October 16, 2019

3122 words 15 mins read

Paper Group ANR 1099

Semantic Matching Against a Corpus: New Applications and Methods. Deep Learning for Inferring the Surface Solar Irradiance from Sky Imagery. Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model. Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism. How should a fixed budget of …

Semantic Matching Against a Corpus: New Applications and Methods


Title	Semantic Matching Against a Corpus: New Applications and Methods
Authors	Lucy H. Lin, Scott Miles, Noah A. Smith
Abstract	We consider the case of a domain expert who wishes to explore the extent to which a particular idea is expressed in a text collection. We propose the task of semantically matching the idea, expressed as a natural language proposition, against a corpus. We create two preliminary tasks derived from existing datasets, and then introduce a more realistic one on disaster recovery designed for emergency managers, whom we engaged in a user study. On the latter, we find that a new model built from natural language entailment data produces higher-quality matches than simple word-vector averaging, both on expert-crafted queries and on ones produced by the subjects themselves. This work provides a proof-of-concept for such applications of semantic matching and illustrates key challenges.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09502v1
PDF	http://arxiv.org/pdf/1808.09502v1.pdf
PWC	https://paperswithcode.com/paper/semantic-matching-against-a-corpus-new
Repo
Framework

Deep Learning for Inferring the Surface Solar Irradiance from Sky Imagery


Title	Deep Learning for Inferring the Surface Solar Irradiance from Sky Imagery
Authors	Mehdi Zakroum, Mounir Ghogho, Mustapha Faqir, Mohamed Aymane Ahajjam
Abstract	We present a novel approach to perform ground-based estimation and prediction of the surface solar irradiance with the view to predicting photovoltaic energy production. We propose the use of mini-batch k-means clustering to extract features, referred to as per cluster number of pixels (PCNP), from sky images taken by a low-cost fish eye camera. These features are first used to classify the sky as clear or cloudy using a single hidden layer neural network; the classification accuracy achieves 99.7%. If the sky is classified as cloudy, we propose to use a deep neural network having as input features the PCNP to predict intra-hour variability of the solar irradiance. Toward this objective, in this paper, we focus on estimating the deep neural network model relating the PCNP features and the solar irradiance, which is an important step before performing the prediction task. The proposed deep learning-based estimation approach is shown to have an accuracy of 95%.
Tasks
Published	2018-12-23
URL	http://arxiv.org/abs/1812.09793v1
PDF	http://arxiv.org/pdf/1812.09793v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-inferring-the-surface-solar
Repo
Framework

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model


Title	Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Authors	Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Liwei Chen, Vadim Sheinin
Abstract	Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper, we first propose to use the \textit{syntactic graph} to represent three types of syntactic information, i.e., word order, dependency and constituency features. We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form. Experimental results on benchmark datasets show that our model is comparable to the state-of-the-art on Jobs640, ATIS and Geo880. Experimental results on adversarial examples demonstrate the robustness of the model is also improved by encoding more syntactic information.
Tasks	Graph-to-Sequence, Semantic Parsing
Published	2018-08-23
URL	http://arxiv.org/abs/1808.07624v1
PDF	http://arxiv.org/pdf/1808.07624v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-rich-syntactic-information-for
Repo
Framework

Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism


Title	Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism
Authors	Mincong Luo, Xinfu He, Li Liu
Abstract	Material irradiation experiment is dangerous and complex, thus it requires those with a vast advanced expertise to process the images and data manually. In this paper, we propose a generative adversarial model based on prior knowledge and attention mechanism to achieve the generation of irradiated material images (data-to-image model), and a prediction model for corresponding industrial performance (image-to-data model). With the proposed models, researchers can skip the dangerous and complex irradiation experiments and obtain the irradiation images and industrial performance parameters directly by inputing some experimental parameters only. We also introduce a new dataset ISMD which contains 22000 irradiated images with 22,143 sets of corresponding parameters. Our model achieved high quality results by compared with several baseline models. The evaluation and detailed analysis are also performed.
Tasks
Published	2018-11-16
URL	http://arxiv.org/abs/1811.07982v1
PDF	http://arxiv.org/pdf/1811.07982v1.pdf
PWC	https://paperswithcode.com/paper/generative-model-for-material-experiments
Repo
Framework

How should a fixed budget of dwell time be spent in scanning electron microscopy to optimize image quality?


Title	How should a fixed budget of dwell time be spent in scanning electron microscopy to optimize image quality?
Authors	Patrick Trampert, Faysal Bourghorbel, Pavel Potocek, Maurice Peemen, Christian Schlinkmann, Tim Dahmen, Philipp Slusallek
Abstract	In scanning electron microscopy, the achievable image quality is often limited by a maximum feasible acquisition time per dataset. Particularly with regard to three-dimensional or large field-of-view imaging, a compromise must be found between a high amount of shot noise, which leads to a low signal-to-noise ratio, and excessive acquisition times. Assuming a fixed acquisition time per frame, we compared three different strategies for algorithm-assisted image acquisition in scanning electron microscopy. We evaluated (1) raster scanning with a reduced dwell time per pixel followed by a state-of-the-art Denoising algorithm, (2) raster scanning with a decreased resolution in conjunction with a state-of-the-art Super Resolution algorithm, and (3) a sparse scanning approach where a fixed percentage of pixels is visited by the beam in combination with state-of-the-art inpainting algorithms. Additionally, we considered increased beam currents for each of the strategies. The experiments showed that sparse scanning using an appropriate reconstruction technique was superior to the other strategies.
Tasks	Denoising, Super-Resolution
Published	2018-01-12
URL	http://arxiv.org/abs/1801.04085v1
PDF	http://arxiv.org/pdf/1801.04085v1.pdf
PWC	https://paperswithcode.com/paper/how-should-a-fixed-budget-of-dwell-time-be
Repo
Framework

Videos as Space-Time Region Graphs


Title	Videos as Space-Time Region Graphs
Authors	Xiaolong Wang, Abhinav Gupta
Abstract	How do humans recognize the action “opening a book” ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations capturing the interactions between nearby objects. We perform reasoning on this graph representation via Graph Convolutional Networks. We achieve state-of-the-art results on both Charades and Something-Something datasets. Especially for Charades, we obtain a huge 4.4% gain when our model is applied in complex environments.
Tasks	Action Classification, Action Recognition In Videos
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01810v2
PDF	http://arxiv.org/pdf/1806.01810v2.pdf
PWC	https://paperswithcode.com/paper/videos-as-space-time-region-graphs
Repo
Framework

Composing Finite State Transducers on GPUs


Title	Composing Finite State Transducers on GPUs
Authors	Arturo Argueta, David Chiang
Abstract	Weighted finite-state transducers (FSTs) are frequently used in language processing to handle tasks such as part-of-speech tagging and speech recognition. There has been previous work using multiple CPU cores to accelerate finite state algorithms, but limited attention has been given to parallel graphics processing unit (GPU) implementations. In this paper, we introduce the first (to our knowledge) GPU implementation of the FST composition operation, and we also discuss the optimizations used to achieve the best performance on this architecture. We show that our approach obtains speedups of up to 6x over our serial implementation and 4.5x over OpenFST.
Tasks	Part-Of-Speech Tagging, Speech Recognition
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06383v1
PDF	http://arxiv.org/pdf/1805.06383v1.pdf
PWC	https://paperswithcode.com/paper/composing-finite-state-transducers-on-gpus
Repo
Framework

Accurate, Data-Efficient Learning from Noisy, Choice-Based Labels for Inherent Risk Scoring


Title	Accurate, Data-Efficient Learning from Noisy, Choice-Based Labels for Inherent Risk Scoring
Authors	W. Ronny Huang, Miguel A. Perez
Abstract	Inherent risk scoring is an important function in anti-money laundering, used for determining the riskiness of an individual during onboarding $\textit{before}$ fraudulent transactions occur. It is, however, often fraught with two challenges: (1) inconsistent notions of what constitutes as high or low risk by experts and (2) the lack of labeled data. This paper explores a new paradigm of data labeling and data collection to tackle these issues. The data labeling is choice-based; the expert does not provide an absolute risk score but merely chooses the most/least risky example out of a small choice set, which reduces inconsistency because experts make only relative judgments of risk. The data collection is synthetic; examples are crafted using optimal experimental design methods, obviating the need for real data which is often difficult to obtain due to regulatory concerns. We present the methodology of an end-to-end inherent risk scoring algorithm that we built for a large financial institution. The system was trained on a small set of synthetic data (188 examples, 24 features) whose labels are obtained via the choice-based paradigm using an efficient number of expert labelers. The system achieves 89% accuracy on a test set of 52 examples, with an area under the ROC curve of 93%.
Tasks
Published	2018-11-27
URL	http://arxiv.org/abs/1811.10791v1
PDF	http://arxiv.org/pdf/1811.10791v1.pdf
PWC	https://paperswithcode.com/paper/accurate-data-efficient-learning-from-noisy
Repo
Framework

Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis


Title	Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis
Authors	Pengtao Xie, Wei Wu, Yichen Zhu, Eric P. Xing
Abstract	Distance metric learning (DML), which learns a distance metric from labeled “similar” and “dissimilar” data pairs, is widely utilized. Recently, several works investigate orthogonality-promoting regularization (OPR), which encourages the projection vectors in DML to be close to being orthogonal, to achieve three effects: (1) high balancedness – achieving comparable performance on both frequent and infrequent classes; (2) high compactness – using a small number of projection vectors to achieve a “good” metric; (3) good generalizability – alleviating overfitting to training data. While showing promising results, these approaches suffer three problems. First, they involve solving non-convex optimization problems where achieving the global optimal is NP-hard. Second, it lacks a theoretical understanding why OPR can lead to balancedness. Third, the current generalization error analysis of OPR is not directly on the regularizer. In this paper, we address these three issues by (1) seeking convex relaxations of the original nonconvex problems so that the global optimal is guaranteed to be achievable; (2) providing a formal analysis on OPR’s capability of promoting balancedness; (3) providing a theoretical analysis that directly reveals the relationship between OPR and generalization performance. Experiments on various datasets demonstrate that our convex methods are more effective in promoting balancedness, compactness, and generalization, and are computationally more efficient, compared with the nonconvex methods.
Tasks	Metric Learning
Published	2018-02-16
URL	http://arxiv.org/abs/1802.06014v1
PDF	http://arxiv.org/pdf/1802.06014v1.pdf
PWC	https://paperswithcode.com/paper/orthogonality-promoting-distance-metric
Repo
Framework

Learning Filter Bank Sparsifying Transforms


Title	Learning Filter Bank Sparsifying Transforms
Authors	Luke Pfister, Yoram Bresler
Abstract	Data is said to follow the transform (or analysis) sparsity model if it becomes sparse when acted on by a linear operator called a sparsifying transform. Several algorithms have been designed to learn such a transform directly from data, and data-adaptive sparsifying transforms have demonstrated excellent performance in signal restoration tasks. Sparsifying transforms are typically learned using small sub-regions of data called patches, but these algorithms often ignore redundant information shared between neighboring patches. We show that many existing transform and analysis sparse representations can be viewed as filter banks, thus linking the local properties of patch-based model to the global properties of a convolutional model. We propose a new transform learning framework where the sparsifying transform is an undecimated perfect reconstruction filter bank. Unlike previous transform learning algorithms, the filter length can be chosen independently of the number of filter bank channels. Numerical results indicate filter bank sparsifying transforms outperform existing patch-based transform learning for image denoising while benefiting from additional flexibility in the design process.
Tasks	Denoising, Image Denoising
Published	2018-03-06
URL	http://arxiv.org/abs/1803.01980v1
PDF	http://arxiv.org/pdf/1803.01980v1.pdf
PWC	https://paperswithcode.com/paper/learning-filter-bank-sparsifying-transforms
Repo
Framework

Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network


Title	Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network
Authors	Pedro H. C. Avelar, Henrique Lemos, Marcelo O. R. Prates, Luis Lamb
Abstract	The application of deep learning to symbolic domains remains an active research endeavour. Graph neural networks (GNN), consisting of trained neural modules which can be arranged in different topologies at run time, are sound alternatives to tackle relational problems which lend themselves to graph representations. In this paper, we show that GNNs are capable of multitask learning, which can be naturally enforced by training the model to refine a single set of multidimensional embeddings $\in \mathbb{R}^d$ and decode them into multiple outputs by connecting MLPs at the end of the pipeline. We demonstrate the multitask learning capability of the model in the relevant relational problem of estimating network centrality measures, focusing primarily on producing rankings based on these measures, i.e. is vertex $v_1$ more central than vertex $v_2$ given centrality $c$?. We then show that a GNN can be trained to develop a \emph{lingua franca} of vertex embeddings from which all relevant information about any of the trained centrality measures can be decoded. The proposed model achieves $89%$ accuracy on a test dataset of random instances with up to 128 vertices and is shown to generalise to larger problem sizes. The model is also shown to obtain reasonable accuracy on a dataset of real world instances with up to 4k vertices, vastly surpassing the sizes of the largest instances with which the model was trained ($n=128$). Finally, we believe that our contributions attest to the potential of GNNs in symbolic domains in general and in relational learning in particular.
Tasks	Relational Reasoning
Published	2018-09-11
URL	https://arxiv.org/abs/1809.07695v4
PDF	https://arxiv.org/pdf/1809.07695v4.pdf
PWC	https://paperswithcode.com/paper/multitask-learning-on-graph-neural-networks
Repo
Framework

Poisson Image Denoising Using Best Linear Prediction: A Post-processing Framework


Title	Poisson Image Denoising Using Best Linear Prediction: A Post-processing Framework
Authors	Milad Niknejad, Mario A. T. Figueiredo
Abstract	In this paper, we address the problem of denoising images degraded by Poisson noise. We propose a new patch-based approach based on best linear prediction to estimate the underlying clean image. A simplified prediction formula is derived for Poisson observations, which requires the covariance matrix of the underlying clean patch. We use the assumption that similar patches in a neighborhood share the same covariance matrix, and we use off-the-shelf Poisson denoising methods in order to obtain an initial estimate of the covariance matrices. Our method can be seen as a post-processing step for Poisson denoising methods and the results show that it improves upon several Poisson denoising methods by relevant margins.
Tasks	Denoising, Image Denoising
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00389v1
PDF	http://arxiv.org/pdf/1803.00389v1.pdf
PWC	https://paperswithcode.com/paper/poisson-image-denoising-using-best-linear
Repo
Framework

Image denoising with generalized Gaussian mixture model patch priors


Title	Image denoising with generalized Gaussian mixture model patch priors
Authors	Charles-Alban Deledalle, Shibin Parameswaran, Truong Q. Nguyen
Abstract	Patch priors have become an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-Likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned on clean image patches as a way to regularize degraded patches. In this paper, we show that a generalized Gaussian mixture model (GGMM) captures the underlying distribution of patches better than a GMM. Even though GGMM is a powerful prior to combine with EPLL, the non-Gaussianity of its components presents major challenges to be applied to a computationally intensive process of image restoration. Specifically, each patch has to undergo a patch classification step and a shrinkage step. These two steps can be efficiently solved with a GMM prior but are computationally impractical when using a GGMM prior. In this paper, we provide approximations and computational recipes for fast evaluation of these two steps, so that EPLL can embed a GGMM prior on an image with more than tens of thousands of patches. Our main contribution is to analyze the accuracy of our approximations based on thorough theoretical analysis. Our evaluations indicate that the GGMM prior is consistently a better fit formodeling image patch distribution and performs better on average in image denoising task.
Tasks	Denoising, Image Denoising, Image Restoration
Published	2018-02-05
URL	http://arxiv.org/abs/1802.01458v2
PDF	http://arxiv.org/pdf/1802.01458v2.pdf
PWC	https://paperswithcode.com/paper/image-denoising-with-generalized-gaussian
Repo
Framework

SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond


Title	SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond
Authors	Wei Ke, Jie Chen, Jianbin Jiao, Guoying Zhao, Qixiang Ye
Abstract	In this paper, we establish a baseline for object reflection symmetry detection in complex backgrounds by presenting a new benchmark and an end-to-end deep learning approach, opening up a promising direction for symmetry detection in the wild. The new benchmark, Sym-PASCAL, spans challenges including object diversity, multi-objects, part-invisibility, and various complex backgrounds that are far beyond those in existing datasets. The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the object ground-truth symmetry and the side-outputs of multiple stages. By cascading RUs in a deep-to-shallow manner, SRN exploits the ‘flow’ of errors among multiple stages to address the challenges of fitting complex output with limited convolutional layers, suppressing the complex backgrounds, and effectively matching object symmetry at different scales. SRN is further upgraded to a multi-task side-output residual network (MT-SRN) for joint symmetry and edge detection, demonstrating its generality to image-to-mask learning tasks. Experimental results validate both the challenging aspects of Sym-PASCAL benchmark related to real-world images and the state-of-the-art performance of the proposed SRN approach.
Tasks	Edge Detection, Hand Pose Estimation
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06621v2
PDF	http://arxiv.org/pdf/1807.06621v2.pdf
PWC	https://paperswithcode.com/paper/srn-side-output-residual-network-for-object
Repo
Framework

Discrepancy-based Evolutionary Diversity Optimization


Title	Discrepancy-based Evolutionary Diversity Optimization
Authors	Aneta Neumann, Wanru Gao, Carola Doerr, Frank Neumann, Markus Wagner
Abstract	Diversity plays a crucial role in evolutionary computation. While diversity has been mainly used to prevent the population of an evolutionary algorithm from premature convergence, the use of evolutionary algorithms to obtain a diverse set of solutions has gained increasing attention in recent years. Diversity optimization in terms of features on the underlying problem allows to obtain a better understanding of possible solutions to the problem at hand and can be used for algorithm selection when dealing with combinatorial optimization problems such as the Traveling Salesperson Problem. We explore the use of the star-discrepancy measure to guide the diversity optimization process of an evolutionary algorithm. In our experimental investigations, we consider our discrepancy-based diversity optimization approaches for evolving diverse sets of images as well as instances of the Traveling Salesperson problem where a local search is not able to find near optimal solutions. Our experimental investigations comparing three diversity optimization approaches show that a discrepancy-based diversity optimization approach using a tie-breaking rule based on weighted differences to surrounding feature points provides the best results in terms of the star discrepancy measure.
Tasks	Combinatorial Optimization
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05448v1
PDF	http://arxiv.org/pdf/1802.05448v1.pdf
PWC	https://paperswithcode.com/paper/discrepancy-based-evolutionary-diversity
Repo
Framework