Paper Group ANR 428
Distribution-Preserving k-Anonymity. Persistent homology machine learning for fingerprint classification. Computing LPMLN Using ASP and MLN Solvers. Curriculum Learning for Multi-Task Classification of Visual Attributes. Winqi: A System for 6D Localization and SLAM Augmentation Using Wideangle Optics and Coded Light Beacons. Art of singular vectors …
Distribution-Preserving k-Anonymity
| Title | Distribution-Preserving k-Anonymity |
| Authors | Dennis Wei, Karthikeyan Natesan Ramamurthy, Kush R. Varshney |
| Abstract | Preserving the privacy of individuals by protecting their sensitive attributes is an important consideration during microdata release. However, it is equally important to preserve the quality or utility of the data for at least some targeted workloads. We propose a novel framework for privacy preservation based on the k-anonymity model that is ideally suited for workloads that require preserving the probability distribution of the quasi-identifier variables in the data. Our framework combines the principles of distribution-preserving quantization and k-member clustering, and we specialize it to two variants that respectively use intra-cluster and Gaussian dithering of cluster centers to achieve distribution preservation. We perform theoretical analysis of the proposed schemes in terms of distribution preservation, and describe their utility in workloads such as covariate shift and transfer learning where such a property is necessary. Using extensive experiments on real-world Medical Expenditure Panel Survey data, we demonstrate the merits of our algorithms over standard k-anonymization for a hallmark health care application where an insurance company wishes to understand the risk in entering a new market. Furthermore, by empirically quantifying the reidentification risk, we also show that the proposed approaches indeed maintain k-anonymity. |
| Tasks | Quantization, Transfer Learning |
| Published | 2017-11-05 |
| URL | http://arxiv.org/abs/1711.01514v1 |
| http://arxiv.org/pdf/1711.01514v1.pdf | |
| PWC | https://paperswithcode.com/paper/distribution-preserving-k-anonymity |
| Repo | |
| Framework | |
Persistent homology machine learning for fingerprint classification
| Title | Persistent homology machine learning for fingerprint classification |
| Authors | Noah Giansiracusa, Robert Giansiracusa, Chul Moon |
| Abstract | The fingerprint classification problem is to sort fingerprints into pre-determined groups, such as arch, loop, and whorl. It was asserted in the literature that minutiae points, which are commonly used for fingerprint matching, are not useful for classification. We show that, to the contrary, near state-of-the-art classification accuracy rates can be achieved when applying topological data analysis (TDA) to 3-dimensional point clouds of oriented minutiae points. We also apply TDA to fingerprint ink-roll images, which yields a lower accuracy rate but still shows promise, particularly since the only preprocessing is cropping; moreover, combining the two approaches outperforms each one individually. These methods use supervised learning applied to persistent homology and allow us to explore feature selection on barcodes, an important topic at the interface between TDA and machine learning. We test our classification algorithms on the NIST fingerprint database SD-27. |
| Tasks | Feature Selection, Topological Data Analysis |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.09158v1 |
| http://arxiv.org/pdf/1711.09158v1.pdf | |
| PWC | https://paperswithcode.com/paper/persistent-homology-machine-learning-for |
| Repo | |
| Framework | |
Computing LPMLN Using ASP and MLN Solvers
| Title | Computing LPMLN Using ASP and MLN Solvers |
| Authors | Joohyung Lee, Samidh Talsania, Yi Wang |
| Abstract | LPMLN is a recent addition to probabilistic logic programming languages. Its main idea is to overcome the rigid nature of the stable model semantics by assigning a weight to each rule in a way similar to Markov Logic is defined. We present two implementations of LPMLN, $\text{LPMLN2ASP}$ and $\text{LPMLN2MLN}$. System $\text{LPMLN2ASP}$ translates LPMLN programs into the input language of answer set solver $\text{CLINGO}$, and using weak constraints and stable model enumeration, it can compute most probable stable models as well as exact conditional and marginal probabilities. System $\text{LPMLN2MLN}$ translates LPMLN programs into the input language of Markov Logic solvers, such as $\text{ALCHEMY}$, $\text{TUFFY}$, and $\text{ROCKIT}$, and allows for performing approximate probabilistic inference on LPMLN programs. We also demonstrate the usefulness of the LPMLN systems for computing other languages, such as ProbLog and Pearl’s Causal Models, that are shown to be translatable into LPMLN. (Under consideration for acceptance in TPLP) |
| Tasks | |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.06325v3 |
| http://arxiv.org/pdf/1707.06325v3.pdf | |
| PWC | https://paperswithcode.com/paper/computing-lpmln-using-asp-and-mln-solvers |
| Repo | |
| Framework | |
Curriculum Learning for Multi-Task Classification of Visual Attributes
| Title | Curriculum Learning for Multi-Task Classification of Visual Attributes |
| Authors | Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou, Ioannis A. Kakadiaris |
| Abstract | Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped based on their correlation so that two groups of strongly and weakly correlated tasks are formed. The two groups of tasks are learned in a curriculum learning setup by transferring the acquired knowledge from the strongly to the weakly correlated. The learning process within each group though, is performed in a multi-task classification setup. The proposed method learns better and converges faster than learning all the tasks in a typical multi-task learning paradigm. We demonstrate the effectiveness of our approach on the publicly available, SoBiR, VIPeR and PETA datasets and report state-of-the-art results across the board. |
| Tasks | Multi-Task Learning |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.08728v1 |
| http://arxiv.org/pdf/1708.08728v1.pdf | |
| PWC | https://paperswithcode.com/paper/curriculum-learning-for-multi-task |
| Repo | |
| Framework | |
Winqi: A System for 6D Localization and SLAM Augmentation Using Wideangle Optics and Coded Light Beacons
| Title | Winqi: A System for 6D Localization and SLAM Augmentation Using Wideangle Optics and Coded Light Beacons |
| Authors | Aaron Wetzler, Ron Kimmel |
| Abstract | Simultaneous Localization and Mapping (SLAM) systems use commodity visible/near visible digital sensors coupled with processing units that detect, recognize and track image points in a camera stream. These systems are cheap, fast and make use of readily available camera technologies. However, SLAM systems suffer from issues of drift as well as sensitivity to lighting variation such as shadows and changing brightness. Beaconless SLAM systems will continue to suffer from this inherent drift problem irrespective of the improvements in on-board camera resolution, speed and inertial sensor precision. To cancel out destructive forms of drift, relocalization algorithms are used which use known detected landmarks together with loop closure processes to continually readjust the current location and orientation estimates to match “known” positions. However this is inherently problematic because these landmarks themselves may have been recorded with errors and they may also change under different illumination conditions. In this note we describe a unique beacon light coding system which is robust to desynchronized clock bit drift. The described beacons and codes are designed to be used in industrial or consumer environments for full standalone 6dof tracking or as known error free landmarks in a SLAM pipeline. |
| Tasks | Simultaneous Localization and Mapping |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05625v2 |
| http://arxiv.org/pdf/1708.05625v2.pdf | |
| PWC | https://paperswithcode.com/paper/winqi-a-system-for-6d-localization-and-slam |
| Repo | |
| Framework | |
Art of singular vectors and universal adversarial perturbations
| Title | Art of singular vectors and universal adversarial perturbations |
| Authors | Valentin Khrulkov, Ivan Oseledets |
| Abstract | Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has been attracting a lot of attention in recent studies. It has been shown that for many state of the art DNNs performing image classification there exist universal adversarial perturbations — image-agnostic perturbations mere addition of which to natural images with high probability leads to their misclassification. In this work we propose a new algorithm for constructing such universal perturbations. Our approach is based on computing the so-called $(p, q)$-singular vectors of the Jacobian matrices of hidden layers of a network. Resulting perturbations present interesting visual patterns, and by using only 64 images we were able to construct universal perturbations with more than 60 % fooling rate on the dataset consisting of 50000 images. We also investigate a correlation between the maximal singular value of the Jacobian matrix and the fooling rate of the corresponding singular vector, and show that the constructed perturbations generalize across networks. |
| Tasks | Image Classification |
| Published | 2017-09-11 |
| URL | http://arxiv.org/abs/1709.03582v2 |
| http://arxiv.org/pdf/1709.03582v2.pdf | |
| PWC | https://paperswithcode.com/paper/art-of-singular-vectors-and-universal |
| Repo | |
| Framework | |
DTATG: An Automatic Title Generator based on Dependency Trees
| Title | DTATG: An Automatic Title Generator based on Dependency Trees |
| Authors | Liqun Shao, Jie Wang |
| Abstract | We study automatic title generation for a given block of text and present a method called DTATG to generate titles. DTATG first extracts a small number of central sentences that convey the main meanings of the text and are in a suitable structure for conversion into a title. DTATG then constructs a dependency tree for each of these sentences and removes certain branches using a Dependency Tree Compression Model we devise. We also devise a title test to determine if a sentence can be used as a title. If a trimmed sentence passes the title test, then it becomes a title candidate. DTATG selects the title candidate with the highest ranking score as the final title. Our experiments showed that DTATG can generate adequate titles. We also showed that DTATG-generated titles have higher F1 scores than those generated by the previous methods. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://arxiv.org/abs/1710.00286v1 |
| http://arxiv.org/pdf/1710.00286v1.pdf | |
| PWC | https://paperswithcode.com/paper/dtatg-an-automatic-title-generator-based-on |
| Repo | |
| Framework | |
Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes
| Title | Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes |
| Authors | Tomoharu Iwata, Zoubin Ghahramani |
| Abstract | We propose a simple method that combines neural networks and Gaussian processes. The proposed method can estimate the uncertainty of outputs and flexibly adjust target functions where training data exist, which are advantages of Gaussian processes. The proposed method can also achieve high generalization performance for unseen input configurations, which is an advantage of neural networks. With the proposed method, neural networks are used for the mean functions of Gaussian processes. We present a scalable stochastic inference procedure, where sparse Gaussian processes are inferred by stochastic variational inference, and the parameters of neural networks and kernels are estimated by stochastic gradient descent methods, simultaneously. We use two real-world spatio-temporal data sets to demonstrate experimentally that the proposed method achieves better uncertainty estimation and generalization performance than neural networks and Gaussian processes. |
| Tasks | Gaussian Processes |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.05922v1 |
| http://arxiv.org/pdf/1707.05922v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-output-uncertainty-estimation-and |
| Repo | |
| Framework | |
Privacy Preserving Identification Using Sparse Approximation with Ambiguization
| Title | Privacy Preserving Identification Using Sparse Approximation with Ambiguization |
| Authors | Behrooz Razeghi, Slava Voloshynovskiy, Dimche Kostadinov, Olga Taran |
| Abstract | In this paper, we consider a privacy preserving encoding framework for identification applications covering biometrics, physical object security and the Internet of Things (IoT). The proposed framework is based on a sparsifying transform, which consists of a trained linear map, an element-wise nonlinearity, and privacy amplification. The sparsifying transform and privacy amplification are not symmetric for the data owner and data user. We demonstrate that the proposed approach is closely related to sparse ternary codes (STC), a recent information-theoretic concept proposed for fast approximate nearest neighbor (ANN) search in high dimensional feature spaces that being machine learning in nature also offers significant benefits in comparison to sparse approximation and binary embedding approaches. We demonstrate that the privacy of the database outsourced to a server as well as the privacy of the data user are preserved at a low computational cost, storage and communication burdens. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10297v1 |
| http://arxiv.org/pdf/1709.10297v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-identification-using |
| Repo | |
| Framework | |
StyleBank: An Explicit Representation for Neural Image Style Transfer
| Title | StyleBank: An Explicit Representation for Neural Image Style Transfer |
| Authors | Dongdong Chen, Lu Yuan, Jing Liao, Nenghai Yu, Gang Hua |
| Abstract | We propose StyleBank, which is composed of multiple convolution filter banks and each filter bank explicitly represents one style, for neural image style transfer. To transfer an image to a specific style, the corresponding filter bank is operated on top of the intermediate feature embedding produced by a single auto-encoder. The StyleBank and the auto-encoder are jointly learnt, where the learning is conducted in such a way that the auto-encoder does not encode any style information thanks to the flexibility introduced by the explicit filter bank representation. It also enables us to conduct incremental learning to add a new image style by learning a new filter bank while holding the auto-encoder fixed. The explicit style representation along with the flexible network design enables us to fuse styles at not only the image level, but also the region level. Our method is the first style transfer network that links back to traditional texton mapping methods, and hence provides new understanding on neural style transfer. Our method is easy to train, runs in real-time, and produces results that qualitatively better or at least comparable to existing methods. |
| Tasks | Style Transfer |
| Published | 2017-03-27 |
| URL | http://arxiv.org/abs/1703.09210v2 |
| http://arxiv.org/pdf/1703.09210v2.pdf | |
| PWC | https://paperswithcode.com/paper/stylebank-an-explicit-representation-for |
| Repo | |
| Framework | |
Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging
| Title | Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging |
| Authors | Steven McDonagh, Benjamin Hou, Konstantinos Kamnitsas, Ozan Oktay, Amir Alansary, Mary Rutherford, Jo V. Hajnal, Bernhard Kainz |
| Abstract | 3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast but low-resolution image acquisition and highly detailed but slow image acquisition. Fast imaging is required for targets that move to avoid motion artefacts. This is in particular difficult for fetal MRI. Spatially independent upsampling techniques, which are the state-of-the-art to address this problem, are error prone and disregard contextual information. In this paper we propose a context-sensitive upsampling method based on a residual convolutional neural network model that learns organ specific appearance and adopts semantically to input data allowing for the generation of high resolution images with sharp edges and fine scale detail. By making contextual decisions about appearance and shape, present in different parts of an image, we gain a maximum of structural detail at a similar contrast as provided by high-resolution data. We experiment on $145$ fetal scans and show that our approach yields an increased PSNR of $1.25$ $dB$ when applied to under-sampled fetal data \emph{cf.} baseline upsampling. Furthermore, our method yields an increased PSNR of $1.73$ $dB$ when utilizing under-sampled fetal data to perform brain volume reconstruction on motion corrupted captured data. |
| Tasks | Super-Resolution |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1703.00035v3 |
| http://arxiv.org/pdf/1703.00035v3.pdf | |
| PWC | https://paperswithcode.com/paper/context-sensitive-super-resolution-for-fast |
| Repo | |
| Framework | |
Efficient Licence Plate Detection By Unique Edge Detection Algorithm and Smarter Interpretation Through IoT
| Title | Efficient Licence Plate Detection By Unique Edge Detection Algorithm and Smarter Interpretation Through IoT |
| Authors | Tejas K, Ashok Reddy K, Pradeep Reddy D, Rajesh Kumar M |
| Abstract | Vehicles play a vital role in modern day transportation systems. Number plate provides a standard means of identification for any vehicle. To serve this purpose, automatic licence plate recognition system was developed. This consisted of four major steps: Pre-processing of the obtained image, extraction of licence plate region, segmentation and character recognition. In earlier research, direct application of Sobel edge detection algorithm or applying threshold were used as key steps to extract the licence plate region, which does not produce effective results when the captured image is subjected to the high intensity of light. The use of morphological operations causes deformity in the characters during segmentation. We propose a novel algorithm to tackle the mentioned issues through a unique edge detection algorithm. It is also a tedious task to create and update the database of required vehicles frequently. This problem is solved by the use of Internet of things(IOT) where an online database can be created and updated from any module instantly. Also, through IoT, we connect all the cameras in a geographical area to one server to create a universal eye which drastically increases the probability of tracing a vehicle over having manual database attached to each camera for identification purpose. |
| Tasks | Edge Detection |
| Published | 2017-10-28 |
| URL | http://arxiv.org/abs/1710.10418v1 |
| http://arxiv.org/pdf/1710.10418v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-licence-plate-detection-by-unique |
| Repo | |
| Framework | |
Differentially Private Regression for Discrete-Time Survival Analysis
| Title | Differentially Private Regression for Discrete-Time Survival Analysis |
| Authors | Thông T. Nguyên, Siu Cheung Hui |
| Abstract | In survival analysis, regression models are used to understand the effects of explanatory variables (e.g., age, sex, weight, etc.) to the survival probability. However, for sensitive survival data such as medical data, there are serious concerns about the privacy of individuals in the data set when medical data is used to fit the regression models. The closest work addressing such privacy concerns is the work on Cox regression which linearly projects the original data to a lower dimensional space. However, the weakness of this approach is that there is no formal privacy guarantee for such projection. In this work, we aim to propose solutions for the regression problem in survival analysis with the protection of differential privacy which is a golden standard of privacy protection in data privacy research. To this end, we extend the Output Perturbation and Objective Perturbation approaches which are originally proposed to protect differential privacy for the Empirical Risk Minimization (ERM) problems. In addition, we also propose a novel sampling approach based on the Markov Chain Monte Carlo (MCMC) method to practically guarantee differential privacy with better accuracy. We show that our proposed approaches achieve good accuracy as compared to the non-private results while guaranteeing differential privacy for individuals in the private data set. |
| Tasks | Survival Analysis |
| Published | 2017-08-24 |
| URL | http://arxiv.org/abs/1708.07436v2 |
| http://arxiv.org/pdf/1708.07436v2.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-regression-for |
| Repo | |
| Framework | |
Proceedings of the 12th Workshop on User Interfaces for Theorem Provers
| Title | Proceedings of the 12th Workshop on User Interfaces for Theorem Provers |
| Authors | Serge Autexier, Pedro Quaresma |
| Abstract | The UITP workshop series brings together researchers interested in designing, developing and evaluating user interfaces for automated reasoning tools, such as interactive proof assistants, automated theorem provers, model finders, tools for formal methods, and tools for visualising and manipulating logical formulas and proofs. The twelth edition of UITP took place in Coimbra, Portugal, and was part of the International Joint Conference on Automated Reasoning (IJCAR’16). The workshop consisted of an invited talk, six presentations of submitted papers and lively hands-on session for reasoning tools and their user-interface. These post-proceedings contain four contributed papers accepted for publication after a second round of reviewing after the workshop as well as the invited paper. |
| Tasks | |
| Published | 2017-01-24 |
| URL | http://arxiv.org/abs/1701.06745v1 |
| http://arxiv.org/pdf/1701.06745v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-12th-workshop-on-user |
| Repo | |
| Framework | |
Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks
| Title | Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks |
| Authors | Anh Nguyen, Dimitrios Kanoulas, Luca Muratore, Darwin G. Caldwell, Nikos G. Tsagarakis |
| Abstract | We present a new method to translate videos to commands for robotic manipulation using Deep Recurrent Neural Networks (RNN). Our framework first extracts deep features from the input video frames with a deep Convolutional Neural Networks (CNN). Two RNN layers with an encoder-decoder architecture are then used to encode the visual features and sequentially generate the output words as the command. We demonstrate that the translation accuracy can be improved by allowing a smooth transaction between two RNN layers and using the state-of-the-art feature extractor. The experimental results on our new challenging dataset show that our approach outperforms recent methods by a fair margin. Furthermore, we combine the proposed translation module with the vision and planning system to let a robot perform various manipulation tasks. Finally, we demonstrate the effectiveness of our framework on a full-size humanoid robot WALK-MAN. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://arxiv.org/abs/1710.00290v1 |
| http://arxiv.org/pdf/1710.00290v1.pdf | |
| PWC | https://paperswithcode.com/paper/translating-videos-to-commands-for-robotic |
| Repo | |
| Framework | |
