Paper Group ANR 998
Cross-Domain Deep Face Matching for Real Banking Security Systems. Policy Regret in Repeated Games. Sampling Superquadric Point Clouds with Normals. Cuckoo Search: State-of-the-Art and Opportunities. A Self-Adaptive Network For Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Protocols. On Kernel Derivative Approx …
Cross-Domain Deep Face Matching for Real Banking Security Systems
Title | Cross-Domain Deep Face Matching for Real Banking Security Systems |
Authors | Johnatan S. Oliveira, Gustavo B. Souza, Anderson R. Rocha, Flávio E. Deus, Aparecido N. Marana |
Abstract | Ensuring the security of transactions is currently one of the major challenges that banking systems deal with. The usage of face for biometric authentication of users is attracting large investments from banks worldwide due to its convenience and acceptability by people, especially in cross-domain scenarios, in which facial images from ID documents are compared with digital self-portraits (selfies) for the automated opening of new checking accounts, e.g, or financial transactions authorization. Actually, the comparison of selfies and IDs has also been applied in another wide variety of tasks nowadays, such as automated immigration control. The major difficulty in such process consists in attenuating the differences between the facial images compared given their different domains. In this work, besides of collecting a large cross-domain face dataset, with 27,002 real facial images of selfies and ID documents (13,501 subjects) captured from the databases of the major public Brazilian bank, we propose a novel architecture for such cross-domain matching problem based on deep features extracted by two well-referenced Convolutional Neural Networks (CNN). Results obtained on the dataset collected, called FaceBank, with accuracy rates higher than 93%, demonstrate the robustness of the proposed approach to the cross-domain face matching problem and its feasible application in real banking security systems. |
Tasks | |
Published | 2018-06-20 |
URL | https://arxiv.org/abs/1806.07644v2 |
https://arxiv.org/pdf/1806.07644v2.pdf | |
PWC | https://paperswithcode.com/paper/cross-domain-deep-face-matching-for-real |
Repo | |
Framework | |
Policy Regret in Repeated Games
Title | Policy Regret in Repeated Games |
Authors | Raman Arora, Michael Dinitz, Teodor V. Marinov, Mehryar Mohri |
Abstract | The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the notion of policy regret and first show that there are online learning settings in which policy regret and external regret are incompatible: any sequence of play that achieves a favorable regret with respect to one definition must do poorly with respect to the other. We then focus on the game-theoretic setting where the adversary is a self-interested agent. In that setting, we show that external regret and policy regret are not in conflict and, in fact, that a wide class of algorithms can ensure a favorable regret with respect to both definitions, so long as the adversary is also using such an algorithm. We also show that the sequence of play of no-policy regret algorithms converges to a \emph{policy equilibrium}, a new notion of equilibrium that we introduce. Relating this back to external regret, we show that coarse correlated equilibria, which no-external regret players converge to, are a strict subset of policy equilibria. Thus, in game-theoretic settings, every sequence of play with no external regret also admits no policy regret, but the converse does not hold. |
Tasks | |
Published | 2018-11-09 |
URL | https://arxiv.org/abs/1811.04127v2 |
https://arxiv.org/pdf/1811.04127v2.pdf | |
PWC | https://paperswithcode.com/paper/policy-regret-in-repeated-games |
Repo | |
Framework | |
Sampling Superquadric Point Clouds with Normals
Title | Sampling Superquadric Point Clouds with Normals |
Authors | Paulo Ferreira |
Abstract | Superquadrics provide a compact representation of common shapes and have been used both for object/surface modelling in computer graphics and as object-part representation in computer vision and robotics. Superquadrics refer to a family of shapes: here we deal with the superellipsoids and superparaboloids. Due to the strong non-linearities involved in the equations, uniform or close-to-uniform sampling is not attainable through a naive approach of direct sampling from the parametric formulation. This is specially true for more `cubic’ superquadrics (with shape parameters close to $0.1$). We extend a previous solution of 2D close-to-uniform uniform sampling of superellipses to the superellipsoid (3D) case and derive our own for the superparaboloid. Additionally, we are able to provide normals for each sampled point. To the best of our knowledge, this is the first complete approach for close-to-uniform sampling of superellipsoids and superparaboloids in one single framework. We present derivations, pseudocode and qualitative and quantitative results using our code, which is available online. | |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.05176v1 |
http://arxiv.org/pdf/1802.05176v1.pdf | |
PWC | https://paperswithcode.com/paper/sampling-superquadric-point-clouds-with |
Repo | |
Framework | |
Cuckoo Search: State-of-the-Art and Opportunities
Title | Cuckoo Search: State-of-the-Art and Opportunities |
Authors | Xin-She Yang, Suash Deb |
Abstract | Since the development of cuckoo search (CS) by Yang and Deb in 2009, CS has been applied in a diverse range of applications. This paper first outlines the key features of the algorithm and its variants, and then briefly summarizes the state-of-the-art developments in many applications. The opportunities for further research are also identified. |
Tasks | |
Published | 2018-04-22 |
URL | http://arxiv.org/abs/1806.01631v1 |
http://arxiv.org/pdf/1806.01631v1.pdf | |
PWC | https://paperswithcode.com/paper/cuckoo-search-state-of-the-art-and |
Repo | |
Framework | |
A Self-Adaptive Network For Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Protocols
Title | A Self-Adaptive Network For Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Protocols |
Authors | Yushan Feng, Huitong Pan, Craig Meyer, Xue Feng |
Abstract | Deep neural networks (DNN) have shown promises in the lesion segmentation of multiple sclerosis (MS) from multicontrast MRI including T1, T2, proton density (PD) and FLAIR sequences. However, one challenge in deploying such networks into clinical practice is the variability of imaging protocols, which often differ from the training dataset as certain MRI sequences may be unavailable or unusable. Therefore, trained networks need to adapt to practical situations when imaging protocols are different in deployment. In this paper, we propose a DNN-based MS lesion segmentation framework with a novel technique called sequence dropout which can adapt to various combinations of input MRI sequences during deployment and achieve the maximal possible performance from the given input. In addition, with this framework, we studied the quantitative impact of each MRI sequence on the MS lesion segmentation task without training separate networks. Experiments were performed using the IEEE ISBI 2015 Longitudinal MS Lesion Challenge dataset and our method is currently ranked 2nd with a Dice similarity coefficient of 0.684. Furthermore, we showed our network achieved the maximal possible performance when one sequence is unavailable during deployment by comparing with separate networks trained on the corresponding input MRI sequences. In particular, we discovered T1 and PD have minor impact on segmentation performance while FLAIR is the predominant sequence. Experiments with multiple missing sequences were also performed and showed the robustness of our network. |
Tasks | Lesion Segmentation |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07491v1 |
http://arxiv.org/pdf/1811.07491v1.pdf | |
PWC | https://paperswithcode.com/paper/a-self-adaptive-network-for-multiple |
Repo | |
Framework | |
On Kernel Derivative Approximation with Random Fourier Features
Title | On Kernel Derivative Approximation with Random Fourier Features |
Authors | Zoltan Szabo, Bharath K. Sriperumbudur |
Abstract | Random Fourier features (RFF) represent one of the most popular and wide-spread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applications of RFFs, unfortunately, quite little is understood theoretically on their optimality and limitations of their performance. Only recently, precise statistical-computational trade-offs have been established for RFFs in the approximation of kernel values, kernel ridge regression, kernel PCA and SVM classification. Our goal is to spark the investigation of optimality of RFF-based approximations in tasks involving not only function values but derivatives, which naturally lead to optimization problems with kernel derivatives. Particularly, in this paper, we focus on the approximation quality of RFFs for kernel derivatives and prove that the existing finite-sample guarantees can be improved exponentially in terms of the domain where they hold, using recent tools from unbounded empirical process theory. Our result implies that the same approximation guarantee is attainable for kernel derivatives using RFF as achieved for kernel values. |
Tasks | |
Published | 2018-10-11 |
URL | http://arxiv.org/abs/1810.05207v3 |
http://arxiv.org/pdf/1810.05207v3.pdf | |
PWC | https://paperswithcode.com/paper/on-kernel-derivative-approximation-with |
Repo | |
Framework | |
Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
Title | Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation |
Authors | Shahab Aslani, Michael Dayan, Loredana Storelli, Massimo Filippi, Vittorio Murino, Maria A Rocca, Diego Sona |
Abstract | In this paper, we present an automated approach for segmenting multiple sclerosis (MS) lesions from multi-modal brain magnetic resonance images. Our method is based on a deep end-to-end 2D convolutional neural network (CNN) for slice-based segmentation of 3D volumetric data. The proposed CNN includes a multi-branch downsampling path, which enables the network to encode information from multiple modalities separately. Multi-scale feature fusion blocks are proposed to combine feature maps from different modalities at different stages of the network. Then, multi-scale feature upsampling blocks are introduced to upsize combined feature maps to leverage information from lesion shape and location. We trained and tested the proposed model using orthogonal plane orientations of each 3D modality to exploit the contextual information in all directions. The proposed pipeline is evaluated on two different datasets: a private dataset including 37 MS patients and a publicly available dataset known as the ISBI 2015 longitudinal MS lesion segmentation challenge dataset, consisting of 14 MS patients. Considering the ISBI challenge, at the time of submission, our method was amongst the top performing solutions. On the private dataset, using the same array of performance metrics as in the ISBI challenge, the proposed approach shows high improvements in MS lesion segmentation compared with other publicly available tools. |
Tasks | Lesion Segmentation |
Published | 2018-11-07 |
URL | http://arxiv.org/abs/1811.02942v4 |
http://arxiv.org/pdf/1811.02942v4.pdf | |
PWC | https://paperswithcode.com/paper/multi-branch-convolutional-neural-network-for |
Repo | |
Framework | |
Robust event-stream pattern tracking based on correlative filter
Title | Robust event-stream pattern tracking based on correlative filter |
Authors | Hongmin Li, Luping Shi |
Abstract | Object tracking based on retina-inspired and event-based dynamic vision sensor (DVS) is challenging for the noise events, rapid change of event-stream shape, chaos of complex background textures, and occlusion. To address these challenges, this paper presents a robust event-stream pattern tracking method based on correlative filter mechanism. In the proposed method, rate coding is used to encode the event-stream object in each segment. Feature representations from hierarchical convolutional layers of a deep convolutional neural network (CNN) are used to represent the appearance of the rate encoded event-stream object. The results prove that our method not only achieves good tracking performance in many complicated scenes with noise events, complex background textures, occlusion, and intersected trajectories, but also is robust to variable scale, variable pose, and non-rigid deformations. In addition, this correlative filter based event-stream tracking has the advantage of high speed. The proposed approach will promote the potential applications of these event-based vision sensors in self-driving, robots and many other high-speed scenes. |
Tasks | Event-based vision, Object Tracking |
Published | 2018-03-17 |
URL | http://arxiv.org/abs/1803.06490v1 |
http://arxiv.org/pdf/1803.06490v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-event-stream-pattern-tracking-based-on |
Repo | |
Framework | |
ReNN: Rule-embedded Neural Networks
Title | ReNN: Rule-embedded Neural Networks |
Authors | Hu Wang |
Abstract | The artificial neural network shows powerful ability of inference, but it is still criticized for lack of interpretability and prerequisite needs of big dataset. This paper proposes the Rule-embedded Neural Network (ReNN) to overcome the shortages. ReNN first makes local-based inferences to detect local patterns, and then uses rules based on domain knowledge about the local patterns to generate rule-modulated map. After that, ReNN makes global-based inferences that synthesizes the local patterns and the rule-modulated map. To solve the optimization problem caused by rules, we use a two-stage optimization strategy to train the ReNN model. By introducing rules into ReNN, we can strengthen traditional neural networks with long-term dependencies which are difficult to learn with limited empirical dataset, thus improving inference accuracy. The complexity of neural networks can be reduced since long-term dependencies are not modeled with neural connections, and thus the amount of data needed to optimize the neural networks can be reduced. Besides, inferences from ReNN can be analyzed with both local patterns and rules, and thus have better interpretability. In this paper, ReNN has been validated with a time-series detection problem. |
Tasks | Time Series |
Published | 2018-01-30 |
URL | http://arxiv.org/abs/1801.09856v2 |
http://arxiv.org/pdf/1801.09856v2.pdf | |
PWC | https://paperswithcode.com/paper/renn-rule-embedded-neural-networks |
Repo | |
Framework | |
Approximation Schemes for Low-Rank Binary Matrix Approximation Problems
Title | Approximation Schemes for Low-Rank Binary Matrix Approximation Problems |
Authors | Fedor V. Fomin, Petr A. Golovach, Daniel Lokshtanov, Fahad Panolan, Saket Saurabh |
Abstract | We provide a randomized linear time approximation scheme for a generic problem about clustering of binary vectors subject to additional constrains. The new constrained clustering problem encompasses a number of problems and by solving it, we obtain the first linear time-approximation schemes for a number of well-studied fundamental problems concerning clustering of binary vectors and low-rank approximation of binary matrices. Among the problems solvable by our approach are \textsc{Low GF(2)-Rank Approximation}, \textsc{Low Boolean-Rank Approximation}, and various versions of \textsc{Binary Clustering}. For example, for \textsc{Low GF(2)-Rank Approximation} problem, where for an $m\times n$ binary matrix $A$ and integer $r>0$, we seek for a binary matrix $B$ of $GF_2$ rank at most $r$ such that $\ell_0$ norm of matrix $A-B$ is minimum, our algorithm, for any $\epsilon>0$ in time $ f(r,\epsilon)\cdot n\cdot m$, where $f$ is some computable function, outputs a $(1+\epsilon)$-approximate solution with probability at least $(1-\frac{1}{e})$. Our approximation algorithms substantially improve the running times and approximation factors of previous works. We also give (deterministic) PTASes for these problems running in time $n^{f(r)\frac{1}{\epsilon^2}\log \frac{1}{\epsilon}}$, where $f$ is some function depending on the problem. Our algorithm for the constrained clustering problem is based on a novel sampling lemma, which is interesting in its own. |
Tasks | |
Published | 2018-07-18 |
URL | http://arxiv.org/abs/1807.07156v1 |
http://arxiv.org/pdf/1807.07156v1.pdf | |
PWC | https://paperswithcode.com/paper/approximation-schemes-for-low-rank-binary |
Repo | |
Framework | |
SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint
Title | SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint |
Authors | Pavel Ostyakov, Roman Suvorov, Elizaveta Logacheva, Oleg Khomenko, Sergey I. Nikolenko |
Abstract | We present a novel approach to image manipulation and understanding by simultaneously learning to segment object masks, paste objects to another background image, and remove them from original images. For this purpose, we develop a novel generative model for compositional image generation, SEIGAN (Segment-Enhance-Inpaint Generative Adversarial Network), which learns these three operations together in an adversarial architecture with additional cycle consistency losses. To train, SEIGAN needs only bounding box supervision and does not require pairing or ground truth masks. SEIGAN produces better generated images (evaluated by human assessors) than other approaches and produces high-quality segmentation masks, improving over other adversarially trained approaches and getting closer to the results of fully supervised training. |
Tasks | Image Generation |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07630v2 |
http://arxiv.org/pdf/1811.07630v2.pdf | |
PWC | https://paperswithcode.com/paper/seigan-towards-compositional-image-generation |
Repo | |
Framework | |
Extrinsic camera calibration method and its performance evaluation
Title | Extrinsic camera calibration method and its performance evaluation |
Authors | Jacek Komorowski, Przemyslaw Rokita |
Abstract | This paper presents a method for extrinsic camera calibration (estimation of camera rotation and translation matrices) from a sequence of images. It is assumed camera intrinsic matrix and distortion coefficients are known and fixed during the entire sequence. %This allows to decrease a number of pairs of corresponding keypoints between images needed to estimate epipolar geometry compared to uncalibrated case. Performance of the presented method is evaluated on a number of multi-view stereo test datasets. Presented algorithm can be used as a first stage in a dense stereo reconstruction system. |
Tasks | Calibration |
Published | 2018-09-28 |
URL | http://arxiv.org/abs/1809.11073v1 |
http://arxiv.org/pdf/1809.11073v1.pdf | |
PWC | https://paperswithcode.com/paper/extrinsic-camera-calibration-method-and-its |
Repo | |
Framework | |
An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection
Title | An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection |
Authors | Liyan Sun, Jiexiang Wang, Yue Huang, Xinghao Ding, Hayit Greenspan, John Paisley |
Abstract | The identification of lesion within medical image data is necessary for diagnosis, treatment and prognosis. Segmentation and classification approaches are mainly based on supervised learning with well-paired image-level or voxel-level labels. However, labeling the lesion in medical images is laborious requiring highly specialized knowledge. We propose a medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN) to generate a normal-looking medical image based on its abnormal-looking counterpart without the need for paired training data. Unlike typical GANs, whose aim is to generate realistic samples with variations, our more restrictive model aims at producing a normal-looking image corresponding to one containing lesions, and thus requires a special design. Being able to provide a “normal” counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments. In the other aspect, the ANT-GAN model is also capable of producing highly realistic lesion-containing image corresponding to the healthy one, which shows the potential in data augmentation verified in our experiments. |
Tasks | Data Augmentation, Image Generation, Lesion Segmentation |
Published | 2018-10-25 |
URL | http://arxiv.org/abs/1810.10850v2 |
http://arxiv.org/pdf/1810.10850v2.pdf | |
PWC | https://paperswithcode.com/paper/an-adversarial-learning-approach-to-medical |
Repo | |
Framework | |
A Multi-stage Framework with Context Information Fusion Structure for Skin Lesion Segmentation
Title | A Multi-stage Framework with Context Information Fusion Structure for Skin Lesion Segmentation |
Authors | Yujiao Tang, Feng Yang, Shaofeng Yuan, Chang’an Zhan |
Abstract | The computer-aided diagnosis (CAD) systems can highly improve the reliability and efficiency of melanoma recognition. As a crucial step of CAD, skin lesion segmentation has the unsatisfactory accuracy in existing methods due to large variability in lesion appearance and artifacts. In this work, we propose a framework employing multi-stage UNets (MS-UNet) in the auto-context scheme to segment skin lesion accurately end-to-end. We apply two approaches to boost the performance of MS-UNet. First, UNet is coupled with a context information fusion structure (CIFS) to integrate the low-level and context information in the multi-scale feature space. Second, to alleviate the gradient vanishing problem, we use deep supervision mechanism through supervising MS-UNet by minimizing a weighted Jaccard distance loss function. Four out of five commonly used performance metrics, including Jaccard index and Dice coefficient, show that our approach outperforms the state-ofthe-art deep learning based methods on the ISBI 2016 Skin Lesion Challenge dataset. |
Tasks | Lesion Segmentation |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.07075v1 |
http://arxiv.org/pdf/1810.07075v1.pdf | |
PWC | https://paperswithcode.com/paper/a-multi-stage-framework-with-context |
Repo | |
Framework | |
Language Distribution Prediction based on Batch Markov Monte Carlo Simulation with Migration
Title | Language Distribution Prediction based on Batch Markov Monte Carlo Simulation with Migration |
Authors | XingYu Fu, ZiYi Yang, XiuWen Duan |
Abstract | Language spreading is a complex mechanism that involves issues like culture, economics, migration, population etc. In this paper, we propose a set of methods to model the dynamics of the spreading system. To model the randomness of language spreading, we propose the Batch Markov Monte Carlo Simulation with Migration(BMMCSM) algorithm, in which each agent is treated as a language stack. The agent learns languages and migrates based on the proposed Batch Markov Property according to the transition matrix T and migration matrix M. Since population plays a crucial role in language spreading, we also introduce the Mortality and Fertility Mechanism, which controls the birth and death of the simulated agents, into the BMMCSM algorithm. The simulation results of BMMCSM show that the numerical and geographic distribution of languages varies across the time. The change of distribution fits the world cultural and economic development trend. Next, when we construct Matrix T, there are some entries of T can be directly calculated from historical statistics while some entries of T is unknown. Thus, the key to the success of the BMMCSM lies in the accurate estimation of transition matrix T by estimating the unknown entries of T under the supervision of the known entries. To achieve this, we first construct a 20 by 20 by 5 factor tensor X to characterize each entry of T. Then we train a Random Forest Regressor on the known entries of T and use the trained regressor to predict the unknown entries. The reason why we choose Random Forest(RF) is that, compared to Single Decision Tree, it conquers the problem of over fitting and the Shapiro test also suggests that the residual of RF subjects to the Normal distribution. |
Tasks | |
Published | 2018-02-26 |
URL | http://arxiv.org/abs/1802.09189v1 |
http://arxiv.org/pdf/1802.09189v1.pdf | |
PWC | https://paperswithcode.com/paper/language-distribution-prediction-based-on |
Repo | |
Framework | |