Paper Group ANR 258
IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate. A clustering approach to heterogeneous change detection. GapTV: Accurate and Interpretable Low-Dimensional Regression and Classification. SORT: Second-Order Response Transform for Visual Recognition. How Intelligent is your Intelligent Robot?. Plug-and-Play Unplugged: …
IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate
| Title | IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate |
| Authors | Aryan Mokhtari, Mark Eisen, Alejandro Ribeiro |
| Abstract | The problem of minimizing an objective that can be written as the sum of a set of $n$ smooth and strongly convex functions is considered. The Incremental Quasi-Newton (IQN) method proposed here belongs to the family of stochastic and incremental methods that have a cost per iteration independent of $n$. IQN iterations are a stochastic version of BFGS iterations that use memory to reduce the variance of stochastic approximations. The convergence properties of IQN bridge a gap between deterministic and stochastic quasi-Newton methods. Deterministic quasi-Newton methods exploit the possibility of approximating the Newton step using objective gradient differences. They are appealing because they have a smaller computational cost per iteration relative to Newton’s method and achieve a superlinear convergence rate under customary regularity assumptions. Stochastic quasi-Newton methods utilize stochastic gradient differences in lieu of actual gradient differences. This makes their computational cost per iteration independent of the number of objective functions $n$. However, existing stochastic quasi-Newton methods have sublinear or linear convergence at best. IQN is the first stochastic quasi-Newton method proven to converge superlinearly in a local neighborhood of the optimal solution. IQN differs from state-of-the-art incremental quasi-Newton methods in three aspects: (i) The use of aggregated information of variables, gradients, and quasi-Newton Hessian approximation matrices to reduce the noise of gradient and Hessian approximations. (ii) The approximation of each individual function by its Taylor’s expansion in which the linear and quadratic terms are evaluated with respect to the same iterate. (iii) The use of a cyclic scheme to update the functions in lieu of a random selection routine. We use these fundamental properties of IQN to establish its local superlinear convergence rate. |
| Tasks | |
| Published | 2017-02-02 |
| URL | http://arxiv.org/abs/1702.00709v2 |
| http://arxiv.org/pdf/1702.00709v2.pdf | |
| PWC | https://paperswithcode.com/paper/iqn-an-incremental-quasi-newton-method-with |
| Repo | |
| Framework | |
A clustering approach to heterogeneous change detection
| Title | A clustering approach to heterogeneous change detection |
| Authors | Luigi Tommaso Luppino, Stian Normann Anfinsen, Gabriele Moser, Robert Jenssen, Filippo Maria Bianchi, Sebastiano Serpico, Gregoire Mercier |
| Abstract | Change detection in heterogeneous multitemporal satellite images is a challenging and still not much studied topic in remote sensing and earth observation. This paper focuses on comparison of image pairs covering the same geographical area and acquired by two different sensors, one optical radiometer and one synthetic aperture radar, at two different times. We propose a clustering-based technique to detect changes, identified as clusters that split or merge in the different images. To evaluate potentials and limitations of our method, we perform experiments on real data. Preliminary results confirm the relationship between splits and merges of clusters and the occurrence of changes. However, it becomes evident that it is necessary to incorporate prior, ancillary, or application-specific information to improve the interpretation of clustering results and to identify unambiguously the areas of change. |
| Tasks | |
| Published | 2017-02-10 |
| URL | http://arxiv.org/abs/1702.03176v1 |
| http://arxiv.org/pdf/1702.03176v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-clustering-approach-to-heterogeneous-change |
| Repo | |
| Framework | |
GapTV: Accurate and Interpretable Low-Dimensional Regression and Classification
| Title | GapTV: Accurate and Interpretable Low-Dimensional Regression and Classification |
| Authors | Wesley Tansey, James G. Scott |
| Abstract | We consider the problem of estimating a regression function in the common situation where the number of features is small, where interpretability of the model is a high priority, and where simple linear or additive models fail to provide adequate performance. To address this problem, we present GapTV, an approach that is conceptually related both to CART and to the more recent CRISP algorithm, a state-of-the-art alternative method for interpretable nonlinear regression. GapTV divides the feature space into blocks of constant value and fits the value of all blocks jointly via a convex optimization routine. Our method is fully data-adaptive, in that it incorporates highly robust routines for tuning all hyperparameters automatically. We compare our approach against CART and CRISP and demonstrate that GapTV finds a much better trade-off between accuracy and interpretability. |
| Tasks | |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07405v1 |
| http://arxiv.org/pdf/1702.07405v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaptv-accurate-and-interpretable-low |
| Repo | |
| Framework | |
SORT: Second-Order Response Transform for Visual Recognition
| Title | SORT: Second-Order Response Transform for Visual Recognition |
| Authors | Yan Wang, Lingxi Xie, Chenxi Liu, Ya Zhang, Wenjun Zhang, Alan Yuille |
| Abstract | In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its weights based on the current status of the other branch. Moreover, SORT augments the family of transform operations and increases the nonlinearity of the network, making it possible to learn flexible functions to fit the complicated distribution of feature space. SORT can be applied to a wide range of network architectures, including a branched variant of a chain-styled network and a residual network, with very light-weighted modifications. We observe consistent accuracy gain on both small (CIFAR10, CIFAR100 and SVHN) and big (ILSVRC2012) datasets. In addition, SORT is very efficient, as the extra computation overhead is less than 5%. |
| Tasks | |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06993v3 |
| http://arxiv.org/pdf/1703.06993v3.pdf | |
| PWC | https://paperswithcode.com/paper/sort-second-order-response-transform-for |
| Repo | |
| Framework | |
How Intelligent is your Intelligent Robot?
| Title | How Intelligent is your Intelligent Robot? |
| Authors | Alan F. T. Winfield |
| Abstract | How intelligent is robot A compared with robot B? And how intelligent are robots A and B compared with animals (or plants) X and Y? These are both interesting and deeply challenging questions. In this paper we address the question “how intelligent is your intelligent robot?” by proposing that embodied intelligence emerges from the interaction and integration of four different and distinct kinds of intelligence. We then suggest a simple diagrammatic representation on which these kinds of intelligence are shown as four axes in a star diagram. A crude qualitative comparison of the intelligence graphs of animals and robots both exposes and helps to explain the chronic intelligence deficit of intelligent robots. Finally we examine the options for determining numerical values for the four kinds of intelligence in an effort to move toward a quantifiable intelligence vector. |
| Tasks | |
| Published | 2017-12-24 |
| URL | http://arxiv.org/abs/1712.08878v1 |
| http://arxiv.org/pdf/1712.08878v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-intelligent-is-your-intelligent-robot |
| Repo | |
| Framework | |
Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibrium
| Title | Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibrium |
| Authors | Gregery T. Buzzard, Stanley H. Chan, Suhas Sreehari, Charles A. Bouman |
| Abstract | Regularized inversion methods for image reconstruction are used widely due to their tractability and ability to combine complex physical sensor models with useful regularity criteria. Such methods motivated the recently developed Plug-and-Play prior method, which provides a framework to use advanced denoising algorithms as regularizers in inversion. However, the need to formulate regularized inversion as the solution to an optimization problem limits the possible regularity conditions and physical sensor models. In this paper, we introduce Consensus Equilibrium (CE), which generalizes regularized inversion to include a much wider variety of both forward components and prior components without the need for either to be expressed with a cost function. CE is based on the solution of a set of equilibrium equations that balance data fit and regularity. In this framework, the problem of MAP estimation in regularized inversion is replaced by the problem of solving these equilibrium equations, which can be approached in multiple ways. The key contribution of CE is to provide a novel framework for fusing multiple heterogeneous models of physical sensors or models learned from data. We describe the derivation of the CE equations and prove that the solution of the CE equations generalizes the standard MAP estimate under appropriate circumstances. We also discuss algorithms for solving the CE equations, including ADMM with a novel form of preconditioning and Newton’s method. We give examples to illustrate consensus equilibrium and the convergence properties of these algorithms and demonstrate this method on some toy problems and on a denoising example in which we use an array of convolutional neural network denoisers, none of which is tuned to match the noise level in a noisy image but which in consensus can achieve a better result than any of them individually. |
| Tasks | Denoising, Image Reconstruction |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08983v3 |
| http://arxiv.org/pdf/1705.08983v3.pdf | |
| PWC | https://paperswithcode.com/paper/plug-and-play-unplugged-optimization-free |
| Repo | |
| Framework | |
Direct Estimation of Information Divergence Using Nearest Neighbor Ratios
| Title | Direct Estimation of Information Divergence Using Nearest Neighbor Ratios |
| Authors | Morteza Noshad, Kevin R. Moon, Salimeh Yasaei Sekeh, Alfred O. Hero III |
| Abstract | We propose a direct estimation method for R'{e}nyi and f-divergence measures based on a new graph theoretical interpretation. Suppose that we are given two sample sets $X$ and $Y$, respectively with $N$ and $M$ samples, where $\eta:=M/N$ is a constant value. Considering the $k$-nearest neighbor ($k$-NN) graph of $Y$ in the joint data set $(X,Y)$, we show that the average powered ratio of the number of $X$ points to the number of $Y$ points among all $k$-NN points is proportional to R'{e}nyi divergence of $X$ and $Y$ densities. A similar method can also be used to estimate f-divergence measures. We derive bias and variance rates, and show that for the class of $\gamma$-H"{o}lder smooth functions, the estimator achieves the MSE rate of $O(N^{-2\gamma/(\gamma+d)})$. Furthermore, by using a weighted ensemble estimation technique, for density functions with continuous and bounded derivatives of up to the order $d$, and some extra conditions at the support set boundary, we derive an ensemble estimator that achieves the parametric MSE rate of $O(1/N)$. Our estimators are more computationally tractable than other competing estimators, which makes them appealing in many practical applications. |
| Tasks | |
| Published | 2017-02-17 |
| URL | http://arxiv.org/abs/1702.05222v2 |
| http://arxiv.org/pdf/1702.05222v2.pdf | |
| PWC | https://paperswithcode.com/paper/direct-estimation-of-information-divergence |
| Repo | |
| Framework | |
A Deep-Reinforcement Learning Approach for Software-Defined Networking Routing Optimization
| Title | A Deep-Reinforcement Learning Approach for Software-Defined Networking Routing Optimization |
| Authors | Giorgio Stampa, Marta Arias, David Sanchez-Charles, Victor Muntes-Mulero, Albert Cabellos |
| Abstract | In this paper we design and evaluate a Deep-Reinforcement Learning agent that optimizes routing. Our agent adapts automatically to current traffic conditions and proposes tailored configurations that attempt to minimize the network delay. Experiments show very promising performance. Moreover, this approach provides important operational advantages with respect to traditional optimization algorithms. |
| Tasks | |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.07080v1 |
| http://arxiv.org/pdf/1709.07080v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-reinforcement-learning-approach-for |
| Repo | |
| Framework | |
Shape Registration with Directional Data
| Title | Shape Registration with Directional Data |
| Authors | Mairéad Grogan, Rozenn Dahyot |
| Abstract | We propose several cost functions for registration of shapes encoded with Euclidean and/or non-Euclidean information (unit vectors). Our framework is assessed for estimation of both rigid and non-rigid transformations between the target and model shapes corresponding to 2D contours and 3D surfaces. The experimental results obtained confirm that using the combination of a point’s position and unit normal vector in a cost function can enhance the registration results compared to state of the art methods. |
| Tasks | |
| Published | 2017-08-25 |
| URL | http://arxiv.org/abs/1708.07791v2 |
| http://arxiv.org/pdf/1708.07791v2.pdf | |
| PWC | https://paperswithcode.com/paper/shape-registration-with-directional-data |
| Repo | |
| Framework | |
The Ontological Multidimensional Data Model
| Title | The Ontological Multidimensional Data Model |
| Authors | Leopoldo Bertossi, Mostafa Milani |
| Abstract | In this extended abstract we describe, mainly by examples, the main elements of the Ontological Multidimensional Data Model, which considerably extends a relational reconstruction of the multidimensional data model proposed by Hurtado and Mendelzon by means of tuple-generating dependencies, equality-generating dependencies, and negative constraints as found in Datalog+-. We briefly mention some good computational properties of the model. |
| Tasks | |
| Published | 2017-03-10 |
| URL | http://arxiv.org/abs/1703.03524v2 |
| http://arxiv.org/pdf/1703.03524v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-ontological-multidimensional-data-model |
| Repo | |
| Framework | |
Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency
| Title | Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency |
| Authors | Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik |
| Abstract | We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view consistency using a differentiable ray consistency (DRC) term. We show that this formulation can be incorporated in a learning framework to leverage different types of multi-view observations e.g. foreground masks, depth, color images, semantics etc. as supervision for learning single-view 3D prediction. We present empirical analysis of our technique in a controlled setting. We also show that this approach allows us to improve over existing techniques for single-view reconstruction of objects from the PASCAL VOC dataset. |
| Tasks | |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1704.06254v1 |
| http://arxiv.org/pdf/1704.06254v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-supervision-for-single-view |
| Repo | |
| Framework | |
Natural and Effective Obfuscation by Head Inpainting
| Title | Natural and Effective Obfuscation by Head Inpainting |
| Authors | Qianru Sun, Liqian Ma, Seong Joon Oh, Luc Van Gool, Bernt Schiele, Mario Fritz |
| Abstract | As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection. People have largely resorted to blacking out or blurring head regions, but they result in poor user experience while being surprisingly ineffective against state of the art person recognizers. In this work, we propose a novel head inpainting obfuscation technique. Generating a realistic head inpainting in social media photos is challenging because subjects appear in diverse activities and head orientations. We thus split the task into two sub-tasks: (1) facial landmark generation from image context (e.g. body pose) for seamless hypothesis of sensible head pose, and (2) facial landmark conditioned head inpainting. We verify that our inpainting method generates realistic person images, while achieving superior obfuscation performance against automatic person recognizers. |
| Tasks | |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.09001v5 |
| http://arxiv.org/pdf/1711.09001v5.pdf | |
| PWC | https://paperswithcode.com/paper/natural-and-effective-obfuscation-by-head |
| Repo | |
| Framework | |
A New Pseudo-color Technique Based on Intensity Information Protection for Passive Sensor Imagery
| Title | A New Pseudo-color Technique Based on Intensity Information Protection for Passive Sensor Imagery |
| Authors | Mohammad Reza Khosravi, Habib Rostami, Gholam Reza Ahmadi, Suleiman Mansouri, Ahmad Keshavarz |
| Abstract | Remote sensing image processing is so important in geo-sciences. Images which are obtained by different types of sensors might initially be unrecognizable. To make an acceptable visual perception in the images, some pre-processing steps (for removing noises and etc) are preformed which they affect the analysis of images. There are different types of processing according to the types of remote sensing images. The method that we are going to introduce in this paper is to use virtual colors to colorize the gray-scale images of satellite sensors. This approach helps us to have a better analysis on a sample single-band image which has been taken by Landsat-8 (OLI) sensor (as a multi-band sensor with natural color bands, its images’ natural color can be compared to synthetic color by our approach). A good feature of this method is the original image reversibility in order to keep the suitable resolution of output images. |
| Tasks | |
| Published | 2017-04-08 |
| URL | http://arxiv.org/abs/1704.02455v1 |
| http://arxiv.org/pdf/1704.02455v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-pseudo-color-technique-based-on |
| Repo | |
| Framework | |
Arabic Language Sentiment Analysis on Health Services
| Title | Arabic Language Sentiment Analysis on Health Services |
| Authors | Abdulaziz M. Alayba, Vasile Palade, Matthew England, Rahat Iqbal |
| Abstract | The social media network phenomenon leads to a massive amount of valuable data that is available online and easy to access. Many users share images, videos, comments, reviews, news and opinions on different social networks sites, with Twitter being one of the most popular ones. Data collected from Twitter is highly unstructured, and extracting useful information from tweets is a challenging task. Twitter has a huge number of Arabic users who mostly post and write their tweets using the Arabic language. While there has been a lot of research on sentiment analysis in English, the amount of researches and datasets in Arabic language is limited. This paper introduces an Arabic language dataset which is about opinions on health services and has been collected from Twitter. The paper will first detail the process of collecting the data from Twitter and also the process of filtering, pre-processing and annotating the Arabic text in order to build a big sentiment analysis dataset in Arabic. Several Machine Learning algorithms (Naive Bayes, Support Vector Machine and Logistic Regression) alongside Deep and Convolutional Neural Networks were utilized in our experiments of sentiment analysis on our health dataset. |
| Tasks | Sentiment Analysis |
| Published | 2017-02-10 |
| URL | http://arxiv.org/abs/1702.03197v1 |
| http://arxiv.org/pdf/1702.03197v1.pdf | |
| PWC | https://paperswithcode.com/paper/arabic-language-sentiment-analysis-on-health |
| Repo | |
| Framework | |
Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information
| Title | Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information |
| Authors | Trang Tran, Shubham Toshniwal, Mohit Bansal, Kevin Gimpel, Karen Livescu, Mari Ostendorf |
| Abstract | In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features using a convolutional neural network over energy and pitch trajectories coupled with an attention-based recurrent neural network that accepts text and prosodic features. We find that different types of acoustic-prosodic features are individually helpful, and together give statistically significant improvements in parse and disfluency detection F1 scores over a strong text-only baseline. For this study with known sentence boundaries, error analyses show that the main benefit of acoustic-prosodic features is in sentences with disfluencies, attachment decisions are most improved, and transcription errors obscure gains from prosody. |
| Tasks | |
| Published | 2017-04-24 |
| URL | http://arxiv.org/abs/1704.07287v2 |
| http://arxiv.org/pdf/1704.07287v2.pdf | |
| PWC | https://paperswithcode.com/paper/parsing-speech-a-neural-approach-to |
| Repo | |
| Framework | |
