May 5, 2019

3329 words 16 mins read

Paper Group ANR 491

Complexity of Manipulation with Partial Information in Voting. Hippocampus Temporal Lobe Epilepsy Detection using a Combination of Shape-based Features and Spherical Harmonics Representation. Curie: A method for protecting SVM Classifier from Poisoning Attack. Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology A …

Complexity of Manipulation with Partial Information in Voting


Title	Complexity of Manipulation with Partial Information in Voting
Authors	Palash Dey, Neeldhara Misra, Y. Narahari
Abstract	The Coalitional Manipulation problem has been studied extensively in the literature for many voting rules. However, most studies have focused on the complete information setting, wherein the manipulators know the votes of the non-manipulators. While this assumption is reasonable for purposes of showing intractability, it is unrealistic for algorithmic considerations. In most real-world scenarios, it is impractical for the manipulators to have accurate knowledge of all the other votes. In this paper, we investigate manipulation with incomplete information. In our framework, the manipulators know a partial order for each voter that is consistent with the true preference of that voter. In this setting, we formulate three natural computational notions of manipulation, namely weak, opportunistic, and strong manipulation. We say that an extension of a partial order is if there exists a manipulative vote for that extension. 1. Weak Manipulation (WM): the manipulators seek to vote in a way that makes their preferred candidate win in at least one extension of the partial votes of the non-manipulators. 2. Opportunistic Manipulation (OM): the manipulators seek to vote in a way that makes their preferred candidate win in every viable extension of the partial votes of the non-manipulators. 3. Strong Manipulation (SM): the manipulators seek to vote in a way that makes their preferred candidate win in every extension of the partial votes of the non-manipulators. We consider several scenarios for which the traditional manipulation problems are easy (for instance, Borda with a single manipulator). For many of them, the corresponding manipulative questions that we propose turn out to be computationally intractable. Our hardness results often hold even when very little information is missing, or in other words, even when the instances are quite close to the complete information setting.
Tasks
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04359v2
PDF	http://arxiv.org/pdf/1604.04359v2.pdf
PWC	https://paperswithcode.com/paper/complexity-of-manipulation-with-partial
Repo
Framework

Hippocampus Temporal Lobe Epilepsy Detection using a Combination of Shape-based Features and Spherical Harmonics Representation


Title	Hippocampus Temporal Lobe Epilepsy Detection using a Combination of Shape-based Features and Spherical Harmonics Representation
Authors	Zohreh Kohan, Hamidreza Farhidzadeh, Reza Azmi, Behrouz Gholizadeh
Abstract	Most of the temporal lobe epilepsy detection approaches are based on hippocampus deformation and use complicated features, resulting, detection is done with complicated features extraction and pre-processing task. In this paper, a new detection method based on shape-based features and spherical harmonics is proposed which can analysis the hippocampus shape anomaly and detection asymmetry. This method consisted of two main parts; (1) shape feature extraction, and (2) image classification. For evaluation, HFH database is used which is publicly available in this field. Nine different geometry and 256 spherical harmonic features are introduced then selected Eighteen of them that detect the asymmetry in hippocampus significantly in a randomly selected subset of the dataset. Then a support vector machine (SVM) classifier was employed to classify the remaining images of the dataset to normal and epileptic images using our selected features. On a dataset of 25 images, 12 images were used for feature extraction and the rest 13 for classification. The results show that the proposed method has accuracy, specificity and sensitivity of, respectively, 84%, 100%, and 80%. Therefore, the proposed approach shows acceptable result and is straightforward also; complicated pre-processing steps were omitted compared to other methods.
Tasks	Image Classification
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00338v2
PDF	http://arxiv.org/pdf/1612.00338v2.pdf
PWC	https://paperswithcode.com/paper/hippocampus-temporal-lobe-epilepsy-detection
Repo
Framework

Curie: A method for protecting SVM Classifier from Poisoning Attack


Title	Curie: A method for protecting SVM Classifier from Poisoning Attack
Authors	Ricky Laishram, Vir Virander Phoha
Abstract	Machine learning is used in a number of security related applications such as biometric user authentication, speaker identification etc. A type of causative integrity attack against machine learning called Poisoning attack works by injecting specially crafted data points in the training data so as to increase the false positive rate of the classifier. In the context of the biometric authentication, this means that more intruders will be classified as valid user, and in case of speaker identification system, user A will be classified user B. In this paper, we examine poisoning attack against SVM and introduce - Curie - a method to protect the SVM classifier from the poisoning attack. The basic idea of our method is to identify the poisoned data points injected by the adversary and filter them out. Our method is light weight and can be easily integrated into existing systems. Experimental results show that it works very well in filtering out the poisoned data.
Tasks	Speaker Identification
Published	2016-06-05
URL	http://arxiv.org/abs/1606.01584v2
PDF	http://arxiv.org/pdf/1606.01584v2.pdf
PWC	https://paperswithcode.com/paper/curie-a-method-for-protecting-svm-classifier
Repo
Framework

Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis


Title	Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
Authors	Yo Seob Han, Jaejun Yoo, Jong Chul Ye
Abstract	Recently, compressed sensing (CS) computed tomography (CT) using sparse projection views has been extensively investigated to reduce the potential risk of radiation to patient. However, due to the insufficient number of projection views, an analytic reconstruction approach results in severe streaking artifacts and CS-based iterative approach is computationally very expensive. To address this issue, here we propose a novel deep residual learning approach for sparse view CT reconstruction. Specifically, based on a novel persistent homology analysis showing that the manifold of streaking artifacts is topologically simpler than original ones, a deep residual learning architecture that estimates the streaking artifacts is developed. Once a streaking artifact image is estimated, an artifact-free image can be obtained by subtracting the streaking artifacts from the input image. Using extensive experiments with real patient data set, we confirm that the proposed residual learning provides significantly better image reconstruction performance with several orders of magnitude faster computational speed.
Tasks	Computed Tomography (CT), Image Reconstruction
Published	2016-11-19
URL	http://arxiv.org/abs/1611.06391v2
PDF	http://arxiv.org/pdf/1611.06391v2.pdf
PWC	https://paperswithcode.com/paper/deep-residual-learning-for-compressed-sensing
Repo
Framework

Personalized and situation-aware multimodal route recommendations: the FAVOUR algorithm


Title	Personalized and situation-aware multimodal route recommendations: the FAVOUR algorithm
Authors	Paolo Campigotto, Christian Rudloff, Maximilian Leodolter, Dietmar Bauer
Abstract	Route choice in multimodal networks shows a considerable variation between different individuals as well as the current situational context. Personalization of recommendation algorithms are already common in many areas, e.g., online retail. However, most online routing applications still provide shortest distance or shortest travel-time routes only, neglecting individual preferences as well as the current situation. Both aspects are of particular importance in a multimodal setting as attractivity of some transportation modes such as biking crucially depends on personal characteristics and exogenous factors like the weather. This paper introduces the FAVourite rOUte Recommendation (FAVOUR) approach to provide personalized, situation-aware route proposals based on three steps: first, at the initialization stage, the user provides limited information (home location, work place, mobility options, sociodemographics) used to select one out of a small number of initial profiles. Second, based on this information, a stated preference survey is designed in order to sharpen the profile. In this step a mass preference prior is used to encode the prior knowledge on preferences from the class identified in step one. And third, subsequently the profile is continuously updated during usage of the routing services. The last two steps use Bayesian learning techniques in order to incorporate information from all contributing individuals. The FAVOUR approach is presented in detail and tested on a small number of survey participants. The experimental results on this real-world dataset show that FAVOUR generates better-quality recommendations w.r.t. alternative learning algorithms from the literature. In particular the definition of the mass preference prior for initialization of step two is shown to provide better predictions than a number of alternatives from the literature.
Tasks
Published	2016-02-29
URL	http://arxiv.org/abs/1602.09076v1
PDF	http://arxiv.org/pdf/1602.09076v1.pdf
PWC	https://paperswithcode.com/paper/personalized-and-situation-aware-multimodal
Repo
Framework

Personalized Machine Translation: Preserving Original Author Traits


Title	Personalized Machine Translation: Preserving Original Author Traits
Authors	Ella Rabinovich, Shachar Mirkin, Raj Nath Patel, Lucia Specia, Shuly Wintner
Abstract	The language that we produce reflects our personality, and various personal and demographic characteristics can be detected in natural language texts. We focus on one particular personal trait of the author, gender, and study how it is manifested in original texts and in translations. We show that author’s gender has a powerful, clear signal in originals texts, but this signal is obfuscated in human and machine translation. We then propose simple domain-adaptation techniques that help retain the original gender traits in the translation, without harming the quality of the translation, thereby creating more personalized machine translation systems.
Tasks	Domain Adaptation, Machine Translation
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05461v2
PDF	http://arxiv.org/pdf/1610.05461v2.pdf
PWC	https://paperswithcode.com/paper/personalized-machine-translation-preserving
Repo
Framework

AFFACT - Alignment-Free Facial Attribute Classification Technique


Title	AFFACT - Alignment-Free Facial Attribute Classification Technique
Authors	Manuel Günther, Andras Rozsa, Terrance E. Boult
Abstract	Facial attributes are soft-biometrics that allow limiting the search space, e.g., by rejecting identities with non-matching facial characteristics such as nose sizes or eyebrow shapes. In this paper, we investigate how the latest versions of deep convolutional neural networks, ResNets, perform on the facial attribute classification task. We test two loss functions: the sigmoid cross-entropy loss and the Euclidean loss, and find that for classification performance there is little difference between these two. Using an ensemble of three ResNets, we obtain the new state-of-the-art facial attribute classification error of 8.00% on the aligned images of the CelebA dataset. More significantly, we introduce the Alignment-Free Facial Attribute Classification Technique (AFFACT), a data augmentation technique that allows a network to classify facial attributes without requiring alignment beyond detected face bounding boxes. To our best knowledge, we are the first to report similar accuracy when using only the detected bounding boxes – rather than requiring alignment based on automatically detected facial landmarks – and who can improve classification accuracy with rotating and scaling test images. We show that this approach outperforms the CelebA baseline on unaligned images with a relative improvement of 36.8%.
Tasks	Data Augmentation, Facial Attribute Classification
Published	2016-11-18
URL	http://arxiv.org/abs/1611.06158v2
PDF	http://arxiv.org/pdf/1611.06158v2.pdf
PWC	https://paperswithcode.com/paper/affact-alignment-free-facial-attribute
Repo
Framework

A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses


Title	A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses
Authors	Matteo Ruggero Ronchi, Joon Sik Kim, Yisong Yue
Abstract	We tackle the problem of learning a rotation invariant latent factor model when the training data is comprised of lower-dimensional projections of the original feature space. The main goal is the discovery of a set of 3-D bases poses that can characterize the manifold of primitive human motions, or movemes, from a training set of 2-D projected poses obtained from still images taken at various camera angles. The proposed technique for basis discovery is data-driven rather than hand-designed. The learned representation is rotation invariant, and can reconstruct any training instance from multiple viewing angles. We apply our method to modeling human poses in sports (via the Leeds Sports Dataset), and demonstrate the effectiveness of the learned bases in a range of applications such as activity classification, inference of dynamics from a single frame, and synthetic representation of movements.
Tasks
Published	2016-09-23
URL	http://arxiv.org/abs/1609.07495v1
PDF	http://arxiv.org/pdf/1609.07495v1.pdf
PWC	https://paperswithcode.com/paper/a-rotation-invariant-latent-factor-model-for
Repo
Framework

Data Centroid Based Multi-Level Fuzzy Min-Max Neural Network


Title	Data Centroid Based Multi-Level Fuzzy Min-Max Neural Network
Authors	Shraddha Deshmukh, Sagar Gandhi, Pratap Sanap, Vivek Kulkarni
Abstract	Recently, a multi-level fuzzy min max neural network (MLF) was proposed, which improves the classification accuracy by handling an overlapped region (area of confusion) with the help of a tree structure. In this brief, an extension of MLF is proposed which defines a new boundary region, where the previously proposed methods mark decisions with less confidence and hence misclassification is more frequent. A methodology to classify patterns more accurately is presented. Our work enhances the testing procedure by means of data centroids. We exhibit an illustrative example, clearly highlighting the advantage of our approach. Results on standard datasets are also presented to evidentially prove a consistent improvement in the classification rate.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05513v2
PDF	http://arxiv.org/pdf/1608.05513v2.pdf
PWC	https://paperswithcode.com/paper/data-centroid-based-multi-level-fuzzy-min-max
Repo
Framework

PCA-aided Fully Convolutional Networks for Semantic Segmentation of Multi-channel fMRI


Title	PCA-aided Fully Convolutional Networks for Semantic Segmentation of Multi-channel fMRI
Authors	Lei Tai, Haoyang Ye, Qiong Ye, Ming Liu
Abstract	Semantic segmentation of functional magnetic resonance imaging (fMRI) makes great sense for pathology diagnosis and decision system of medical robots. The multi-channel fMRI provides more information of the pathological features. But the increased amount of data causes complexity in feature detections. This paper proposes a principal component analysis (PCA)-aided fully convolutional network to particularly deal with multi-channel fMRI. We transfer the learned weights of contemporary classification networks to the segmentation task by fine-tuning. The results of the convolutional network are compared with various methods e.g. k-NN. A new labeling strategy is proposed to solve the semantic segmentation problem with unclear boundaries. Even with a small-sized training dataset, the test results demonstrate that our model outperforms other pathological feature detection methods. Besides, its forward inference only takes 90 milliseconds for a single set of fMRI data. To our knowledge, this is the first time to realize pixel-wise labeling of multi-channel magnetic resonance image using FCN.
Tasks	Semantic Segmentation
Published	2016-10-06
URL	http://arxiv.org/abs/1610.01732v4
PDF	http://arxiv.org/pdf/1610.01732v4.pdf
PWC	https://paperswithcode.com/paper/pca-aided-fully-convolutional-networks-for
Repo
Framework

Learning to learn with backpropagation of Hebbian plasticity


Title	Learning to learn with backpropagation of Hebbian plasticity
Authors	Thomas Miconi
Abstract	Hebbian plasticity is a powerful principle that allows biological brains to learn from their lifetime experience. By contrast, artificial neural networks trained with backpropagation generally have fixed connection weights that do not change once training is complete. While recent methods can endow neural networks with long-term memories, Hebbian plasticity is currently not amenable to gradient descent. Here we derive analytical expressions for activity gradients in neural networks with Hebbian plastic connections. Using these expressions, we can use backpropagation to train not just the baseline weights of the connections, but also their plasticity. As a result, the networks “learn how to learn” in order to solve the problem at hand: the trained networks automatically perform fast learning of unpredictable environmental features during their lifetime, expanding the range of solvable problems. We test the algorithm on various on-line learning tasks, including pattern completion, one-shot learning, and reversal learning. The algorithm successfully learns how to learn the relevant associations from one-shot instruction, and fine-tunes the temporal dynamics of plasticity to allow for continual learning in response to changing environmental parameters. We conclude that backpropagation of Hebbian plasticity offers a powerful model for lifelong learning.
Tasks	Continual Learning, One-Shot Learning
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02228v2
PDF	http://arxiv.org/pdf/1609.02228v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-learn-with-backpropagation-of
Repo
Framework

Multi-View Fuzzy Clustering with Minimax Optimization for Effective Clustering of Data from Multiple Sources


Title	Multi-View Fuzzy Clustering with Minimax Optimization for Effective Clustering of Data from Multiple Sources
Authors	Yangtao Wang, Lihui Chen
Abstract	Multi-view data clustering refers to categorizing a data set by making good use of related information from multiple representations of the data. It becomes important nowadays because more and more data can be collected in a variety of ways, in different settings and from different sources, so each data set can be represented by different sets of features to form different views of it. Many approaches have been proposed to improve clustering performance by exploring and integrating heterogeneous information underlying different views. In this paper, we propose a new multi-view fuzzy clustering approach called MinimaxFCM by using minimax optimization based on well-known Fuzzy c means. In MinimaxFCM the consensus clustering results are generated based on minimax optimization in which the maximum disagreements of different weighted views are minimized. Moreover, the weight of each view can be learned automatically in the clustering process. In addition, there is only one parameter to be set besides the fuzzifier. The detailed problem formulation, updating rules derivation, and the in-depth analysis of the proposed MinimaxFCM are provided here. Experimental studies on nine multi-view data sets including real world image and document data sets have been conducted. We observed that MinimaxFCM outperforms related multi-view clustering approaches in terms of clustering accuracy, demonstrating the great potential of MinimaxFCM for multi-view data analysis.
Tasks
Published	2016-08-25
URL	http://arxiv.org/abs/1608.07005v1
PDF	http://arxiv.org/pdf/1608.07005v1.pdf
PWC	https://paperswithcode.com/paper/multi-view-fuzzy-clustering-with-minimax
Repo
Framework

Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data


Title	Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data
Authors	Jing Wang, Yu Cheng, Rogerio Schmidt Feris
Abstract	The way people look in terms of facial attributes (ethnicity, hair color, facial hair, etc.) and the clothes or accessories they wear (sunglasses, hat, hoodies, etc.) is highly dependent on geo-location and weather condition, respectively. This work explores, for the first time, the use of this contextual information, as people with wearable cameras walk across different neighborhoods of a city, in order to learn a rich feature representation for facial attribute classification, without the costly manual annotation required by previous methods. By tracking the faces of casual walkers on more than 40 hours of egocentric video, we are able to cover tens of thousands of different identities and automatically extract nearly 5 million pairs of images connected by or from different face tracks, along with their weather and location context, under pose and lighting variations. These image pairs are then fed into a deep network that preserves similarity of images connected by the same track, in order to capture identity-related attribute features, and optimizes for location and weather prediction to capture additional facial attribute features. Finally, the network is fine-tuned with manually annotated samples. We perform an extensive experimental analysis on wearable data and two standard benchmark datasets based on web images (LFWA and CelebA). Our method outperforms by a large margin a network trained from scratch. Moreover, even without using manually annotated identity labels for pre-training as in previous methods, our approach achieves results that are better than the state of the art.
Tasks	Facial Attribute Classification, Representation Learning
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06433v3
PDF	http://arxiv.org/pdf/1604.06433v3.pdf
PWC	https://paperswithcode.com/paper/walk-and-learn-facial-attribute
Repo
Framework

A Topological Lowpass Filter for Quasiperiodic Signals


Title	A Topological Lowpass Filter for Quasiperiodic Signals
Authors	Michael Robinson
Abstract	This article presents a two-stage topological algorithm for recovering an estimate of a quasiperiodic function from a set of noisy measurements. The first stage of the algorithm is a topological phase estimator, which detects the quasiperiodic structure of the function without placing additional restrictions on the function. By respecting this phase estimate, the algorithm avoids creating distortion even when it uses a large number of samples for the estimate of the function.
Tasks
Published	2016-06-28
URL	http://arxiv.org/abs/1607.06032v1
PDF	http://arxiv.org/pdf/1607.06032v1.pdf
PWC	https://paperswithcode.com/paper/a-topological-lowpass-filter-for
Repo
Framework

Predicting Performance on MOOC Assessments using Multi-Regression Models


Title	Predicting Performance on MOOC Assessments using Multi-Regression Models
Authors	Zhiyun Ren, Huzefa Rangwala, Aditya Johri
Abstract	The past few years has seen the rapid growth of data min- ing approaches for the analysis of data obtained from Mas- sive Open Online Courses (MOOCs). The objectives of this study are to develop approaches to predict the scores a stu- dent may achieve on a given grade-related assessment based on information, considered as prior performance or prior ac- tivity in the course. We develop a personalized linear mul- tiple regression (PLMR) model to predict the grade for a student, prior to attempting the assessment activity. The developed model is real-time and tracks the participation of a student within a MOOC (via click-stream server logs) and predicts the performance of a student on the next as- sessment within the course offering. We perform a com- prehensive set of experiments on data obtained from three openEdX MOOCs via a Stanford University initiative. Our experimental results show the promise of the proposed ap- proach in comparison to baseline approaches and also helps in identification of key features that are associated with the study habits and learning behaviors of students.
Tasks
Published	2016-05-08
URL	http://arxiv.org/abs/1605.02269v1
PDF	http://arxiv.org/pdf/1605.02269v1.pdf
PWC	https://paperswithcode.com/paper/predicting-performance-on-mooc-assessments
Repo
Framework