July 27, 2019

3061 words 15 mins read

Paper Group ANR 500

Affine-Gradient Based Local Binary Pattern Descriptor for Texture Classiffication. Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains. Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization. Statistical Analysis on Bangla Newspaper Data to Extract Trending Topic and Visualize Its Change Over Time. …

Affine-Gradient Based Local Binary Pattern Descriptor for Texture Classiffication


Title	Affine-Gradient Based Local Binary Pattern Descriptor for Texture Classiffication
Authors	You Hao, Shirui Li, Hanlin Mo, Hua Li
Abstract	We present a novel Affine-Gradient based Local Binary Pattern (AGLBP) descriptor for texture classification. It is very hard to describe complicated texture using single type information, such as Local Binary Pattern (LBP), which just utilizes the sign information of the difference between the pixel and its local neighbors. Our descriptor has three characteristics: 1) In order to make full use of the information contained in the texture, the Affine-Gradient, which is different from Euclidean-Gradient and invariant to affine transformation is incorporated into AGLBP. 2) An improved method is proposed for rotation invariance, which depends on the reference direction calculating respect to local neighbors. 3) Feature selection method, considering both the statistical frequency and the intraclass variance of the training dataset, is also applied to reduce the dimensionality of descriptors. Experiments on three standard texture datasets, Outex12, Outex10 and KTH-TIPS2, are conducted to evaluate the performance of AGLBP. The results show that our proposed descriptor gets better performance comparing to some state-of-the-art rotation texture descriptors in texture classification.
Tasks	Feature Selection, Texture Classification
Published	2017-05-19
URL	http://arxiv.org/abs/1705.06871v1
PDF	http://arxiv.org/pdf/1705.06871v1.pdf
PWC	https://paperswithcode.com/paper/affine-gradient-based-local-binary-pattern
Repo
Framework

Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains


Title	Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains
Authors	Tegjyot Singh Sethi, Mehmed Kantardzic
Abstract	While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and sophistication of attacks, has prompted the need for a data driven solution, with machine learning forming the core of many cybersecurity systems. Machine learning was not designed with security in mind, and the essential assumption of stationarity, requiring that the training and testing data follow similar distributions, is violated in an adversarial domain. In this paper, an adversary’s view point of a classification based system, is presented. Based on a formal adversarial model, the Seed-Explore-Exploit framework is presented, for simulating the generation of data driven and reverse engineering attacks on classifiers. Experimental evaluation, on 10 real world datasets and using the Google Cloud Prediction Platform, demonstrates the innate vulnerability of classifiers and the ease with which evasion can be carried out, without any explicit information about the classifier type, the training data or the application domain. The proposed framework, algorithms and empirical evaluation, serve as a white hat analysis of the vulnerabilities, and aim to foster the development of secure machine learning frameworks.
Tasks
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07909v1
PDF	http://arxiv.org/pdf/1703.07909v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-exploratory-attacks-on-black-box
Repo
Framework

Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization


Title	Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization
Authors	Mark O. Riedl, Brent Harrison
Abstract	Autonomous systems that operate around humans will likely always rely on kill switches that stop their execution and allow them to be remote-controlled for the safety of humans or to prevent damage to the system. It is theoretically possible for an autonomous system with sufficient sensor and effector capability that learn online using reinforcement learning to discover that the kill switch deprives it of long-term reward and thus learn to disable the switch or otherwise prevent a human operator from using the switch. This is referred to as the big red button problem. We present a technique that prevents a reinforcement learning agent from learning to disable the kill switch. We introduce an interruption process in which the agent’s sensors and effectors are redirected to a virtual simulation where it continues to believe it is receiving reward. We illustrate our technique in a simple grid world environment.
Tasks
Published	2017-03-30
URL	http://arxiv.org/abs/1703.10284v2
PDF	http://arxiv.org/pdf/1703.10284v2.pdf
PWC	https://paperswithcode.com/paper/enter-the-matrix-safely-interruptible
Repo
Framework


Title	Statistical Analysis on Bangla Newspaper Data to Extract Trending Topic and Visualize Its Change Over Time
Authors	Syed Mehedi Hasan Nirob, Md. Kazi Nayeem, Md. Saiful Islam
Abstract	Trending topic of newspapers is an indicator to understand the situation of a country and also a way to evaluate the particular newspaper. This paper represents a model describing few techniques to select trending topics from Bangla Newspaper. Topics that are discussed more frequently than other in Bangla newspaper will be marked and how a very famous topic loses its importance with the change of time and another topic takes its place will be demonstrated. Data from two popular Bangla Newspaper with date and time were collected. Statistical analysis was performed after on these data after preprocessing. Popular and most used keywords were extracted from the stream of Bangla keyword with this analysis. This model can also cluster category wise news trend or a list of news trend in daily or weekly basis with enough data. A pattern can be found on their news trend too. Comparison among past news trend of Bangla newspapers will give a visualization of the situation of Bangladesh. This visualization will be helpful to predict future trending topics of Bangla Newspaper.
Tasks
Published	2017-01-27
URL	http://arxiv.org/abs/1701.07955v1
PDF	http://arxiv.org/pdf/1701.07955v1.pdf
PWC	https://paperswithcode.com/paper/statistical-analysis-on-bangla-newspaper-data
Repo
Framework

Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP


Title	Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
Authors	Satyen Kale, Zohar Karnin, Tengyuan Liang, Dávid Pál
Abstract	Online sparse linear regression is an online problem where an algorithm repeatedly chooses a subset of coordinates to observe in an adversarially chosen feature vector, makes a real-valued prediction, receives the true label, and incurs the squared loss. The goal is to design an online learning algorithm with sublinear regret to the best sparse linear predictor in hindsight. Without any assumptions, this problem is known to be computationally intractable. In this paper, we make the assumption that data matrix satisfies restricted isometry property, and show that this assumption leads to computationally efficient algorithms with sublinear regret for two variants of the problem. In the first variant, the true label is generated according to a sparse linear model with additive Gaussian noise. In the second, the true label is chosen adversarially.
Tasks	Feature Selection
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04690v1
PDF	http://arxiv.org/pdf/1706.04690v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-feature-selection-computationally
Repo
Framework

PROBE-GK: Predictive Robust Estimation using Generalized Kernels


Title	PROBE-GK: Predictive Robust Estimation using Generalized Kernels
Authors	Valentin Peretroukhin, William Vega-Brown, Nicholas Roy, Jonathan Kelly
Abstract	Many algorithms in computer vision and robotics make strong assumptions about uncertainty, and rely on the validity of these assumptions to produce accurate and consistent state estimates. In practice, dynamic environments may degrade sensor performance in predictable ways that cannot be captured with static uncertainty parameters. In this paper, we employ fast nonparametric Bayesian inference techniques to more accurately model sensor uncertainty. By setting a prior on observation uncertainty, we derive a predictive robust estimator, and show how our model can be learned from sample images, both with and without knowledge of the motion used to generate the data. We validate our approach through Monte Carlo simulations, and report significant improvements in localization accuracy relative to a fixed noise model in several settings, including on synthetic data, the KITTI dataset, and our own experimental platform.
Tasks	Bayesian Inference
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00171v2
PDF	http://arxiv.org/pdf/1708.00171v2.pdf
PWC	https://paperswithcode.com/paper/probe-gk-predictive-robust-estimation-using
Repo
Framework

Multimodal Attribute Extraction


Title	Multimodal Attribute Extraction
Authors	Robert L. Logan IV, Samuel Humeau, Sameer Singh
Abstract	The broad goal of information extraction is to derive structured information from unstructured data. However, most existing methods focus solely on text, ignoring other types of unstructured data such as images, video and audio which comprise an increasing portion of the information on the web. To address this shortcoming, we propose the task of multimodal attribute extraction. Given a collection of unstructured and semi-structured contextual information about an entity (such as a textual description, or visual depictions) the task is to extract the entity’s underlying attributes. In this paper, we provide a dataset containing mixed-media data for over 2 million product items along with 7 million attribute-value pairs describing the items which can be used to train attribute extractors in a weakly supervised manner. We provide a variety of baselines which demonstrate the relative effectiveness of the individual modes of information towards solving the task, as well as study human performance.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11118v1
PDF	http://arxiv.org/pdf/1711.11118v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-attribute-extraction
Repo
Framework

A Gabor Filter Texture Analysis Approach for Histopathological Brain Tumor Subtype Discrimination


Title	A Gabor Filter Texture Analysis Approach for Histopathological Brain Tumor Subtype Discrimination
Authors	Omar S. Al-Kadi
Abstract	Meningioma brain tumour discrimination is challenging as many histological patterns are mixed between the different subtypes. In clinical practice, dominant patterns are investigated for signs of specific meningioma pathology; however the simple observation could result in inter- and intra-observer variation due to the complexity of the histopathological patterns. Also employing a computerised feature extraction approach applied at a single resolution scale might not suffice in accurately delineating the mixture of histopathological patterns. In this work we propose a novel multiresolution feature extraction approach for characterising the textural properties of the different pathological patterns (i.e. mainly cell nuclei shape, orientation and spatial arrangement within the cytoplasm). The pattern textural properties are characterised at various scales and orientations for an improved separability between the different extracted features. The Gabor filter energy output of each magnitude response was combined with four other fixed-resolution texture signatures (2 model-based and 2 statistical-based) with and without cell nuclei segmentation. The highest classification accuracy of 95% was reported when combining the Gabor filters energy and the meningioma subimage fractal signature as a feature vector without performing any prior cell nuceli segmentation. This indicates that characterising the cell-nuclei self-similarity properties via Gabor filters can assists in achieving an improved meningioma subtype classification, which can assist in overcoming variations in reported diagnosis.
Tasks	Texture Classification
Published	2017-04-17
URL	http://arxiv.org/abs/1704.05122v1
PDF	http://arxiv.org/pdf/1704.05122v1.pdf
PWC	https://paperswithcode.com/paper/a-gabor-filter-texture-analysis-approach-for
Repo
Framework

Transformation Forests


Title	Transformation Forests
Authors	Torsten Hothorn, Achim Zeileis
Abstract	Regression models for supervised learning problems with a continuous target are commonly understood as models for the conditional mean of the target given predictors. This notion is simple and therefore appealing for interpretation and visualisation. Information about the whole underlying conditional distribution is, however, not available from these models. A more general understanding of regression models as models for conditional distributions allows much broader inference from such models, for example the computation of prediction intervals. Several random forest-type algorithms aim at estimating conditional distributions, most prominently quantile regression forests (Meinshausen, 2006, JMLR). We propose a novel approach based on a parametric family of distributions characterised by their transformation function. A dedicated novel “transformation tree” algorithm able to detect distributional changes is developed. Based on these transformation trees, we introduce “transformation forests” as an adaptive local likelihood estimator of conditional distribution functions. The resulting models are fully parametric yet very general and allow broad inference procedures, such as the model-based bootstrap, to be applied in a straightforward way.
Tasks
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02110v2
PDF	http://arxiv.org/pdf/1701.02110v2.pdf
PWC	https://paperswithcode.com/paper/transformation-forests
Repo
Framework

Political Footprints: Political Discourse Analysis using Pre-Trained Word Vectors


Title	Political Footprints: Political Discourse Analysis using Pre-Trained Word Vectors
Authors	Christophe Bruchansky
Abstract	In this paper, we discuss how machine learning could be used to produce a systematic and more objective political discourse analysis. Political footprints are vector space models (VSMs) applied to political discourse. Each of their vectors represents a word, and is produced by training the English lexicon on large text corpora. This paper presents a simple implementation of political footprints, some heuristics on how to use them, and their application to four cases: the U.N. Kyoto Protocol and Paris Agreement, and two U.S. presidential elections. The reader will be offered a number of reasons to believe that political footprints produce meaningful results, along with some suggestions on how to improve their implementation.
Tasks
Published	2017-05-17
URL	http://arxiv.org/abs/1705.06353v1
PDF	http://arxiv.org/pdf/1705.06353v1.pdf
PWC	https://paperswithcode.com/paper/political-footprints-political-discourse
Repo
Framework

Deep Direct Regression for Multi-Oriented Scene Text Detection


Title	Deep Direct Regression for Multi-Oriented Scene Text Detection
Authors	Wenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu
Abstract	In this paper, we first provide a new perspective to divide existing high performance object detection methods into direct and indirect regressions. Direct regression performs boundary regression by predicting the offsets from a given point, while indirect regression predicts the offsets from some bounding box proposals. Then we analyze the drawbacks of the indirect regression, which the recent state-of-the-art detection structures like Faster-RCNN and SSD follows, for multi-oriented scene text detection, and point out the potential superiority of direct regression. To verify this point of view, we propose a deep direct regression based method for multi-oriented scene text detection. Our detection framework is simple and effective with a fully convolutional network and one-step post processing. The fully convolutional network is optimized in an end-to-end way and has bi-task outputs where one is pixel-wise classification between text and non-text, and the other is direct regression to determine the vertex coordinates of quadrilateral text boundaries. The proposed method is particularly beneficial for localizing incidental scene texts. On the ICDAR2015 Incidental Scene Text benchmark, our method achieves the F1-measure of 81%, which is a new state-of-the-art and significantly outperforms previous approaches. On other standard datasets with focused scene texts, our method also reaches the state-of-the-art performance.
Tasks	Multi-Oriented Scene Text Detection, Object Detection, Scene Text Detection
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08289v1
PDF	http://arxiv.org/pdf/1703.08289v1.pdf
PWC	https://paperswithcode.com/paper/deep-direct-regression-for-multi-oriented
Repo
Framework

Resilient Linear Classification: An Approach to Deal with Attacks on Training Data


Title	Resilient Linear Classification: An Approach to Deal with Attacks on Training Data
Authors	Sangdon Park, James Weimer, Insup Lee
Abstract	Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven techniques extract models from training data, where their performance is often analyzed with respect to random errors in the training data. However, if the training data is maliciously altered by attackers, the effect of these attacks on the learning algorithms underpinning data-driven CPS have yet to be considered. In this paper, we analyze the resilience of classification algorithms to training data attacks. Specifically, a generic metric is proposed that is tailored to measure resilience of classification algorithms with respect to worst-case tampering of the training data. Using the metric, we show that traditional linear classification algorithms are resilient under restricted conditions. To overcome these limitations, we propose a linear classification algorithm with a majority constraint and prove that it is strictly more resilient than the traditional algorithms. Evaluations on both synthetic data and a real-world retrospective arrhythmia medical case-study show that the traditional algorithms are vulnerable to tampered training data, whereas the proposed algorithm is more resilient (as measured by worst-case tampering).
Tasks	Autonomous Vehicles
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03366v2
PDF	http://arxiv.org/pdf/1708.03366v2.pdf
PWC	https://paperswithcode.com/paper/resilient-linear-classification-an-approach
Repo
Framework

Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection


Title	Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection
Authors	Cheng-Tao Chung, Cheng-Yu Tsai, Chia-Hsiang Liu, Lin-Shan Lee
Abstract	In this paper we aim to automatically discover high quality frame-level speech features and acoustic tokens directly from unlabeled speech data. A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets of acoustic tokens from the given corpus. Each acoustic token set is specified by a set of hyperparameters describing the model configuration. These different sets of acoustic tokens carry different characteristics for the given corpus and the language behind, thus can be mutually reinforced. The multiple sets of token labels are then used as the targets of a Multi-target Deep Neural Network (MDNN) trained on frame-level acoustic features. Bottleneck features extracted from the MDNN are then used as the feedback input to the MAT and the MDNN itself in the next iteration. The multi-granular acoustic token sets and the frame-level speech features can be iteratively optimized in the iterative deep learning framework. We call this framework the Multi-granular Acoustic Tokenizing Deep Neural Network (MATDNN). The results were evaluated using the metrics and corpora defined in the Zero Resource Speech Challenge organized at Interspeech 2015, and improved performance was obtained with a set of experiments of query-by-example spoken term detection on the same corpora. Visualization for the discovered tokens against the English phonemes was also shown.
Tasks
Published	2017-07-17
URL	http://arxiv.org/abs/1707.05315v1
PDF	http://arxiv.org/pdf/1707.05315v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-iterative-deep-learning-of
Repo
Framework

A Hybrid Deep Learning Approach for Texture Analysis


Title	A Hybrid Deep Learning Approach for Texture Analysis
Authors	Hussein Adly, Mohamed Moustafa
Abstract	Texture classification is a problem that has various applications such as remote sensing and forest species recognition. Solutions tend to be custom fit to the dataset used but fails to generalize. The Convolutional Neural Network (CNN) in combination with Support Vector Machine (SVM) form a robust selection between powerful invariant feature extractor and accurate classifier. The fusion of experts provides stability in classification rates among different datasets.
Tasks	Texture Classification
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08366v1
PDF	http://arxiv.org/pdf/1703.08366v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-deep-learning-approach-for-texture
Repo
Framework

Role of zero synapses in unsupervised feature learning


Title	Role of zero synapses in unsupervised feature learning
Authors	Haiping Huang
Abstract	Synapses in real neural circuits can take discrete values, including zero (silent or potential) synapses. The computational role of zero synapses in unsupervised feature learning of unlabeled noisy data is still unclear, thus it is important to understand how the sparseness of synaptic activity is shaped during learning and its relationship with receptive field formation. Here, we formulate this kind of sparse feature learning by a statistical mechanics approach. We find that learning decreases the fraction of zero synapses, and when the fraction decreases rapidly around a critical data size, an intrinsically structured receptive field starts to develop. Further increasing the data size refines the receptive field, while a very small fraction of zero synapses remain to act as contour detectors. This phenomenon is discovered not only in learning a handwritten digits dataset, but also in learning retinal neural activity measured in a natural-movie-stimuli experiment.
Tasks
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07943v4
PDF	http://arxiv.org/pdf/1703.07943v4.pdf
PWC	https://paperswithcode.com/paper/role-of-zero-synapses-in-unsupervised-feature
Repo
Framework