May 6, 2019

3172 words 15 mins read

Paper Group ANR 378

Adaptive Local Window for Level Set Segmentation of CT and MRI Liver Lesions. Scalable Semi-Supervised Learning over Networks using Nonsmooth Convex Optimization. Mean Absolute Percentage Error for regression models. Warm Starting Bayesian Optimization. Encoding Cryptographic Functions to SAT Using Transalg System. TripleSpin - a generic compact pa …

Adaptive Local Window for Level Set Segmentation of CT and MRI Liver Lesions


Title	Adaptive Local Window for Level Set Segmentation of CT and MRI Liver Lesions
Authors	Assaf Hoogi, Christopher F. Beaulieu, Guilherme M. Cunha, Elhamy Heba, Claude B. Sirlin, Sandy Napel, Daniel L. Rubin
Abstract	We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those images were obtained by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compare our method to a global level set segmentation and to local framework that uses predefined fixed-size square windows. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25+- 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p < 0.001).
Tasks
Published	2016-06-12
URL	http://arxiv.org/abs/1606.03765v1
PDF	http://arxiv.org/pdf/1606.03765v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-local-window-for-level-set
Repo
Framework

Scalable Semi-Supervised Learning over Networks using Nonsmooth Convex Optimization


Title	Scalable Semi-Supervised Learning over Networks using Nonsmooth Convex Optimization
Authors	Alexander Jung, Alfred O. Hero III, Alexandru Mara, Sabeur Aridhi
Abstract	We propose a scalable method for semi-supervised (transductive) learning from massive network-structured datasets. Our approach to semi-supervised learning is based on representing the underlying hypothesis as a graph signal with small total variation. Requiring a small total variation of the graph signal representing the underlying hypothesis corresponds to the central smoothness assumption that forms the basis for semi-supervised learning, i.e., input points forming clusters have similar output values or labels. We formulate the learning problem as a nonsmooth convex optimization problem which we solve by appealing to Nesterovs optimal first-order method for nonsmooth optimization. We also provide a message passing formulation of the learning method which allows for a highly scalable implementation in big data frameworks.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00714v1
PDF	http://arxiv.org/pdf/1611.00714v1.pdf
PWC	https://paperswithcode.com/paper/scalable-semi-supervised-learning-over
Repo
Framework

Mean Absolute Percentage Error for regression models


Title	Mean Absolute Percentage Error for regression models
Authors	Arnaud De Myttenaere, Boris Golden, Bénédicte Le Grand, Fabrice Rossi
Abstract	We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We prove the existence of an optimal MAPE model and we show the universal consistency of Empirical Risk Minimization based on the MAPE. We also show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression, and we apply this weighting strategy to kernel regression. The behavior of the MAPE kernel regression is illustrated on simulated data.
Tasks
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02541v2
PDF	http://arxiv.org/pdf/1605.02541v2.pdf
PWC	https://paperswithcode.com/paper/mean-absolute-percentage-error-for-regression
Repo
Framework

Warm Starting Bayesian Optimization


Title	Warm Starting Bayesian Optimization
Authors	Matthias Poloczek, Jialei Wang, Peter I. Frazier
Abstract	We develop a framework for warm-starting Bayesian optimization, that reduces the solution time required to solve an optimization problem that is one in a sequence of related problems. This is useful when optimizing the output of a stochastic simulator that fails to provide derivative information, for which Bayesian optimization methods are well-suited. Solving sequences of related optimization problems arises when making several business decisions using one optimization model and input data collected over different time periods or markets. While many gradient-based methods can be warm started by initiating optimization at the solution to the previous problem, this warm start approach does not apply to Bayesian optimization methods, which carry a full metamodel of the objective function from iteration to iteration. Our approach builds a joint statistical model of the entire collection of related objective functions, and uses a value of information calculation to recommend points to evaluate.
Tasks
Published	2016-08-11
URL	http://arxiv.org/abs/1608.03585v1
PDF	http://arxiv.org/pdf/1608.03585v1.pdf
PWC	https://paperswithcode.com/paper/warm-starting-bayesian-optimization
Repo
Framework

Encoding Cryptographic Functions to SAT Using Transalg System


Title	Encoding Cryptographic Functions to SAT Using Transalg System
Authors	Ilya Otpuschennikov, Alexander Semenov, Irina Gribanova, Oleg Zaikin, Stepan Kochemazov
Abstract	In this paper we propose the technology for constructing propositional encodings of discrete functions. It is aimed at solving inversion problems of considered functions using state-of-the-art SAT solvers. We implemented this technology in the form of the software system called Transalg, and used it to construct SAT encodings for a number of cryptanalysis problems. By applying SAT solvers to these encodings we managed to invert several cryptographic functions. In particular, we used the SAT encodings produced by Transalg to construct the family of two-block MD5 collisions in which the first 10 bytes are zeros. Also we used Transalg encoding for the widely known A5/1 keystream generator to solve several dozen of its cryptanalysis instances in a distributed computing environment. In the paper we compare in detail the functionality of Transalg with that of similar software systems.
Tasks	Cryptanalysis
Published	2016-07-04
URL	http://arxiv.org/abs/1607.00888v1
PDF	http://arxiv.org/pdf/1607.00888v1.pdf
PWC	https://paperswithcode.com/paper/encoding-cryptographic-functions-to-sat-using
Repo
Framework

TripleSpin - a generic compact paradigm for fast machine learning computations


Title	TripleSpin - a generic compact paradigm for fast machine learning computations
Authors	Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, Anne Morvan, Tamas Sarlos, Jamal Atif
Abstract	We present a generic compact computational framework relying on structured random matrices that can be applied to speed up several machine learning algorithms with almost no loss of accuracy. The applications include new fast LSH-based algorithms, efficient kernel computations via random feature maps, convex optimization algorithms, quantization techniques and many more. Certain models of the presented paradigm are even more compressible since they apply only bit matrices. This makes them suitable for deploying on mobile devices. All our findings come with strong theoretical guarantees. In particular, as a byproduct of the presented techniques and by using relatively new Berry-Esseen-type CLT for random vectors, we give the first theoretical guarantees for one of the most efficient existing LSH algorithms based on the $\textbf{HD}{3}\textbf{HD}{2}\textbf{HD}_{1}$ structured matrix (“Practical and Optimal LSH for Angular Distance”). These guarantees as well as theoretical results for other aforementioned applications follow from the same general theoretical principle that we present in the paper. Our structured family contains as special cases all previously considered structured schemes, including the recently introduced $P$-model. Experimental evaluation confirms the accuracy and efficiency of TripleSpin matrices.
Tasks	Quantization
Published	2016-05-29
URL	http://arxiv.org/abs/1605.09046v2
PDF	http://arxiv.org/pdf/1605.09046v2.pdf
PWC	https://paperswithcode.com/paper/triplespin-a-generic-compact-paradigm-for
Repo
Framework

Sharper Bounds for Regularized Data Fitting


Title	Sharper Bounds for Regularized Data Fitting
Authors	Haim Avron, Kenneth L. Clarkson, David P. Woodruff
Abstract	We study matrix sketching methods for regularized variants of linear regression, low rank approximation, and canonical correlation analysis. Our main focus is on sketching techniques which preserve the objective function value for regularized problems, which is an area that has remained largely unexplored. We study regularization both in a fairly broad setting, and in the specific context of the popular and widely used technique of ridge regularization; for the latter, as applied to each of these problems, we show algorithmic resource bounds in which the {\em statistical dimension} appears in places where in previous bounds the rank would appear. The statistical dimension is always smaller than the rank, and decreases as the amount of regularization increases. In particular, for the ridge low-rank approximation problem $\min_{Y,X} \lVert YX - A \rVert_F^2 + \lambda \lVert Y\rVert_F^2 + \lambda\lVert X \rVert_F^2$, where $Y\in\mathbb{R}^{n\times k}$ and $X\in\mathbb{R}^{k\times d}$, we give an approximation algorithm needing [ O(\mathtt{nnz}(A)) + \tilde{O}((n+d)\varepsilon^{-1}k \min{k, \varepsilon^{-1}\mathtt{sd}_\lambda(Y^)})+ \mathtt{poly}(\mathtt{sd}_\lambda(Y^) \varepsilon^{-1}) ] time, where $s_{\lambda}(Y^)\le k$ is the statistical dimension of $Y^$, $Y^*$ is an optimal $Y$, $\varepsilon$ is an error parameter, and $\mathtt{nnz}(A)$ is the number of nonzero entries of $A$.This is faster than prior work, even when $\lambda=0$. We also study regularization in a much more general setting. For example, we obtain sketching-based algorithms for the low-rank approximation problem $\min_{X,Y} \lVert YX - A \rVert_F^2 + f(Y,X)$ where $f(\cdot,\cdot)$ is a regularizing function satisfying some very general conditions (chiefly, invariance under orthogonal transformations).
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03225v2
PDF	http://arxiv.org/pdf/1611.03225v2.pdf
PWC	https://paperswithcode.com/paper/sharper-bounds-for-regularized-data-fitting
Repo
Framework

Crowd Counting by Adapting Convolutional Neural Networks with Side Information


Title	Crowd Counting by Adapting Convolutional Neural Networks with Side Information
Authors	Di Kang, Debarun Dhar, Antoni B. Chan
Abstract	Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and scale of people in the scene. While side information has been shown to be useful for counting systems using traditional hand-crafted features, it has not been fully utilized in counting systems based on deep learning. In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt to the current scene context via the side information. In particular, we model the filter weights as a low-dimensional manifold, parametrized by the side information, within the high-dimensional space of filter weights. With the help of side information and adaptive weights, the ACNN can disentangle the variations related to the side information, and extract discriminative features related to the current context. Since existing crowd counting datasets do not contain ground-truth side information, we collect a new dataset with the ground-truth camera angle and height as the side information. On experiments in crowd counting, the ACNN improves counting accuracy compared to a plain CNN with a similar number of parameters. We also apply ACNN to image deconvolution to show its potential effectiveness on other computer vision applications.
Tasks	Crowd Counting, Image Deconvolution
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06748v1
PDF	http://arxiv.org/pdf/1611.06748v1.pdf
PWC	https://paperswithcode.com/paper/crowd-counting-by-adapting-convolutional
Repo
Framework

An Adaptive Parameter Estimation for Guided Filter based Image Deconvolution


Title	An Adaptive Parameter Estimation for Guided Filter based Image Deconvolution
Authors	Hang Yang, Zhongbo Zhang, Yujing Guan
Abstract	Image deconvolution is still to be a challenging ill-posed problem for recovering a clear image from a given blurry image, when the point spread function is known. Although competitive deconvolution methods are numerically impressive and approach theoretical limits, they are becoming more complex, making analysis, and implementation difficult. Furthermore, accurate estimation of the regularization parameter is not easy for successfully solving image deconvolution problems. In this paper, we develop an effective approach for image restoration based on one explicit image filter - guided filter. By applying the decouple of denoising and deblurring techniques to the deconvolution model, we reduce the optimization complexity and achieve a simple but effective algorithm to automatically compute the parameter in each iteration, which is based on Morozov’s discrepancy principle. Experimental results demonstrate that the proposed algorithm outperforms many state-of-the-art deconvolution methods in terms of both ISNR and visual quality.
Tasks	Deblurring, Denoising, Image Deconvolution, Image Restoration
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01380v1
PDF	http://arxiv.org/pdf/1609.01380v1.pdf
PWC	https://paperswithcode.com/paper/an-adaptive-parameter-estimation-for-guided
Repo
Framework

Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization


Title	Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization
Authors	Sean C. Smithson, Guang Yang, Warren J. Gross, Brett H. Meyer
Abstract	Artificial neural networks have gone through a recent rise in popularity, achieving state-of-the-art results in various fields, including image classification, speech recognition, and automated control. Both the performance and computational complexity of such models are heavily dependant on the design of characteristic hyper-parameters (e.g., number of hidden layers, nodes per layer, or choice of activation functions), which have traditionally been optimized manually. With machine learning penetrating low-power mobile and embedded areas, the need to optimize not only for performance (accuracy), but also for implementation complexity, becomes paramount. In this work, we present a multi-objective design space exploration method that reduces the number of solution networks trained and evaluated through response surface modelling. Given spaces which can easily exceed 1020 solutions, manually designing a near-optimal architecture is unlikely as opportunities to reduce network complexity, while maintaining performance, may be overlooked. This problem is exacerbated by the fact that hyper-parameters which perform well on specific datasets may yield sub-par results on others, and must therefore be designed on a per-application basis. In our work, machine learning is leveraged by training an artificial neural network to predict the performance of future candidate networks. The method is evaluated on the MNIST and CIFAR-10 image datasets, optimizing for both recognition accuracy and computational complexity. Experimental results demonstrate that the proposed method can closely approximate the Pareto-optimal front, while only exploring a small fraction of the design space.
Tasks	Image Classification, Speech Recognition
Published	2016-11-07
URL	http://arxiv.org/abs/1611.02120v1
PDF	http://arxiv.org/pdf/1611.02120v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-designing-neural-networks
Repo
Framework

Road Curb Extraction from Mobile LiDAR Point Clouds


Title	Road Curb Extraction from Mobile LiDAR Point Clouds
Authors	Sheng Xu, Ruisheng Wang, Han Zheng
Abstract	Automatic extraction of road curbs from uneven, unorganized, noisy and massive 3D point clouds is a challenging task. Existing methods often project 3D point clouds onto 2D planes to extract curbs. However, the projection causes loss of 3D information which degrades the performance of the detection. This paper presents a robust, accurate and efficient method to extract road curbs from 3D mobile LiDAR point clouds. Our method consists of two steps: 1) extracting the candidate points of curbs based on the proposed novel energy function and 2) refining the candidate points using the proposed least cost path model. We evaluated our method on a large-scale of residential area (16.7GB, 300 million points) and an urban area (1.07GB, 20 million points) mobile LiDAR point clouds. Results indicate that the proposed method is superior to the state-of-the-art methods in terms of robustness, accuracy and efficiency. The proposed curb extraction method achieved a completeness of 78.62% and a correctness of 83.29%. These experiments demonstrate that the proposed method is a promising solution to extract road curbs from mobile LiDAR point clouds.
Tasks
Published	2016-10-15
URL	http://arxiv.org/abs/1610.04673v2
PDF	http://arxiv.org/pdf/1610.04673v2.pdf
PWC	https://paperswithcode.com/paper/road-curb-extraction-from-mobile-lidar-point
Repo
Framework

Joint Optical Flow and Temporally Consistent Semantic Segmentation


Title	Joint Optical Flow and Temporally Consistent Semantic Segmentation
Authors	Junhwa Hur, Stefan Roth
Abstract	The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems. Consequently, there has been a large amount of research dedicated to semantic segmentation and dense motion estimation. In this paper, we propose a method for jointly estimating optical flow and temporally consistent semantic segmentation, which closely connects these two problem domains and leverages each other. Semantic segmentation provides information on plausible physical motion to its associated pixels, and accurate pixel-level temporal correspondences enhance the accuracy of semantic segmentation in the temporal domain. We demonstrate the benefits of our approach on the KITTI benchmark, where we observe performance gains for flow and segmentation. We achieve state-of-the-art optical flow results, and outperform all published algorithms by a large margin on challenging, but crucial dynamic objects.
Tasks	Motion Estimation, Optical Flow Estimation, Scene Understanding, Semantic Segmentation
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07716v1
PDF	http://arxiv.org/pdf/1607.07716v1.pdf
PWC	https://paperswithcode.com/paper/joint-optical-flow-and-temporally-consistent
Repo
Framework

Joint Embeddings of Hierarchical Categories and Entities


Title	Joint Embeddings of Hierarchical Categories and Entities
Authors	Yuezhang Li, Ronghuo Zheng, Tian Tian, Zhiting Hu, Rahul Iyer, Katia Sycara
Abstract	Due to the lack of structured knowledge applied in learning distributed representation of categories, existing work cannot incorporate category hierarchies into entity information.~We propose a framework that embeds entities and categories into a semantic space by integrating structured knowledge and taxonomy hierarchy from large knowledge bases. The framework allows to compute meaningful semantic relatedness between entities and categories.~Compared with the previous state of the art, our framework can handle both single-word concepts and multiple-word concepts with superior performance in concept categorization and semantic relatedness.
Tasks
Published	2016-05-12
URL	http://arxiv.org/abs/1605.03924v2
PDF	http://arxiv.org/pdf/1605.03924v2.pdf
PWC	https://paperswithcode.com/paper/joint-embeddings-of-hierarchical-categories
Repo
Framework

Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation


Title	Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
Authors	Wadim Kehl, Fausto Milletari, Federico Tombari, Slobodan Ilic, Nassir Navab
Abstract	We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collection of random local patches. During testing, scene patch descriptors are matched against a database of synthetic model view patches and cast 6D object votes which are subsequently filtered to refined hypotheses. We evaluate on three datasets to show that our method generalizes well to previously unseen input data, delivers robust detection results that compete with and surpass the state-of-the-art while being scalable in the number of objects.
Tasks	3D Object Detection, 6D Pose Estimation, 6D Pose Estimation using RGB, Object Detection, Pose Estimation
Published	2016-07-20
URL	http://arxiv.org/abs/1607.06038v1
PDF	http://arxiv.org/pdf/1607.06038v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-of-local-rgb-d-patches-for-3d
Repo
Framework

End-to-End Comparative Attention Networks for Person Re-identification


Title	End-to-End Comparative Attention Networks for Person Re-identification
Authors	Hao Liu, Jiashi Feng, Meibin Qi, Jianguo Jiang, Shuicheng Yan
Abstract	Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance. In this paper, we propose a new soft attention based model, i.e., the end to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on three benchmark person re-identification datasets, including CUHK01, CHUHK03 and Market-1501, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.
Tasks	Person Re-Identification
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04404v2
PDF	http://arxiv.org/pdf/1606.04404v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-comparative-attention-networks-for
Repo
Framework