Paper Group ANR 15
Annotation Methodologies for Vision and Language Dataset Creation. An Operator Theoretic Approach to Nonparametric Mixture Models. Non-flat Ground Detection Based on A Local Descriptor. Small ensembles of kriging models for optimization. Grammatical Case Based IS-A Relation Extraction with Boosting for Polish. The Challenge of Non-Technical Loss De …
Annotation Methodologies for Vision and Language Dataset Creation
| Title | Annotation Methodologies for Vision and Language Dataset Creation |
| Authors | Gitit Kehat, James Pustejovsky |
| Abstract | Annotated datasets are commonly used in the training and evaluation of tasks involving natural language and vision (image description generation, action recognition and visual question answering). However, many of the existing datasets reflect problems that emerge in the process of data selection and annotation. Here we point out some of the difficulties and problems one confronts when creating and validating annotated vision and language datasets. |
| Tasks | Question Answering, Temporal Action Localization, Visual Question Answering |
| Published | 2016-07-10 |
| URL | http://arxiv.org/abs/1607.02769v1 |
| http://arxiv.org/pdf/1607.02769v1.pdf | |
| PWC | https://paperswithcode.com/paper/annotation-methodologies-for-vision-and |
| Repo | |
| Framework | |
An Operator Theoretic Approach to Nonparametric Mixture Models
| Title | An Operator Theoretic Approach to Nonparametric Mixture Models |
| Authors | Robert A. Vandermeulen, Clayton D. Scott |
| Abstract | When estimating finite mixture models, it is common to make assumptions on the mixture components, such as parametric assumptions. In this work, we make no distributional assumptions on the mixture components and instead assume that observations from the mixture model are grouped, such that observations in the same group are known to be drawn from the same mixture component. We precisely characterize the number of observations $n$ per group needed for the mixture model to be identifiable, as a function of the number $m$ of mixture components. In addition to our assumption-free analysis, we also study the settings where the mixture components are either linearly independent or jointly irreducible. Furthermore, our analysis considers two kinds of identifiability – where the mixture model is the simplest one explaining the data, and where it is the only one. As an application of these results, we precisely characterize identifiability of multinomial mixture models. Our analysis relies on an operator-theoretic framework that associates mixture models in the grouped-sample setting with certain infinite-dimensional tensors. Based on this framework, we introduce general spectral algorithms for recovering the mixture components and illustrate their use on a synthetic data set. |
| Tasks | |
| Published | 2016-06-30 |
| URL | http://arxiv.org/abs/1607.00071v2 |
| http://arxiv.org/pdf/1607.00071v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-operator-theoretic-approach-to |
| Repo | |
| Framework | |
Non-flat Ground Detection Based on A Local Descriptor
| Title | Non-flat Ground Detection Based on A Local Descriptor |
| Authors | Kangru Wang, Lei Qu, Lili Chen, Yuzhang Gu, DongChen zhu, Xiaolin Zhang |
| Abstract | The detection of road and free space remains challenging for non-flat plane, especially with the varying latitudinal and longitudinal slope or in the case of multi-ground plane. In this paper, we propose a framework of the ground plane detection with stereo vision. The main contribution of this paper is a newly proposed descriptor which is implemented in the disparity image to obtain a disparity texture image. The ground plane regions can be distinguished from their surroundings effectively in the disparity texture image. Because the descriptor is implemented in the local area of the image, it can address well the problem of non-flat plane. And we also present a complete framework to detect the ground plane regions base on the disparity texture image with convolutional neural network architecture. |
| Tasks | |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08436v9 |
| http://arxiv.org/pdf/1609.08436v9.pdf | |
| PWC | https://paperswithcode.com/paper/non-flat-ground-detection-based-on-a-local |
| Repo | |
| Framework | |
Small ensembles of kriging models for optimization
| Title | Small ensembles of kriging models for optimization |
| Authors | Hossein Mohammadi, Rodolphe Le Riche, Eric Touboul |
| Abstract | The Efficient Global Optimization (EGO) algorithm uses a conditional Gaus-sian Process (GP) to approximate an objective function known at a finite number of observation points and sequentially adds new points which maximize the Expected Improvement criterion according to the GP. The important factor that controls the efficiency of EGO is the GP covariance function (or kernel) which should be chosen according to the objective function. Traditionally, a pa-rameterized family of covariance functions is considered whose parameters are learned through statistical procedures such as maximum likelihood or cross-validation. However, it may be questioned whether statistical procedures for learning covariance functions are the most efficient for optimization as they target a global agreement between the GP and the observations which is not the ultimate goal of optimization. Furthermore, statistical learning procedures are computationally expensive. The main alternative to the statistical learning of the GP is self-adaptation, where the algorithm tunes the kernel parameters based on their contribution to objective function improvement. After questioning the possibility of self-adaptation for kriging based optimizers, this paper proposes a novel approach for tuning the length-scale of the GP in EGO: At each iteration, a small ensemble of kriging models structured by their length-scales is created. All of the models contribute to an iterate in an EGO-like fashion. Then, the set of models is densified around the model whose length-scale yielded the best iterate and further points are produced. Numerical experiments are provided which motivate the use of many length-scales. The tested implementation does not perform better than the classical EGO algorithm in a sequential context but show the potential of the approach for parallel implementations. |
| Tasks | |
| Published | 2016-03-08 |
| URL | http://arxiv.org/abs/1603.02638v1 |
| http://arxiv.org/pdf/1603.02638v1.pdf | |
| PWC | https://paperswithcode.com/paper/small-ensembles-of-kriging-models-for |
| Repo | |
| Framework | |
Grammatical Case Based IS-A Relation Extraction with Boosting for Polish
| Title | Grammatical Case Based IS-A Relation Extraction with Boosting for Polish |
| Authors | Paweł Łoziński, Dariusz Czerski, Mieczysław A. Kłopotek |
| Abstract | Pattern-based methods of IS-A relation extraction rely heavily on so called Hearst patterns. These are ways of expressing instance enumerations of a class in natural language. While these lexico-syntactic patterns prove quite useful, they may not capture all taxonomical relations expressed in text. Therefore in this paper we describe a novel method of IS-A relation extraction from patterns, which uses morpho-syntactical annotations along with grammatical case of noun phrases that constitute entities participating in IS-A relation. We also describe a method for increasing the number of extracted relations that we call pseudo-subclass boosting which has potential application in any pattern-based relation extraction method. Experiments were conducted on a corpus of about 0.5 billion web documents in Polish language. |
| Tasks | Relation Extraction |
| Published | 2016-05-10 |
| URL | http://arxiv.org/abs/1605.02916v1 |
| http://arxiv.org/pdf/1605.02916v1.pdf | |
| PWC | https://paperswithcode.com/paper/grammatical-case-based-is-a-relation |
| Repo | |
| Framework | |
The Challenge of Non-Technical Loss Detection using Artificial Intelligence: A Survey
| Title | The Challenge of Non-Technical Loss Detection using Artificial Intelligence: A Survey |
| Authors | Patrick Glauner, Jorge Augusto Meira, Petko Valtchev, Radu State, Franck Bettinger |
| Abstract | Detection of non-technical losses (NTL) which include electricity theft, faulty meters or billing errors has attracted increasing attention from researchers in electrical engineering and computer science. NTLs cause significant harm to the economy, as in some countries they may range up to 40% of the total electricity distributed. The predominant research direction is employing artificial intelligence to predict whether a customer causes NTL. This paper first provides an overview of how NTLs are defined and their impact on economies, which include loss of revenue and profit of electricity providers and decrease of the stability and reliability of electrical power grids. It then surveys the state-of-the-art research efforts in a up-to-date and comprehensive review of algorithms, features and data sets used. It finally identifies the key scientific and engineering challenges in NTL detection and suggests how they could be addressed in the future. |
| Tasks | |
| Published | 2016-06-02 |
| URL | http://arxiv.org/abs/1606.00626v3 |
| http://arxiv.org/pdf/1606.00626v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-challenge-of-non-technical-loss-detection |
| Repo | |
| Framework | |
Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
| Title | Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling |
| Authors | Jonas Uhrig, Marius Cordts, Uwe Franke, Thomas Brox |
| Abstract | Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2016-04-18 |
| URL | http://arxiv.org/abs/1604.05096v2 |
| http://arxiv.org/pdf/1604.05096v2.pdf | |
| PWC | https://paperswithcode.com/paper/pixel-level-encoding-and-depth-layering-for |
| Repo | |
| Framework | |
Random Shuffling and Resets for the Non-stationary Stochastic Bandit Problem
| Title | Random Shuffling and Resets for the Non-stationary Stochastic Bandit Problem |
| Authors | Robin Allesiardo, Raphaël Féraud, Odalric-Ambrym Maillard |
| Abstract | We consider a non-stationary formulation of the stochastic multi-armed bandit where the rewards are no longer assumed to be identically distributed. For the best-arm identification task, we introduce a version of Successive Elimination based on random shuffling of the $K$ arms. We prove that under a novel and mild assumption on the mean gap $\Delta$, this simple but powerful modification achieves the same guarantees in term of sample complexity and cumulative regret than its original version, but in a much wider class of problems, as it is not anymore constrained to stationary distributions. We also show that the original {\sc Successive Elimination} fails to have controlled regret in this more general scenario, thus showing the benefit of shuffling. We then remove our mild assumption and adapt the algorithm to the best-arm identification task with switching arms. We adapt the definition of the sample complexity for that case and prove that, against an optimal policy with $N-1$ switches of the optimal arm, this new algorithm achieves an expected sample complexity of $O(\Delta^{-2}\sqrt{NK\delta^{-1} \log(K \delta^{-1})})$, where $\delta$ is the probability of failure of the algorithm, and an expected cumulative regret of $O(\Delta^{-1}{\sqrt{NTK \log (TK)}})$ after $T$ time steps. |
| Tasks | |
| Published | 2016-09-07 |
| URL | http://arxiv.org/abs/1609.02139v1 |
| http://arxiv.org/pdf/1609.02139v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-shuffling-and-resets-for-the-non |
| Repo | |
| Framework | |
Unsupervised Deep Hashing for Large-scale Visual Search
| Title | Unsupervised Deep Hashing for Large-scale Visual Search |
| Authors | Zhaoqiang Xia, Xiaoyi Feng, Jinye Peng, Abdenour Hadid |
| Abstract | Learning based hashing plays a pivotal role in large-scale visual search. However, most existing hashing algorithms tend to learn shallow models that do not seek representative binary codes. In this paper, we propose a novel hashing approach based on unsupervised deep learning to hierarchically transform features into hash codes. Within the heterogeneous deep hashing framework, the autoencoder layers with specific constraints are considered to model the nonlinear mapping between features and binary codes. Then, a Restricted Boltzmann Machine (RBM) layer with constraints is utilized to reduce the dimension in the hamming space. Extensive experiments on the problem of visual search demonstrate the competitiveness of our proposed approach compared to state-of-the-art. |
| Tasks | |
| Published | 2016-01-31 |
| URL | http://arxiv.org/abs/1602.00206v1 |
| http://arxiv.org/pdf/1602.00206v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-deep-hashing-for-large-scale |
| Repo | |
| Framework | |
Dimension-Free Iteration Complexity of Finite Sum Optimization Problems
| Title | Dimension-Free Iteration Complexity of Finite Sum Optimization Problems |
| Authors | Yossi Arjevani, Ohad Shamir |
| Abstract | Many canonical machine learning problems boil down to a convex optimization problem with a finite sum structure. However, whereas much progress has been made in developing faster algorithms for this setting, the inherent limitations of these problems are not satisfactorily addressed by existing lower bounds. Indeed, current bounds focus on first-order optimization algorithms, and only apply in the often unrealistic regime where the number of iterations is less than $\mathcal{O}(d/n)$ (where $d$ is the dimension and $n$ is the number of samples). In this work, we extend the framework of (Arjevani et al., 2015) to provide new lower bounds, which are dimension-free, and go beyond the assumptions of current bounds, thereby covering standard finite sum optimization methods, e.g., SAG, SAGA, SVRG, SDCA without duality, as well as stochastic coordinate-descent methods, such as SDCA and accelerated proximal SDCA. |
| Tasks | |
| Published | 2016-06-30 |
| URL | http://arxiv.org/abs/1606.09333v1 |
| http://arxiv.org/pdf/1606.09333v1.pdf | |
| PWC | https://paperswithcode.com/paper/dimension-free-iteration-complexity-of-finite |
| Repo | |
| Framework | |
Can DMD obtain a Scene Background in Color?
| Title | Can DMD obtain a Scene Background in Color? |
| Authors | Santosh Tirunagari, Norman Poh, Miroslaw Bober, David Windridge |
| Abstract | A background model describes a scene without any foreground objects and has a number of applications, ranging from video surveillance to computational photography. Recent studies have introduced the method of Dynamic Mode Decomposition (DMD) for robustly separating video frames into a background model and foreground components. While the method introduced operates by converting color images to grayscale, we in this study propose a technique to obtain the background model in the color domain. The effectiveness of our technique is demonstrated using a publicly available Scene Background Initialisation (SBI) dataset. Our results both qualitatively and quantitatively show that DMD can successfully obtain a colored background model. |
| Tasks | |
| Published | 2016-07-22 |
| URL | http://arxiv.org/abs/1607.06783v1 |
| http://arxiv.org/pdf/1607.06783v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-dmd-obtain-a-scene-background-in-color |
| Repo | |
| Framework | |
A Model of Selective Advantage for the Efficient Inference of Cancer Clonal Evolution
| Title | A Model of Selective Advantage for the Efficient Inference of Cancer Clonal Evolution |
| Authors | Daniele Ramazzotti |
| Abstract | Recently, there has been a resurgence of interest in rigorous algorithms for the inference of cancer progression from genomic data. The motivations are manifold: (i) growing NGS and single cell data from cancer patients, (ii) need for novel Data Science and Machine Learning algorithms to infer models of cancer progression, and (iii) a desire to understand the temporal and heterogeneous structure of tumor to tame its progression by efficacious therapeutic intervention. This thesis presents a multi-disciplinary effort to model tumor progression involving successive accumulation of genetic alterations, each resulting populations manifesting themselves in a cancer phenotype. The framework presented in this work along with algorithms derived from it, represents a novel approach for inferring cancer progression, whose accuracy and convergence rates surpass the existing techniques. The approach derives its power from several fields including algorithms in machine learning, theory of causality and cancer biology. Furthermore, a modular pipeline to extract ensemble-level progression models from sequenced cancer genomes is proposed. The pipeline combines state-of-the-art techniques for sample stratification, driver selection, identification of fitness-equivalent exclusive alterations and progression model inference. Furthermore, the results are validated by synthetic data with realistic generative models, and empirically interpreted in the context of real cancer datasets; in the later case, biologically significant conclusions are also highlighted. Specifically, it demonstrates the pipeline’s ability to reproduce much of the knowledge on colorectal cancer, as well as to suggest novel hypotheses. Lastly, it also proves that the proposed framework can be applied to reconstruct the evolutionary history of cancer clones in single patients, as illustrated by an example from clear cell renal carcinomas. |
| Tasks | |
| Published | 2016-02-15 |
| URL | http://arxiv.org/abs/1602.07614v1 |
| http://arxiv.org/pdf/1602.07614v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-of-selective-advantage-for-the |
| Repo | |
| Framework | |
Independent Component Analysis by Entropy Maximization with Kernels
| Title | Independent Component Analysis by Entropy Maximization with Kernels |
| Authors | Zois Boukouvalas, Rami Mowakeaa, Geng-Shen Fu, Tulay Adali |
| Abstract | Independent component analysis (ICA) is the most popular method for blind source separation (BSS) with a diverse set of applications, such as biomedical signal processing, video and image analysis, and communications. Maximum likelihood (ML), an optimal theoretical framework for ICA, requires knowledge of the true underlying probability density function (PDF) of the latent sources, which, in many applications, is unknown. ICA algorithms cast in the ML framework often deviate from its theoretical optimality properties due to poor estimation of the source PDF. Therefore, accurate estimation of source PDFs is critical in order to avoid model mismatch and poor ICA performance. In this paper, we propose a new and efficient ICA algorithm based on entropy maximization with kernels, (ICA-EMK), which uses both global and local measuring functions as constraints to dynamically estimate the PDF of the sources with reasonable complexity. In addition, the new algorithm performs optimization with respect to each of the cost function gradient directions separately, enabling parallel implementations on multi-core computers. We demonstrate the superior performance of ICA-EMK over competing ICA algorithms using simulated as well as real-world data. |
| Tasks | |
| Published | 2016-10-22 |
| URL | http://arxiv.org/abs/1610.07104v1 |
| http://arxiv.org/pdf/1610.07104v1.pdf | |
| PWC | https://paperswithcode.com/paper/independent-component-analysis-by-entropy |
| Repo | |
| Framework | |
Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories
| Title | Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories |
| Authors | Przemysław Andrzej Wałęga, Carl Schultz, Mehul Bhatt |
| Abstract | The systematic modelling of dynamic spatial systems is a key requirement in a wide range of application areas such as commonsense cognitive robotics, computer-aided architecture design, and dynamic geographic information systems. We present ASPMT(QS), a novel approach and fully-implemented prototype for non-monotonic spatial reasoning -a crucial requirement within dynamic spatial systems- based on Answer Set Programming Modulo Theories (ASPMT). ASPMT(QS) consists of a (qualitative) spatial representation module (QS) and a method for turning tight ASPMT instances into Satisfiability Modulo Theories (SMT) instances in order to compute stable models by means of SMT solvers. We formalise and implement concepts of default spatial reasoning and spatial frame axioms. Spatial reasoning is performed by encoding spatial relations as systems of polynomial constraints, and solving via SMT with the theory of real nonlinear arithmetic. We empirically evaluate ASPMT(QS) in comparison with other contemporary spatial reasoning systems both within and outside the context of logic programming. ASPMT(QS) is currently the only existing system that is capable of reasoning about indirect spatial effects (i.e., addressing the ramification problem), and integrating geometric and qualitative spatial information within a non-monotonic spatial reasoning context. This paper is under consideration for publication in TPLP. |
| Tasks | |
| Published | 2016-06-25 |
| URL | http://arxiv.org/abs/1606.07860v2 |
| http://arxiv.org/pdf/1606.07860v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-monotonic-spatial-reasoning-with-answer |
| Repo | |
| Framework | |
Photorealistic Facial Texture Inference Using Deep Neural Networks
| Title | Photorealistic Facial Texture Inference Using Deep Neural Networks |
| Authors | Shunsuke Saito, Lingyu Wei, Liwen Hu, Koki Nagano, Hao Li |
| Abstract | We present a data-driven inference method that can synthesize a photorealistic texture map of a complete 3D face model given a partial 2D view of a person in the wild. After an initial estimation of shape and low-frequency albedo, we compute a high-frequency partial texture map, without the shading component, of the visible face area. To extract the fine appearance details from this incomplete input, we introduce a multi-scale detail analysis technique based on mid-layer feature correlations extracted from a deep convolutional neural network. We demonstrate that fitting a convex combination of feature correlations from a high-resolution face database can yield a semantically plausible facial detail description of the entire face. A complete and photorealistic texture map can then be synthesized by iteratively optimizing for the reconstructed feature correlations. Using these high-resolution textures and a commercial rendering framework, we can produce high-fidelity 3D renderings that are visually comparable to those obtained with state-of-the-art multi-view face capture systems. We demonstrate successful face reconstructions from a wide range of low resolution input images, including those of historical figures. In addition to extensive evaluations, we validate the realism of our results using a crowdsourced user study. |
| Tasks | |
| Published | 2016-12-02 |
| URL | http://arxiv.org/abs/1612.00523v1 |
| http://arxiv.org/pdf/1612.00523v1.pdf | |
| PWC | https://paperswithcode.com/paper/photorealistic-facial-texture-inference-using |
| Repo | |
| Framework | |
