Paper Group ANR 427
Open-Set Language Identification. Towards Social Autonomous Vehicles: Efficient Collision Avoidance Scheme Using Richardson’s Arms Race Model. CollabLoc: Privacy-Preserving Multi-Modal Localization via Collaborative Information Fusion. In Search of an Entity Resolution OASIS: Optimal Asymptotic Sequential Importance Sampling. Attentional Pooling fo …
Open-Set Language Identification
| Title | Open-Set Language Identification |
| Authors | Shervin Malmasi |
| Abstract | We present the first open-set language identification experiments using one-class classification. We first highlight the shortcomings of traditional feature extraction methods and propose a hashing-based feature vectorization approach as a solution. Using a dataset of 10 languages from different writing systems, we train a One- Class Support Vector Machine using only a monolingual corpus for each language. Each model is evaluated against a test set of data from all 10 languages and we achieve an average F-score of 0.99, highlighting the effectiveness of this approach for open-set language identification. |
| Tasks | Language Identification |
| Published | 2017-07-16 |
| URL | http://arxiv.org/abs/1707.04817v1 |
| http://arxiv.org/pdf/1707.04817v1.pdf | |
| PWC | https://paperswithcode.com/paper/open-set-language-identification |
| Repo | |
| Framework | |
Towards Social Autonomous Vehicles: Efficient Collision Avoidance Scheme Using Richardson’s Arms Race Model
| Title | Towards Social Autonomous Vehicles: Efficient Collision Avoidance Scheme Using Richardson’s Arms Race Model |
| Authors | Faisal Riaz, Muaz A. Niazi |
| Abstract | Background Road collisions and casualties pose a serious threat to commuters around the globe. Autonomous Vehicles (AVs) aim to make the use of technology to reduce the road accidents. However, the most of research work in the context of collision avoidance has been performed to address, separately, the rear end, front end and lateral collisions in less congested and with high inter-vehicular distances. Purpose The goal of this paper is to introduce the concept of a social agent, which interact with other AVs in social manners like humans are social having the capability of predicting intentions, i.e. mentalizing and copying the actions of each other, i.e. mirroring. The proposed social agent is based on a human-brain inspired mentalizing and mirroring capabilities and has been modelled for collision detection and avoidance under congested urban road traffic. Method We designed our social agent having the capabilities of mentalizing and mirroring and for this purpose we utilized Exploratory Agent Based Modeling (EABM) level of Cognitive Agent Based Computing (CABC) framework proposed by Niazi and Hussain. Results Our simulation and practical experiments reveal that by embedding Richardson’s arms race model within AVs, collisions can be avoided while travelling on congested urban roads in a flock like topologies. The performance of the proposed social agent has been compared at two different levels. |
| Tasks | Autonomous Vehicles |
| Published | 2017-08-06 |
| URL | http://arxiv.org/abs/1708.01931v1 |
| http://arxiv.org/pdf/1708.01931v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-social-autonomous-vehicles-efficient |
| Repo | |
| Framework | |
CollabLoc: Privacy-Preserving Multi-Modal Localization via Collaborative Information Fusion
| Title | CollabLoc: Privacy-Preserving Multi-Modal Localization via Collaborative Information Fusion |
| Authors | Vidyasagar Sadhu, Dario Pompili, Saman Zonouz, Vincent Sritapan |
| Abstract | Mobile phones provide an excellent opportunity for building context-aware applications. In particular, location-based services are important context-aware services that are more and more used for enforcing security policies, for supporting indoor room navigation, and for providing personalized assistance. However, a major problem still remains unaddressed—the lack of solutions that work across buildings while not using additional infrastructure and also accounting for privacy and reliability needs. In this paper, a privacy-preserving, multi-modal, cross-building, collaborative localization platform is proposed based on Wi-Fi RSSI (existing infrastructure), Cellular RSSI, sound and light levels, that enables room-level localization as main application (though sub room level granularity is possible). The privacy is inherently built into the solution based on onion routing, and perturbation/randomization techniques, and exploits the idea of weighted collaboration to increase the reliability as well as to limit the effect of noisy devices (due to sensor noise/privacy). The proposed solution has been analyzed in terms of privacy, accuracy, optimum parameters, and other overheads on location data collected at multiple indoor and outdoor locations using an Android app. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1710.08306v1 |
| http://arxiv.org/pdf/1710.08306v1.pdf | |
| PWC | https://paperswithcode.com/paper/collabloc-privacy-preserving-multi-modal |
| Repo | |
| Framework | |
In Search of an Entity Resolution OASIS: Optimal Asymptotic Sequential Importance Sampling
| Title | In Search of an Entity Resolution OASIS: Optimal Asymptotic Sequential Importance Sampling |
| Authors | Neil G. Marchant, Benjamin I. P. Rubinstein |
| Abstract | Entity resolution (ER) presents unique challenges for evaluation methodology. While crowdsourcing platforms acquire ground truth, sound approaches to sampling must drive labelling efforts. In ER, extreme class imbalance between matching and non-matching records can lead to enormous labelling requirements when seeking statistically consistent estimates for rigorous evaluation. This paper addresses this important challenge with the OASIS algorithm: a sampler and F-measure estimator for ER evaluation. OASIS draws samples from a (biased) instrumental distribution, chosen to ensure estimators with optimal asymptotic variance. As new labels are collected OASIS updates this instrumental distribution via a Bayesian latent variable model of the annotator oracle, to quickly focus on unlabelled items providing more information. We prove that resulting estimates of F-measure, precision, recall converge to the true population values. Thorough comparisons of sampling methods on a variety of ER datasets demonstrate significant labelling reductions of up to 83% without loss to estimate accuracy. |
| Tasks | Entity Resolution |
| Published | 2017-03-02 |
| URL | http://arxiv.org/abs/1703.00617v3 |
| http://arxiv.org/pdf/1703.00617v3.pdf | |
| PWC | https://paperswithcode.com/paper/in-search-of-an-entity-resolution-oasis |
| Repo | |
| Framework | |
Attentional Pooling for Action Recognition
| Title | Attentional Pooling for Action Recognition |
| Authors | Rohit Girdhar, Deva Ramanan |
| Abstract | We introduce a simple yet surprisingly powerful model to incorporate attention in action recognition and human object interaction tasks. Our proposed attention module can be trained with or without extra supervision, and gives a sizable boost in accuracy while keeping the network size and computational cost nearly the same. It leads to significant improvements over state of the art base architecture on three standard action recognition benchmarks across still images and videos, and establishes new state of the art on MPII dataset with 12.5% relative improvement. We also perform an extensive analysis of our attention module both empirically and analytically. In terms of the latter, we introduce a novel derivation of bottom-up and top-down attention as low-rank approximations of bilinear pooling methods (typically used for fine-grained classification). From this perspective, our attention formulation suggests a novel characterization of action recognition as a fine-grained recognition problem. |
| Tasks | Human-Object Interaction Detection, Temporal Action Localization |
| Published | 2017-11-04 |
| URL | http://arxiv.org/abs/1711.01467v3 |
| http://arxiv.org/pdf/1711.01467v3.pdf | |
| PWC | https://paperswithcode.com/paper/attentional-pooling-for-action-recognition |
| Repo | |
| Framework | |
Disintegration and Bayesian Inversion via String Diagrams
| Title | Disintegration and Bayesian Inversion via String Diagrams |
| Authors | Kenta Cho, Bart Jacobs |
| Abstract | The notions of disintegration and Bayesian inversion are fundamental in conditional probability theory. They produce channels, as conditional probabilities, from a joint state, or from an already given channel (in opposite direction). These notions exist in the literature, in concrete situations, but are presented here in abstract graphical formulations. The resulting abstract descriptions are used for proving basic results in conditional probability theory. The existence of disintegration and Bayesian inversion is discussed for discrete probability, and also for measure-theoretic probability — via standard Borel spaces and via likelihoods. Finally, the usefulness of disintegration and Bayesian inversion is illustrated in several examples. |
| Tasks | |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1709.00322v3 |
| http://arxiv.org/pdf/1709.00322v3.pdf | |
| PWC | https://paperswithcode.com/paper/disintegration-and-bayesian-inversion-via |
| Repo | |
| Framework | |
Comparison of fingerprint authentication algorithms for small imaging sensors
| Title | Comparison of fingerprint authentication algorithms for small imaging sensors |
| Authors | Mathilde Bourjot, Regis Perrier, Jean François Mainguet |
| Abstract | The demand for biometric systems has been increasing with the growth of the smartphone market. Biometric devices allow the user to authenticate easily while securing its private data without the need to remember any access code. Amongst them, fingerprint sensors are the most widespread because they seem to provide a good balance between reliability, cost and ease of use. According to smartphone manufacturers, the security level is guaranteed to be high. However, the size of those sensors, which is only a few millimeters squared, prevents the use of minutiae algorithms. To the best of our knowledge, very few studies shed light onto this problem, though many pattern recognition algorithms already exist as well as commercial solutions which are supposedly robust. In this article we try to provide insights on how to tackle this problem by analyzing the performance of three algorithms dedicated to pattern recognition. |
| Tasks | |
| Published | 2017-12-19 |
| URL | http://arxiv.org/abs/1712.06882v1 |
| http://arxiv.org/pdf/1712.06882v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-fingerprint-authentication |
| Repo | |
| Framework | |
Gradient Regularization Improves Accuracy of Discriminative Models
| Title | Gradient Regularization Improves Accuracy of Discriminative Models |
| Authors | Dániel Varga, Adrián Csiszárik, Zsolt Zombori |
| Abstract | Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve classification accuracy on vision tasks, using modern deep neural networks, especially when the amount of training data is small. We introduce our regularizers as members of a broader class of Jacobian-based regularizers. We demonstrate empirically on real and synthetic data that the learning process leads to gradients controlled beyond the training points, and results in solutions that generalize well. |
| Tasks | |
| Published | 2017-12-28 |
| URL | http://arxiv.org/abs/1712.09936v2 |
| http://arxiv.org/pdf/1712.09936v2.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-regularization-improves-accuracy-of |
| Repo | |
| Framework | |
S-Shaped vs. V-Shaped Transfer Functions for Antlion Optimization Algorithm in Feature Selection Problems
| Title | S-Shaped vs. V-Shaped Transfer Functions for Antlion Optimization Algorithm in Feature Selection Problems |
| Authors | Majdi Mafarja, Seyedali Mirjalili |
| Abstract | Feature selection is an important preprocessing step for classification problems. It deals with selecting near optimal features in the original dataset. Feature selection is an NP-hard problem, so meta-heuristics can be more efficient than exact methods. In this work, Ant Lion Optimizer (ALO), which is a recent metaheuristic algorithm, is employed as a wrapper feature selection method. Six variants of ALO are proposed where each employ a transfer function to map a continuous search space to a discrete search space. The performance of the proposed approaches is tested on eighteen UCI datasets and compared to a number of existing approaches in the literature: Particle Swarm Optimization, Gravitational Search Algorithm, and two existing ALO-based approaches. Computational experiments show that the proposed approaches efficiently explore the feature space and select the most informative features, which help to improve the classification accuracy. |
| Tasks | Feature Selection |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.03223v1 |
| http://arxiv.org/pdf/1712.03223v1.pdf | |
| PWC | https://paperswithcode.com/paper/s-shaped-vs-v-shaped-transfer-functions-for |
| Repo | |
| Framework | |
On Consistency of Compressive Spectral Clustering
| Title | On Consistency of Compressive Spectral Clustering |
| Authors | Muni Sreenivas Pydi, Ambedkar Dukkipati |
| Abstract | Spectral clustering is one of the most popular methods for community detection in graphs. A key step in spectral clustering algorithms is the eigen decomposition of the $n{\times}n$ graph Laplacian matrix to extract its $k$ leading eigenvectors, where $k$ is the desired number of clusters among $n$ objects. This is prohibitively complex to implement for very large datasets. However, it has recently been shown that it is possible to bypass the eigen decomposition by computing an approximate spectral embedding through graph filtering of random signals. In this paper, we analyze the working of spectral clustering performed via graph filtering on the stochastic block model. Specifically, we characterize the effects of sparsity, dimensionality and filter approximation error on the consistency of the algorithm in recovering planted clusters. |
| Tasks | Community Detection |
| Published | 2017-02-12 |
| URL | http://arxiv.org/abs/1702.03522v3 |
| http://arxiv.org/pdf/1702.03522v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-consistency-of-compressive-spectral |
| Repo | |
| Framework | |
Fuzzy-Based Dialectical Non-Supervised Image Classification and Clustering
| Title | Fuzzy-Based Dialectical Non-Supervised Image Classification and Clustering |
| Authors | Wellington Pinheiro dos Santos, Francisco Marcos de Assis, Ricardo Emmanuel de Souza, Priscilla B. Mendes, Henrique S. S. Monteiro, Havana Diogo Alves |
| Abstract | The materialist dialectical method is a philosophical investigative method to analyze aspects of reality. These aspects are viewed as complex processes composed by basic units named poles, which interact with each other. Dialectics has experienced considerable progress in the 19th century, with Hegel’s dialectics and, in the 20th century, with the works of Marx, Engels, and Gramsci, in Philosophy and Economics. The movement of poles through their contradictions is viewed as a dynamic process with intertwined phases of evolution and revolutionary crisis. In order to build a computational process based on dialectics, the interaction between poles can be modeled using fuzzy membership functions. Based on this assumption, we introduce the Objective Dialectical Classifier (ODC), a non-supervised map for classification based on materialist dialectics and designed as an extension of fuzzy c-means classifier. As a case study, we used ODC to classify 181 magnetic resonance synthetic multispectral images composed by proton density, $T_1$- and $T_2$-weighted synthetic brain images. Comparing ODC to k-means, fuzzy c-means, and Kohonen’s self-organized maps, concerning with image fidelity indexes as estimatives of quantization distortion, we proved that ODC can reach almost the same quantization performance as optimal non-supervised classifiers like Kohonen’s self-organized maps. |
| Tasks | Image Classification, Quantization |
| Published | 2017-12-03 |
| URL | http://arxiv.org/abs/1712.01694v1 |
| http://arxiv.org/pdf/1712.01694v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-based-dialectical-non-supervised-image |
| Repo | |
| Framework | |
A Categorical Approach for Recognizing Emotional Effects of Music
| Title | A Categorical Approach for Recognizing Emotional Effects of Music |
| Authors | Mohsen Sahraei Ardakani, Ehsan Arbabi |
| Abstract | Recently, digital music libraries have been developed and can be plainly accessed. Latest research showed that current organization and retrieval of music tracks based on album information are inefficient. Moreover, they demonstrated that people use emotion tags for music tracks in order to search and retrieve them. In this paper, we discuss separability of a set of emotional labels, proposed in the categorical emotion expression, using Fisher’s separation theorem. We determine a set of adjectives to tag music parts: happy, sad, relaxing, exciting, epic and thriller. Temporal, frequency and energy features have been extracted from the music parts. It could be seen that the maximum separability within the extracted features occurs between relaxing and epic music parts. Finally, we have trained a classifier using Support Vector Machines to automatically recognize and generate emotional labels for a music part. Accuracy for recognizing each label has been calculated; where the results show that epic music can be recognized more accurately (77.4%), comparing to the other types of music. |
| Tasks | |
| Published | 2017-09-17 |
| URL | http://arxiv.org/abs/1709.05684v1 |
| http://arxiv.org/pdf/1709.05684v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-categorical-approach-for-recognizing |
| Repo | |
| Framework | |
Lensless computational imaging through deep learning
| Title | Lensless computational imaging through deep learning |
| Authors | Ayan Sinha, Justin Lee, Shuai Li, George Barbastathis |
| Abstract | Deep learning has been proven to yield reliably generalizable answers to numerous classification and decision tasks. Here, we demonstrate for the first time, to our knowledge, that deep neural networks (DNNs) can be trained to solve inverse problems in computational imaging. We experimentally demonstrate a lens-less imaging system where a DNN was trained to recover a phase object given a raw intensity image recorded some distance away. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.08516v2 |
| http://arxiv.org/pdf/1702.08516v2.pdf | |
| PWC | https://paperswithcode.com/paper/lensless-computational-imaging-through-deep |
| Repo | |
| Framework | |
Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks
| Title | Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks |
| Authors | Lei Bi, Jinman Kim, Euijoon Ahn, Dagan Feng |
| Abstract | Malignant melanoma has one of the most rapidly increasing incidences in the world and has a considerable mortality rate. Early diagnosis is particularly important since melanoma can be cured with prompt excision. Dermoscopy images play an important role in the non-invasive early detection of melanoma [1]. However, melanoma detection using human vision alone can be subjective, inaccurate and poorly reproducible even among experienced dermatologists. This is attributed to the challenges in interpreting images with diverse characteristics including lesions of varying sizes and shapes, lesions that may have fuzzy boundaries, different skin colors and the presence of hair [2]. Therefore, the automatic analysis of dermoscopy images is a valuable aid for clinical decision making and for image-based diagnosis to identify diseases such as melanoma [1-4]. Deep residual networks (ResNets) has achieved state-of-the-art results in image classification and detection related problems [5-8]. In this ISIC 2017 skin lesion analysis challenge [9], we propose to exploit the deep ResNets for robust visual features learning and representations. |
| Tasks | Decision Making, Image Classification |
| Published | 2017-03-12 |
| URL | http://arxiv.org/abs/1703.04197v2 |
| http://arxiv.org/pdf/1703.04197v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-skin-lesion-analysis-using-large |
| Repo | |
| Framework | |
Ranking to Learn: Feature Ranking and Selection via Eigenvector Centrality
| Title | Ranking to Learn: Feature Ranking and Selection via Eigenvector Centrality |
| Authors | Giorgio Roffo, Simone Melzi |
| Abstract | In an era where accumulating data is easy and storing it inexpensive, feature selection plays a central role in helping to reduce the high-dimensionality of huge amounts of otherwise meaningless data. In this paper, we propose a graph-based method for feature selection that ranks features by identifying the most important ones into arbitrary set of cues. Mapping the problem on an affinity graph-where features are the nodes-the solution is given by assessing the importance of nodes through some indicators of centrality, in particular, the Eigen-vector Centrality (EC). The gist of EC is to estimate the importance of a feature as a function of the importance of its neighbors. Ranking central nodes individuates candidate features, which turn out to be effective from a classification point of view, as proved by a thoroughly experimental section. Our approach has been tested on 7 diverse datasets from recent literature (e.g., biological data and object recognition, among others), and compared against filter, embedded and wrappers methods. The results are remarkable in terms of accuracy, stability and low execution time. |
| Tasks | Feature Selection, Object Recognition |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05409v1 |
| http://arxiv.org/pdf/1704.05409v1.pdf | |
| PWC | https://paperswithcode.com/paper/ranking-to-learn-feature-ranking-and |
| Repo | |
| Framework | |
