the merits of voxels vs. surfaces and viewer-centered vs. object-centered for familiar vs. unfamiliar objects, as predicted from RGB or depth images. Among our findings, we show that surface-based methods outperform voxel representations for objects from novel classes and produce higher resolution outputs. We also find that using viewer-centered coordinates is advantageous for novel objects, while object-centered representations are better for more familiar objects. Interestingly, the coordinate frame significantly affects the shape representation learned, with object-centered placing more importance on implicitly recognizing the object category and viewer-centered producing shape representations with less dependence on category recognition.
Tasks
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06032v2
PDF	http://arxiv.org/pdf/1804.06032v2.pdf
PWC	https://paperswithcode.com/paper/pixels-voxels-and-views-a-study-of-shape
Repo
Framework

Transductive Learning with String Kernels for Cross-Domain Text Classification


Title	Transductive Learning with String Kernels for Cross-Domain Text Classification
Authors	Radu Tudor Ionescu, Andrei M. Butnaru
Abstract	For many text classification tasks, there is a major problem posed by the lack of labeled data in a target domain. Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of such classifiers is usually lower in the cross-domain setting. Recently, string kernels have obtained state-of-the-art results in various text classification tasks such as native language identification or automatic essay scoring. Moreover, classifiers based on string kernels have been found to be robust to the distribution gap between different domains. In this paper, we formally describe an algorithm composed of two simple yet effective transductive learning approaches to further improve the results of string kernels in cross-domain settings. By adapting string kernels to the test set without using the ground-truth test labels, we report significantly better accuracy rates in cross-domain English polarity classification.
Tasks	Cross-Domain Text Classification, Language Identification, Native Language Identification, Text Classification
Published	2018-11-02
URL	http://arxiv.org/abs/1811.01734v1
PDF	http://arxiv.org/pdf/1811.01734v1.pdf
PWC	https://paperswithcode.com/paper/transductive-learning-with-string-kernels-for
Repo
Framework

Robust Kronecker Component Analysis


Title	Robust Kronecker Component Analysis
Authors	Mehdi Bahri, Yannis Panagakis, Stefanos Zafeiriou
Abstract	Dictionary learning and component analysis models are fundamental for learning compact representations that are relevant to a given task (feature extraction, dimensionality reduction, denoising, etc.). The model complexity is encoded by means of specific structure, such as sparsity, low-rankness, or nonnegativity. Unfortunately, approaches like K-SVD - that learn dictionaries for sparse coding via Singular Value Decomposition (SVD) - are hard to scale to high-volume and high-dimensional visual data, and fragile in the presence of outliers. Conversely, robust component analysis methods such as the Robust Principal Component Analysis (RPCA) are able to recover low-complexity (e.g., low-rank) representations from data corrupted with noise of unknown magnitude and support, but do not provide a dictionary that respects the structure of the data (e.g., images), and also involve expensive computations. In this paper, we propose a novel Kronecker-decomposable component analysis model, coined as Robust Kronecker Component Analysis (RKCA), that combines ideas from sparse dictionary learning and robust component analysis. RKCA has several appealing properties, including robustness to gross corruption; it can be used for low-rank modeling, and leverages separability to solve significantly smaller problems. We design an efficient learning algorithm by drawing links with a restricted form of tensor factorization, and analyze its optimality and low-rankness properties. The effectiveness of the proposed approach is demonstrated on real-world applications, namely background subtraction and image denoising and completion, by performing a thorough comparison with the current state of the art.
Tasks	Denoising, Dictionary Learning, Dimensionality Reduction, Image Denoising
Published	2018-01-18
URL	http://arxiv.org/abs/1801.06432v2
PDF	http://arxiv.org/pdf/1801.06432v2.pdf
PWC	https://paperswithcode.com/paper/robust-kronecker-component-analysis
Repo
Framework

On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition


Title	On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition
Authors	Marco Mondelli, Andrea Montanari
Abstract	We establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\boldsymbol x \in \mathbb R^d$, $r$ hidden units with weights ${\boldsymbol w_i}{1\le i \le r}$ and output $y\in \mathbb R$, i.e., $y=\sum{i=1}^r \sigma( \boldsymbol w_i^{\mathsf T}\boldsymbol x)$, with activation functions given by low-degree polynomials. In particular, if $\sigma(x) = a_0+a_1x+a_3x^3$, we prove that no polynomial-time learning algorithm can outperform the trivial predictor that assigns to each example the response variable $\mathbb E(y)$, when $d^{3/2}\ll r\ll d^2$. Our conclusion holds for a `natural data distribution’, namely standard Gaussian feature vectors $\boldsymbol x$, and output distributed according to a two-layer neural network with random isotropic weights, and under a certain complexity-theoretic assumption on tensor decomposition. Roughly speaking, we assume that no polynomial-time algorithm can substantially outperform current methods for tensor decomposition based on the sum-of-squares hierarchy. We also prove generalizations of this statement for higher degree polynomial activations, and non-random weight vectors. Remarkably, several existing algorithms for learning two-layer networks with rigorous guarantees are based on tensor decomposition. Our results support the idea that this is indeed the core computational difficulty in learning such networks, under the stated generative model for the data. As a side result, we show that under this model learning the network requires accurate learning of its weights, a property that does not hold in a more general setting. \|
Tasks
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07301v3
PDF	http://arxiv.org/pdf/1802.07301v3.pdf
PWC	https://paperswithcode.com/paper/on-the-connection-between-learning-two-layers
Repo
Framework

An Efficient End-to-End Neural Model for Handwritten Text Recognition


Title	An Efficient End-to-End Neural Model for Handwritten Text Recognition
Authors	Arindam Chowdhury, Lovekesh Vig
Abstract	Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to yield superior performance over traditional Hidden Markov Model based approaches that suffer from the Markov assumption and therefore lack the representational power of RNNs. In this paper we introduce a novel approach that combines a deep convolutional network with a recurrent Encoder-Decoder network to map an image to a sequence of characters corresponding to the text present in the image. The entire model is trained end-to-end using Focal Loss, an improvement over the standard Cross-Entropy loss that addresses the class imbalance problem, inherent to text recognition. To enhance the decoding capacity of the model, Beam Search algorithm is employed which searches for the best sequence out of a set of hypotheses based on a joint distribution of individual characters. Our model takes as input a downsampled version of the original image thereby making it both computationally and memory efficient. The experimental results were benchmarked against two publicly available datasets, IAM and RIMES. We surpass the state-of-the-art word level accuracy on the evaluation set of both datasets by 3.5% & 1.1%, respectively.
Tasks
Published	2018-07-20
URL	http://arxiv.org/abs/1807.07965v2
PDF	http://arxiv.org/pdf/1807.07965v2.pdf
PWC	https://paperswithcode.com/paper/an-efficient-end-to-end-neural-model-for
Repo
Framework

A Panel Quantile Approach to Attrition Bias in Big Data: Evidence from a Randomized Experiment


Title	A Panel Quantile Approach to Attrition Bias in Big Data: Evidence from a Randomized Experiment
Authors	Matthew Harding, Carlos Lamarche
Abstract	This paper introduces a quantile regression estimator for panel data models with individual heterogeneity and attrition. The method is motivated by the fact that attrition bias is often encountered in Big Data applications. For example, many users sign-up for the latest program but few remain active users several months later, making the evaluation of such interventions inherently very challenging. Building on earlier work by Hausman and Wise (1979), we provide a simple identification strategy that leads to a two-step estimation procedure. In the first step, the coefficients of interest in the selection equation are consistently estimated using parametric or nonparametric methods. In the second step, standard panel quantile methods are employed on a subset of weighted observations. The estimator is computationally easy to implement in Big Data applications with a large number of subjects. We investigate the conditions under which the parameter estimator is asymptotically Gaussian and we carry out a series of Monte Carlo simulations to investigate the finite sample properties of the estimator. Lastly, using a simulation exercise, we apply the method to the evaluation of a recent Time-of-Day electricity pricing experiment inspired by the work of Aigner and Hausman (1980).
Tasks
Published	2018-08-09
URL	http://arxiv.org/abs/1808.03364v1
PDF	http://arxiv.org/pdf/1808.03364v1.pdf
PWC	https://paperswithcode.com/paper/a-panel-quantile-approach-to-attrition-bias
Repo
Framework

When does Bone Suppression and Lung Field Segmentation Improve Chest X-Ray Disease Classification?


Title	When does Bone Suppression and Lung Field Segmentation Improve Chest X-Ray Disease Classification?
Authors	Ivo M. Baltruschat, Leonhard Steinmeister, Harald Ittrich, Gerhard Adam, Hannes Nickisch, Axel Saalbach, Jens von Berg, Michael Grass, Tobias Knopp
Abstract	Chest radiography is the most common clinical examination type. To improve the quality of patient care and to reduce workload, methods for automatic pathology classification have been developed. In this contribution we investigate the usefulness of two advanced image pre-processing techniques, initially developed for image reading by radiologists, for the performance of Deep Learning methods. First, we use bone suppression, an algorithm to artificially remove the rib cage. Secondly, we employ an automatic lung field detection to crop the image to the lung area. Furthermore, we consider the combination of both in the context of an ensemble approach. In a five-times re-sampling scheme, we use Receiver Operating Characteristic (ROC) statistics to evaluate the effect of the pre-processing approaches. Using a Convolutional Neural Network (CNN), optimized for X-ray analysis, we achieve a good performance with respect to all pathologies on average. Superior results are obtained for selected pathologies when using pre-processing, i.e. for mass the area under the ROC curve increased by 9.95%. The ensemble with pre-processed trained models yields the best overall results.
Tasks
Published	2018-10-17
URL	http://arxiv.org/abs/1810.07500v1
PDF	http://arxiv.org/pdf/1810.07500v1.pdf
PWC	https://paperswithcode.com/paper/when-does-bone-suppression-and-lung-field
Repo
Framework

Human Pose and Path Estimation from Aerial Video using Dynamic Classifier Selection


Title	Human Pose and Path Estimation from Aerial Video using Dynamic Classifier Selection
Authors	Asanka G Perera, Yee Wei Law, Javaan Chahl
Abstract	We consider the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. We present a preliminary solution whose distinguishing feature is a dynamic classifier selection architecture. In our solution, each video frame is corrected for perspective using projective transformation. Then, two alternative feature sets are used: (i) Histogram of Oriented Gradients (HOG) of the silhouette, (ii) Convolutional Neural Network (CNN) features of the RGB image. The features (HOG or CNN) are classified using a dynamic classifier. A class is defined as a pose-viewpoint pair, and a total of 64 classes are defined to represent a forward walking and turning gait sequence. Our solution provides three main advantages: (i) Classification is efficient due to dynamic selection (4-class vs. 64-class classification). (ii) Classification errors are confined to neighbors of the true view-points. (iii) The robust temporal relationship between poses is used to resolve the left-right ambiguities of human silhouettes. Experiments conducted on both fronto-parallel videos and aerial videos confirm our solution can achieve accurate pose and trajectory estimation for both scenarios. We found using HOG features provides higher accuracy than using CNN features. For example, applying the HOG-based variant of our scheme to the ‘walking on a figure 8-shaped path’ dataset (1652 frames) achieved estimation accuracies of 99.6% for viewpoints and 96.2% for number of poses.
Tasks
Published	2018-12-16
URL	http://arxiv.org/abs/1812.06408v1
PDF	http://arxiv.org/pdf/1812.06408v1.pdf
PWC	https://paperswithcode.com/paper/human-pose-and-path-estimation-from-aerial
Repo
Framework

Visually-Aware Personalized Recommendation using Interpretable Image Representations


Title	Visually-Aware Personalized Recommendation using Interpretable Image Representations
Authors	Charles Packer, Julian McAuley, Arnau Ramisa
Abstract	Visually-aware recommender systems use visual signals present in the underlying data to model the visual characteristics of items and users’ preferences towards them. In the domain of clothing recommendation, incorporating items’ visual information (e.g., product images) is particularly important since clothing item appearance is often a critical factor in influencing the user’s purchasing decisions. Current state-of-the-art visually-aware recommender systems utilize image features extracted from pre-trained deep convolutional neural networks, however these extremely high-dimensional representations are difficult to interpret, especially in relation to the relatively low number of visual properties that may guide users’ decisions. In this paper we propose a novel approach to personalized clothing recommendation that models the dynamics of individual users’ visual preferences. By using interpretable image representations generated with a unique feature learning process, our model learns to explain users’ prior feedback in terms of their affinity towards specific visual attributes and styles. Our approach achieves state-of-the-art performance on personalized ranking tasks, and the incorporation of interpretable visual features allows for powerful model introspection, which we demonstrate by using an interactive recommendation algorithm and visualizing the rise and fall of fashion trends over time.
Tasks	Recommendation Systems
Published	2018-06-26
URL	http://arxiv.org/abs/1806.09820v2
PDF	http://arxiv.org/pdf/1806.09820v2.pdf
PWC	https://paperswithcode.com/paper/visually-aware-personalized-recommendation
Repo
Framework

Advancing Tabu and Restart in Local Search for Maximum Weight Cliques


Title	Advancing Tabu and Restart in Local Search for Maximum Weight Cliques
Authors	Yi Fan, Nan Li, Chengqian Li, Zongjie Ma, Longin Jan Latecki, Kaile Su
Abstract	The tabu and restart are two fundamental strategies for local search. In this paper, we improve the local search algorithms for solving the Maximum Weight Clique (MWC) problem by introducing new tabu and restart strategies. Both the tabu and restart strategies proposed are based on the notion of a local search scenario, which involves not only a candidate solution but also the tabu status and unlocking relationship. Compared to the strategy of configuration checking, our tabu mechanism discourages forming a cycle of unlocking operations. Our new restart strategy is based on the re-occurrence of a local search scenario instead of that of a candidate solution. Experimental results show that the resulting MWC solver outperforms several state-of-the-art solvers on the DIMACS, BHOSLIB, and two benchmarks from practical applications.
Tasks
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08187v1
PDF	http://arxiv.org/pdf/1804.08187v1.pdf
PWC	https://paperswithcode.com/paper/advancing-tabu-and-restart-in-local-search
Repo
Framework

Automatic Classification of Knee Rehabilitation Exercises Using a Single Inertial Sensor: a Case Study


Title	Automatic Classification of Knee Rehabilitation Exercises Using a Single Inertial Sensor: a Case Study
Authors	Antonio Bevilacqua, Bingquan Huang, Rob Argent, Brian Caulfield, Tahar Kechadi
Abstract	Inertial measurement units have the ability to accurately record the acceleration and angular velocity of human limb segments during discrete joint movements. These movements are commonly used in exercise rehabilitation programmes following orthopaedic surgery such as total knee replacement. This provides the potential for a biofeedback system with data mining technique for patients undertaking exercises at home without physician supervision. We propose to use machine learning techniques to automatically analyse inertial measurement unit data collected during these exercises, and then assess whether each repetition of the exercise was executed correctly or not. Our approach consists of two main phases: signal segmentation, and segment classification. Accurate pre-processing and feature extraction are paramount topics in order for the technique to work. In this paper, we present a classification method for unsupervised rehabilitation exercises, based on a segmentation process that extracts repetitions from a longer signal activity. The results obtained from experimental datasets of both clinical and healthy subjects, for a set of 4 knee exercises commonly used in rehabilitation, are very promising.
Tasks
Published	2018-12-10
URL	http://arxiv.org/abs/1812.03880v1
PDF	http://arxiv.org/pdf/1812.03880v1.pdf
PWC	https://paperswithcode.com/paper/automatic-classification-of-knee
Repo
Framework