Paper Group ANR 73
Evaluating Induced CCG Parsers on Grounded Semantic Parsing. Image Restoration with Locally Selected Class-Adapted Models. A Geometric Approach to Color Image Regularization. Joint denoising and distortion correction of atomic scale scanning transmission electron microscopy images. Estimating Sparse Signals with Smooth Support via Convex Programmin …
Evaluating Induced CCG Parsers on Grounded Semantic Parsing
| Title | Evaluating Induced CCG Parsers on Grounded Semantic Parsing |
| Authors | Yonatan Bisk, Siva Reddy, John Blitzer, Julia Hockenmaier, Mark Steedman |
| Abstract | We compare the effectiveness of four different syntactic CCG parsers for a semantic slot-filling task to explore how much syntactic supervision is required for downstream semantic analysis. This extrinsic, task-based evaluation provides a unique window to explore the strengths and weaknesses of semantics captured by unsupervised grammar induction systems. We release a new Freebase semantic parsing dataset called SPADES (Semantic PArsing of DEclarative Sentences) containing 93K cloze-style questions paired with answers. We evaluate all our models on this dataset. Our code and data are available at https://github.com/sivareddyg/graph-parser. |
| Tasks | Semantic Parsing, Slot Filling |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09405v2 |
| http://arxiv.org/pdf/1609.09405v2.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-induced-ccg-parsers-on-grounded |
| Repo | |
| Framework | |
Image Restoration with Locally Selected Class-Adapted Models
| Title | Image Restoration with Locally Selected Class-Adapted Models |
| Authors | Afonso M. Teodoro, José M. Bioucas-Dias, Mário A. T. Figueiredo |
| Abstract | State-of-the-art algorithms for imaging inverse problems (namely deblurring and reconstruction) are typically iterative, involving a denoising operation as one of its steps. Using a state-of-the-art denoising method in this context is not trivial, and is the focus of current work. Recently, we have proposed to use a class-adapted denoiser (patch-based using Gaussian mixture models) in a so-called plug-and-play scheme, wherein a state-of-the-art denoiser is plugged into an iterative algorithm, leading to results that outperform the best general-purpose algorithms, when applied to an image of a known class (e.g. faces, text, brain MRI). In this paper, we extend that approach to handle situations where the image being processed is from one of a collection of possible classes or, more importantly, contains regions of different classes. More specifically, we propose a method to locally select one of a set of class-adapted Gaussian mixture patch priors, previously estimated from clean images of those classes. Our approach may be seen as simultaneously performing segmentation and restoration, thus contributing to bridging the gap between image restoration/reconstruction and analysis. |
| Tasks | Deblurring, Denoising, Image Restoration |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.07003v2 |
| http://arxiv.org/pdf/1605.07003v2.pdf | |
| PWC | https://paperswithcode.com/paper/image-restoration-with-locally-selected-class |
| Repo | |
| Framework | |
A Geometric Approach to Color Image Regularization
| Title | A Geometric Approach to Color Image Regularization |
| Authors | Freddie Åström, Christoph Schnörr |
| Abstract | We present a new vectorial total variation method that addresses the problem of color consistent image filtering. Our approach is inspired from the double-opponent cell representation in the human visual cortex. Existing methods of vectorial total variation regularizers have insufficient (or no) coupling between the color channels and thus may introduce color artifacts. We address this problem by introducing a novel coupling between the color channels related to a pullback-metric from the opponent space to the data (RGB color) space. Our energy is a non-convex, non-smooth higher-order vectorial total variation approach and promotes color consistent image filtering via a coupling term. For a convex variant, we show well-posedness and existence of a solution in the space of vectorial bounded variation. For the higher-order scheme we employ a half-quadratic strategy, which model the non-convex energy terms as the infimum of a sequence of quadratic functions. In experiments, we elaborate on traditional image restoration applications of inpainting, deblurring and denoising. Regarding the latter, we demonstrate state of the art restoration quality with respect to structure coherence and color consistency. |
| Tasks | Deblurring, Denoising, Image Restoration |
| Published | 2016-05-19 |
| URL | http://arxiv.org/abs/1605.05977v1 |
| http://arxiv.org/pdf/1605.05977v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-geometric-approach-to-color-image |
| Repo | |
| Framework | |
Joint denoising and distortion correction of atomic scale scanning transmission electron microscopy images
| Title | Joint denoising and distortion correction of atomic scale scanning transmission electron microscopy images |
| Authors | Benjamin Berkels, Benedikt Wirth |
| Abstract | Nowadays, modern electron microscopes deliver images at atomic scale. The precise atomic structure encodes information about material properties. Thus, an important ingredient in the image analysis is to locate the centers of the atoms shown in micrographs as precisely as possible. Here, we consider scanning transmission electron microscopy (STEM), which acquires data in a rastering pattern, pixel by pixel. Due to this rastering combined with the magnification to atomic scale, movements of the specimen even at the nanometer scale lead to random image distortions that make precise atom localization difficult. Given a series of STEM images, we derive a Bayesian method that jointly estimates the distortion in each image and reconstructs the underlying atomic grid of the material by fitting the atom bumps with suitable bump functions. The resulting highly non-convex minimization problems are solved numerically with a trust region approach. Well-posedness of the reconstruction method and the model behavior for faster and faster rastering are investigated using variational techniques. The performance of the method is finally evaluated on both synthetic and real experimental data. |
| Tasks | Denoising |
| Published | 2016-12-24 |
| URL | http://arxiv.org/abs/1612.08170v1 |
| http://arxiv.org/pdf/1612.08170v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-denoising-and-distortion-correction-of |
| Repo | |
| Framework | |
Estimating Sparse Signals with Smooth Support via Convex Programming and Block Sparsity
| Title | Estimating Sparse Signals with Smooth Support via Convex Programming and Block Sparsity |
| Authors | Sohil Shah, Tom Goldstein, Christoph Studer |
| Abstract | Conventional algorithms for sparse signal recovery and sparse representation rely on $l_1$-norm regularized variational methods. However, when applied to the reconstruction of $\textit{sparse images}$, i.e., images where only a few pixels are non-zero, simple $l_1$-norm-based methods ignore potential correlations in the support between adjacent pixels. In a number of applications, one is interested in images that are not only sparse, but also have a support with smooth (or contiguous) boundaries. Existing algorithms that take into account such a support structure mostly rely on non-convex methods and—as a consequence—do not scale well to high-dimensional problems and/or do not converge to global optima. In this paper, we explore the use of new block $l_1$-norm regularizers, which enforce image sparsity while simultaneously promoting smooth support structure. By exploiting the convexity of our regularizers, we develop new computationally-efficient recovery algorithms that guarantee global optimality. We demonstrate the efficacy of our regularizers on a variety of imaging tasks including compressive image recovery, image restoration, and robust PCA. |
| Tasks | Image Restoration |
| Published | 2016-05-06 |
| URL | http://arxiv.org/abs/1605.01813v1 |
| http://arxiv.org/pdf/1605.01813v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-sparse-signals-with-smooth-support |
| Repo | |
| Framework | |
Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications
| Title | Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications |
| Authors | Stanley H. Chan, Xiran Wang, Omar A. Elgendy |
| Abstract | Alternating direction method of multiplier (ADMM) is a widely used algorithm for solving constrained optimization problems in image restoration. Among many useful features, one critical feature of the ADMM algorithm is its modular structure which allows one to plug in any off-the-shelf image denoising algorithm for a subproblem in the ADMM algorithm. Because of the plug-in nature, this type of ADMM algorithms is coined the name “Plug-and-Play ADMM”. Plug-and-Play ADMM has demonstrated promising empirical results in a number of recent papers. However, it is unclear under what conditions and by using what denoising algorithms would it guarantee convergence. Also, since Plug-and-Play ADMM uses a specific way to split the variables, it is unclear if fast implementation can be made for common Gaussian and Poissonian image restoration problems. In this paper, we propose a Plug-and-Play ADMM algorithm with provable fixed point convergence. We show that for any denoising algorithm satisfying an asymptotic criteria, called bounded denoisers, Plug-and-Play ADMM converges to a fixed point under a continuation scheme. We also present fast implementations for two image restoration problems on super-resolution and single-photon imaging. We compare Plug-and-Play ADMM with state-of-the-art algorithms in each problem type, and demonstrate promising experimental results of the algorithm. |
| Tasks | Denoising, Image Denoising, Image Restoration, Super-Resolution |
| Published | 2016-05-05 |
| URL | http://arxiv.org/abs/1605.01710v2 |
| http://arxiv.org/pdf/1605.01710v2.pdf | |
| PWC | https://paperswithcode.com/paper/plug-and-play-admm-for-image-restoration |
| Repo | |
| Framework | |
Initialization and Coordinate Optimization for Multi-way Matching
| Title | Initialization and Coordinate Optimization for Multi-way Matching |
| Authors | Da Tang, Tony Jebara |
| Abstract | We consider the problem of consistently matching multiple sets of elements to each other, which is a common task in fields such as computer vision. To solve the underlying NP-hard objective, existing methods often relax or approximate it, but end up with unsatisfying empirical performance due to a misaligned objective. We propose a coordinate update algorithm that directly optimizes the target objective. By using pairwise alignment information to build an undirected graph and initializing the permutation matrices along the edges of its Maximum Spanning Tree, our algorithm successfully avoids bad local optima. Theoretically, with high probability our algorithm guarantees an optimal solution under reasonable noise assumptions. Empirically, our algorithm consistently and significantly outperforms existing methods on several benchmark tasks on real datasets. |
| Tasks | |
| Published | 2016-11-02 |
| URL | https://arxiv.org/abs/1611.00838v5 |
| https://arxiv.org/pdf/1611.00838v5.pdf | |
| PWC | https://paperswithcode.com/paper/initialization-and-coordinate-optimization |
| Repo | |
| Framework | |
Gender Inference using Statistical Name Characteristics in Twitter
| Title | Gender Inference using Statistical Name Characteristics in Twitter |
| Authors | Juergen Mueller, Gerd Stumme |
| Abstract | Much attention has been given to the task of gender inference of Twitter users. Although names are strong gender indicators, the names of Twitter users are rarely used as a feature; probably due to the high number of ill-formed names, which cannot be found in any name dictionary. Instead of relying solely on a name database, we propose a novel name classifier. Our approach extracts characteristics from the user names and uses those in order to assign the names to a gender. This enables us to classify international first names as well as ill-formed names. |
| Tasks | |
| Published | 2016-06-17 |
| URL | http://arxiv.org/abs/1606.05467v2 |
| http://arxiv.org/pdf/1606.05467v2.pdf | |
| PWC | https://paperswithcode.com/paper/gender-inference-using-statistical-name |
| Repo | |
| Framework | |
Semantic Representations of Word Senses and Concepts
| Title | Semantic Representations of Word Senses and Concepts |
| Authors | José Camacho-Collados, Ignacio Iacobacci, Roberto Navigli, Mohammad Taher Pilehvar |
| Abstract | Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days. Among the range of different linguistic items, words have attracted the most research attention. However, word representations have an important limitation: they conflate different meanings of a word into a single vector. Representations of word senses have the potential to overcome this inherent limitation. Indeed, the representation of individual word senses and concepts has recently gained in popularity with several experimental results showing that a considerable performance improvement can be achieved across different NLP applications upon moving from word level to the deeper sense and concept levels. Another interesting point regarding the representation of concepts and word senses is that these models can be seamlessly applied to other linguistic items, such as words, phrases and sentences. |
| Tasks | |
| Published | 2016-08-02 |
| URL | http://arxiv.org/abs/1608.00841v1 |
| http://arxiv.org/pdf/1608.00841v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-representations-of-word-senses-and |
| Repo | |
| Framework | |
Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning
| Title | Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning |
| Authors | Yichen Chen, Mengdi Wang |
| Abstract | We study the online estimation of the optimal policy of a Markov decision process (MDP). We propose a class of Stochastic Primal-Dual (SPD) methods which exploit the inherent minimax duality of Bellman equations. The SPD methods update a few coordinates of the value and policy estimates as a new state transition is observed. These methods use small storage and has low computational complexity per iteration. The SPD methods find an absolute-$\epsilon$-optimal policy, with high probability, using $\mathcal{O}\left(\frac{\mathcal{S}^4 \mathcal{A}^2\sigma^2 }{(1-\gamma)^6\epsilon^2} \right)$ iterations/samples for the infinite-horizon discounted-reward MDP and $\mathcal{O}\left(\frac{\mathcal{S}^4 \mathcal{A}^2H^6\sigma^2 }{\epsilon^2} \right)$ for the finite-horizon MDP. |
| Tasks | |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02516v1 |
| http://arxiv.org/pdf/1612.02516v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-primal-dual-methods-and-sample |
| Repo | |
| Framework | |
Salient Object Subitizing
| Title | Salient Object Subitizing |
| Authors | Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian Price, Radomir Mech |
| Abstract | We study the problem of Salient Object Subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1-4). To this end, we present a salient object subitizing image dataset of about 14K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained Convolutional Neural Network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval. |
| Tasks | Image Retrieval, Object Detection, Salient Object Detection |
| Published | 2016-07-26 |
| URL | http://arxiv.org/abs/1607.07525v1 |
| http://arxiv.org/pdf/1607.07525v1.pdf | |
| PWC | https://paperswithcode.com/paper/salient-object-subitizing |
| Repo | |
| Framework | |
Correlated Equilibria for Approximate Variational Inference in MRFs
| Title | Correlated Equilibria for Approximate Variational Inference in MRFs |
| Authors | Luis E. Ortiz, Boshen Wang, Ze Gong |
| Abstract | Almost all of the work in graphical models for game theory has mirrored previous work in probabilistic graphical models. Our work considers the opposite direction: Taking advantage of recent advances in equilibrium computation for probabilistic inference. We present formulations of inference problems in Markov random fields (MRFs) as computation of equilibria in a certain class of game-theoretic graphical models. We concretely establishes the precise connection between variational probabilistic inference in MRFs and correlated equilibria. No previous work exploits recent theoretical and empirical results from the literature on algorithmic and computational game theory on the tractable, polynomial-time computation of exact or approximate correlated equilibria in graphical games with arbitrary, loopy graph structure. We discuss how to design new algorithms with equally tractable guarantees for the computation of approximate variational inference in MRFs. Also, inspired by a previously stated game-theoretic view of state-of-the-art tree-reweighed (TRW) message-passing techniques for belief inference as zero-sum game, we propose a different, general-sum potential game to design approximate fictitious-play techniques. We perform synthetic experiments evaluating our proposed approximation algorithms with standard methods and TRW on several classes of classical Ising models (i.e., with binary random variables). We also evaluate the algorithms using Ising models learned from the MNIST dataset. Our experiments show that our global approach is competitive, particularly shinning in a class of Ising models with constant, “highly attractive” edge-weights, in which it is often better than all other alternatives we evaluated. With a notable exception, our more local approach was not as effective. Yet, in fairness, almost all of the alternatives are often no better than a simple baseline: estimate 0.5. |
| Tasks | |
| Published | 2016-04-10 |
| URL | http://arxiv.org/abs/1604.02737v2 |
| http://arxiv.org/pdf/1604.02737v2.pdf | |
| PWC | https://paperswithcode.com/paper/correlated-equilibria-for-approximate |
| Repo | |
| Framework | |
Defensive Distillation is Not Robust to Adversarial Examples
| Title | Defensive Distillation is Not Robust to Adversarial Examples |
| Authors | Nicholas Carlini, David Wagner |
| Abstract | We show that defensive distillation is not secure: it is no more resistant to targeted misclassification attacks than unprotected neural networks. |
| Tasks | |
| Published | 2016-07-14 |
| URL | http://arxiv.org/abs/1607.04311v1 |
| http://arxiv.org/pdf/1607.04311v1.pdf | |
| PWC | https://paperswithcode.com/paper/defensive-distillation-is-not-robust-to |
| Repo | |
| Framework | |
Ear Recognition: More Than a Survey
| Title | Ear Recognition: More Than a Survey |
| Authors | Žiga Emeršič, Vitomir Štruc, Peter Peer |
| Abstract | Automatic identity recognition from ear images represents an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes the technology an appealing choice for surveillance and security applications as well as other application domains. Significant contributions have been made in the field over recent years, but open research problems still remain and hinder a wider (commercial) deployment of the technology. This paper presents an overview of the field of automatic ear recognition (from 2D images) and focuses specifically on the most recent, descriptor-based methods proposed in this area. Open challenges are discussed and potential research directions are outlined with the goal of providing the reader with a point of reference for issues worth examining in the future. In addition to a comprehensive review on ear recognition technology, the paper also introduces a new, fully unconstrained dataset of ear images gathered from the web and a toolbox implementing several state-of-the-art techniques for ear recognition. The dataset and toolbox are meant to address some of the open issues in the field and are made publicly available to the research community. |
| Tasks | |
| Published | 2016-11-18 |
| URL | http://arxiv.org/abs/1611.06203v2 |
| http://arxiv.org/pdf/1611.06203v2.pdf | |
| PWC | https://paperswithcode.com/paper/ear-recognition-more-than-a-survey |
| Repo | |
| Framework | |
Corpus analysis without prior linguistic knowledge - unsupervised mining of phrases and subphrase structure
| Title | Corpus analysis without prior linguistic knowledge - unsupervised mining of phrases and subphrase structure |
| Authors | Stefan Gerdjikov, Klaus U. Schulz |
| Abstract | When looking at the structure of natural language, “phrases” and “words” are central notions. We consider the problem of identifying such “meaningful subparts” of language of any length and underlying composition principles in a completely corpus-based and language-independent way without using any kind of prior linguistic knowledge. Unsupervised methods for identifying “phrases”, mining subphrase structure and finding words in a fully automated way are described. This can be considered as a step towards automatically computing a “general dictionary and grammar of the corpus”. We hope that in the long run variants of our approach turn out to be useful for other kind of sequence data as well, such as, e.g., speech, genom sequences, or music annotation. Even if we are not primarily interested in immediate applications, results obtained for a variety of languages show that our methods are interesting for many practical tasks in text mining, terminology extraction and lexicography, search engine technology, and related fields. |
| Tasks | |
| Published | 2016-02-18 |
| URL | http://arxiv.org/abs/1602.05772v1 |
| http://arxiv.org/pdf/1602.05772v1.pdf | |
| PWC | https://paperswithcode.com/paper/corpus-analysis-without-prior-linguistic |
| Repo | |
| Framework | |
