Paper Group ANR 832
Joint Demosaicing and Denoising with Perceptual Optimization on a Generative Adversarial Network. Physics-aware Deep Generative Models for Creating Synthetic Microstructures. Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect data. NLP-assisted software testing: A systematic mapping of the literature. CA …
Joint Demosaicing and Denoising with Perceptual Optimization on a Generative Adversarial Network
| Title | Joint Demosaicing and Denoising with Perceptual Optimization on a Generative Adversarial Network |
| Authors | Weishong Dong, Ming Yuan, Xin Li, Guangming Shi |
| Abstract | Image demosaicing - one of the most important early stages in digital camera pipelines - addressed the problem of reconstructing a full-resolution image from so-called color-filter-arrays. Despite tremendous progress made in the pase decade, a fundamental issue that remains to be addressed is how to assure the visual quality of reconstructed images especially in the presence of noise corruption. Inspired by recent advances in generative adversarial networks (GAN), we present a novel deep learning approach toward joint demosaicing and denoising (JDD) with perceptual optimization in order to ensure the visual quality of reconstructed images. The key contributions of this work include: 1) we have developed a GAN-based approach toward image demosacing in which a discriminator network with both perceptual and adversarial loss functions are used for quality assurance; 2) we propose to optimize the perceptual quality of reconstructed images by the proposed GAN in an end-to-end manner. Such end-to-end optimization of GAN is particularly effective for jointly exploiting the gain brought by each modular component (e.g., residue learning in the generative network and perceptual loss in the discriminator network). Our extensive experimental results have shown convincingly improved performance over existing state-of-the-art methods in terms of both subjective and objective quality metrics with a comparable computational cost. |
| Tasks | Demosaicking, Denoising |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04723v1 |
| http://arxiv.org/pdf/1802.04723v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-demosaicing-and-denoising-with |
| Repo | |
| Framework | |
Physics-aware Deep Generative Models for Creating Synthetic Microstructures
| Title | Physics-aware Deep Generative Models for Creating Synthetic Microstructures |
| Authors | Rahul Singh, Viraj Shah, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian, Chinmay Hegde |
| Abstract | A key problem in computational material science deals with understanding the effect of material distribution (i.e., microstructure) on material performance. The challenge is to synthesize microstructures, given a finite number of microstructure images, and/or some physical invariances that the microstructure exhibits. Conventional approaches are based on stochastic optimization and are computationally intensive. We introduce three generative models for the fast synthesis of binary microstructure images. The first model is a WGAN model that uses a finite number of training images to synthesize new microstructures that weakly satisfy the physical invariances respected by the original data. The second model explicitly enforces known physical invariances by replacing the traditional discriminator in a GAN with an invariance checker. Our third model combines the first two models to reconstruct microstructures that respect both explicit physics invariances as well as implicit constraints learned from the image data. We illustrate these models by reconstructing two-phase microstructures that exhibit coarsening behavior. The trained models also exhibit interesting latent variable interpolation behavior, and the results indicate considerable promise for enforcing user-defined physics constraints during microstructure synthesis. |
| Tasks | Stochastic Optimization |
| Published | 2018-11-21 |
| URL | http://arxiv.org/abs/1811.09669v1 |
| http://arxiv.org/pdf/1811.09669v1.pdf | |
| PWC | https://paperswithcode.com/paper/physics-aware-deep-generative-models-for |
| Repo | |
| Framework | |
Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect data
| Title | Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect data |
| Authors | Orestes Manzanilla-Salazar, Brunilde Sansò |
| Abstract | This paper proves the concept that it is feasible to accurately recognize specific human mobility shared patterns, based solely on the connection logs between portable devices and WiFi Access Points (APs), while preserving user’s privacy. We gathered data from the Eduroam WiFi network of Polytechnique Montreal, making omission of device tracking or physical layer data. The behaviors we chose to detect were the movements associated to the end of an academic class, and the patterns related to the small break periods between classes. Stringent conditions were self-imposed in our experiments. The data is known to have errors noise, and be susceptible to information loss. No countermeasures were adopted to mitigate any of these issues. Data pre-processing consists of basic statistics that were used in aggregating the data in time intervals. We obtained accuracy values of 93.7 % and 83.3 % (via Bagged Trees) when recognizing behaviour patterns of breaks between classes and end-of-classes, respectively. |
| Tasks | |
| Published | 2018-07-17 |
| URL | http://arxiv.org/abs/1807.06190v2 |
| http://arxiv.org/pdf/1807.06190v2.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-classifiers-recognize |
| Repo | |
| Framework | |
NLP-assisted software testing: A systematic mapping of the literature
| Title | NLP-assisted software testing: A systematic mapping of the literature |
| Authors | Vahid Garousi, Sara Bauer, Michael Felderer |
| Abstract | Context: To reduce manual effort of extracting test cases from natural-language requirements, many approaches based on Natural Language Processing (NLP) have been proposed in the literature. Given the large amount of approaches in this area, and since many practitioners are eager to utilize such techniques, it is important to synthesize and provide an overview of the state-of-the-art in this area. Objective: Our objective is to summarize the state-of-the-art in NLP-assisted software testing which could benefit practitioners to potentially utilize those NLP-based techniques. Moreover, this can benefit researchers in providing an overview of the research landscape. Method: To address the above need, we conducted a survey in the form of a systematic literature mapping (classification). After compiling an initial pool of 95 papers, we conducted a systematic voting, and our final pool included 67 technical papers. Results: This review paper provides an overview of the contribution types presented in the papers, types of NLP approaches used to assist software testing, types of required input requirements, and a review of tool support in this area. Some key results we have detected are: (1) only four of the 38 tools (11%) presented in the papers are available for download; (2) a larger ratio of the papers (30 of 67) provided a shallow exposure to the NLP aspects (almost no details). Conclusion: This paper would benefit both practitioners and researchers by serving as an “index” to the body of knowledge in this area. The results could help practitioners utilizing the existing NLP-based techniques; this in turn reduces the cost of test-case design and decreases the amount of human resources spent on test activities. After sharing this review with some of our industrial collaborators, initial insights show that this review can indeed be useful and beneficial to practitioners. |
| Tasks | |
| Published | 2018-06-02 |
| URL | https://arxiv.org/abs/1806.00696v3 |
| https://arxiv.org/pdf/1806.00696v3.pdf | |
| PWC | https://paperswithcode.com/paper/nlp-assisted-software-testing-a-systematic |
| Repo | |
| Framework | |
CAKE: Compact and Accurate K-dimensional representation of Emotion
| Title | CAKE: Compact and Accurate K-dimensional representation of Emotion |
| Authors | Corentin Kervadec, Valentin Vielzeuf, Stéphane Pateux, Alexis Lechervy, Frédéric Jurie |
| Abstract | Numerous models describing the human emotional states have been built by the psychology community. Alongside, Deep Neural Networks (DNN) are reaching excellent performances and are becoming interesting features extraction tools in many computer vision tasks.Inspired by works from the psychology community, we first study the link between the compact two-dimensional representation of the emotion known as arousal-valence, and discrete emotion classes (e.g. anger, happiness, sadness, etc.) used in the computer vision community. It enables to assess the benefits – in terms of discrete emotion inference – of adding an extra dimension to arousal-valence (usually named dominance). Building on these observations, we propose CAKE, a 3-dimensional representation of emotion learned in a multi-domain fashion, achieving accurate emotion recognition on several public datasets. Moreover, we visualize how emotions boundaries are organized inside DNN representations and show that DNNs are implicitly learning arousal-valence-like descriptions of emotions. Finally, we use the CAKE representation to compare the quality of the annotations of different public datasets. |
| Tasks | Emotion Recognition |
| Published | 2018-07-30 |
| URL | http://arxiv.org/abs/1807.11215v2 |
| http://arxiv.org/pdf/1807.11215v2.pdf | |
| PWC | https://paperswithcode.com/paper/cake-compact-and-accurate-k-dimensional |
| Repo | |
| Framework | |
A context encoder for audio inpainting
| Title | A context encoder for audio inpainting |
| Authors | Andrés Marafioti, Nathanaël Perraudin, Nicki Holighaus, Piotr Majdak |
| Abstract | We study the ability of deep neural networks (DNNs) to restore missing audio content based on its context, i.e., inpaint audio gaps. We focus on a condition which has not received much attention yet: gaps in the range of tens of milliseconds. We propose a DNN structure that is provided with the signal surrounding the gap in the form of time-frequency (TF) coefficients. Two DNNs with either complex-valued TF coefficient output or magnitude TF coefficient output were studied by separately training them on inpainting two types of audio signals (music and musical instruments) having 64-ms long gaps. The magnitude DNN outperformed the complex-valued DNN in terms of signal-to-noise ratios and objective difference grades. Although, for instruments, a reference inpainting obtained through linear predictive coding performed better in both metrics, it performed worse than the magnitude DNN for music. This demonstrates the potential of the magnitude DNN, in particular for inpainting signals that are more complex than single instrument sounds. |
| Tasks | |
| Published | 2018-10-29 |
| URL | https://arxiv.org/abs/1810.12138v2 |
| https://arxiv.org/pdf/1810.12138v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-context-encoder-for-audio-inpainting |
| Repo | |
| Framework | |
High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimization
| Title | High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimization |
| Authors | Swaminathan Gurumurthy, Shubham Agrawal |
| Abstract | Semantic shape completion is a challenging problem in 3D computer vision where the task is to generate a complete 3D shape using a partial 3D shape as input. We propose a learning-based approach to complete incomplete 3D shapes through generative modeling and latent manifold optimization. Our algorithm works directly on point clouds. We use an autoencoder and a GAN to learn a distribution of embeddings for point clouds of object classes. An input point cloud with missing regions is first encoded to a feature vector. The representations learnt by the GAN are then used to find the best latent vector on the manifold using a combined optimization that finds a vector in the manifold of plausible vectors that is close to the original input (both in the feature space and the output space of the decoder). Experiments show that our algorithm is capable of successfully reconstructing point clouds with large missing regions with very high fidelity without having to rely on exemplar based database retrieval. |
| Tasks | |
| Published | 2018-07-09 |
| URL | http://arxiv.org/abs/1807.03407v2 |
| http://arxiv.org/pdf/1807.03407v2.pdf | |
| PWC | https://paperswithcode.com/paper/high-fidelity-semantic-shape-completion-for |
| Repo | |
| Framework | |
Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach
| Title | Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach |
| Authors | Loc Hoang Tran, Trang Hoang, Bui Hoang Nam Huynh |
| Abstract | Most network-based speech recognition methods are based on the assumption that the labels of two adjacent speech samples in the network are likely to be the same. However, assuming the pairwise relationship between speech samples is not complete. The information a group of speech samples that show very similar patterns and tend to have similar labels is missed. The natural way overcoming the information loss of the above assumption is to represent the feature data of speech samples as the hypergraph. Thus, in this paper, the three un-normalized, random walk, and symmetric normalized hypergraph Laplacian based semi-supervised learning methods applied to hypergraph constructed from the feature data of speech samples in order to predict the labels of speech samples are introduced. Experiment results show that the sensitivity performance measures of these three hypergraph Laplacian based semi-supervised learning methods are greater than the sensitivity performance measures of the Hidden Markov Model method (the current state of the art method applied to speech recognition problem) and graph based semi-supervised learning methods (i.e. the current state of the art network-based method for classification problems) applied to network created from the feature data of speech samples. |
| Tasks | Speech Recognition |
| Published | 2018-10-28 |
| URL | http://arxiv.org/abs/1810.12743v1 |
| http://arxiv.org/pdf/1810.12743v1.pdf | |
| PWC | https://paperswithcode.com/paper/hypergraph-based-semi-supervised-learning |
| Repo | |
| Framework | |
Particle identification in ground-based gamma-ray astronomy using convolutional neural networks
| Title | Particle identification in ground-based gamma-ray astronomy using convolutional neural networks |
| Authors | E. B. Postnikov, I. V. Bychkov, J. Y. Dubenskaya, O. L. Fedorov, Y. A. Kazarina, E. E. Korosteleva, A. P. Kryukov, A. A. Mikhailov, M. D. Nguyen, S. P. Polyakov, A. O. Shigarov, D. A. Shipilov, D. P. Zhurov |
| Abstract | Modern detectors of cosmic gamma-rays are a special type of imaging telescopes (air Cherenkov telescopes) supplied with cameras with a relatively large number of photomultiplier-based pixels. For example, the camera of the TAIGA-IACT telescope has 560 pixels of hexagonal structure. Images in such cameras can be analysed by deep learning techniques to extract numerous physical and geometrical parameters and/or for incoming particle identification. The most powerful deep learning technique for image analysis, the so-called convolutional neural network (CNN), was implemented in this study. Two open source libraries for machine learning, PyTorch and TensorFlow, were tested as possible software platforms for particle identification in imaging air Cherenkov telescopes. Monte Carlo simulation was performed to analyse images of gamma-rays and background particles (protons) as well as estimate identification accuracy. Further steps of implementation and improvement of this technique are discussed. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01551v1 |
| http://arxiv.org/pdf/1812.01551v1.pdf | |
| PWC | https://paperswithcode.com/paper/particle-identification-in-ground-based-gamma |
| Repo | |
| Framework | |
Agnostic Sample Compression for Linear Regression
| Title | Agnostic Sample Compression for Linear Regression |
| Authors | Steve Hanneke, Aryeh Kontorovich, Menachem Sadigurschi |
| Abstract | We obtain the first positive results for bounded sample compression in the agnostic regression setting. We show that for p in {1,infinity}, agnostic linear regression with $\ell_p$ loss admits a bounded sample compression scheme. Specifically, we exhibit efficient sample compression schemes for agnostic linear regression in $R^d$ of size $d+1$ under the $\ell_1$ loss and size $d+2$ under the $\ell_\infty$ loss. We further show that for every other $\ell_p$ loss (1 < p < infinity), there does not exist an agnostic compression scheme of bounded size. This refines and generalizes a negative result of David, Moran, and Yehudayoff (2016) for the $\ell_2$ loss. We close by posing a general open question: for agnostic regression with $\ell_1$ loss, does every function class admit a compression scheme of size equal to its pseudo-dimension? This question generalizes Warmuth’s classic sample compression conjecture for realizable-case classification (Warmuth, 2003). |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01864v1 |
| http://arxiv.org/pdf/1810.01864v1.pdf | |
| PWC | https://paperswithcode.com/paper/agnostic-sample-compression-for-linear |
| Repo | |
| Framework | |
Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
| Title | Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data |
| Authors | Dominik Linzner, Heinz Koeppl |
| Abstract | Continuous-time Bayesian networks (CTBNs) constitute a general and powerful framework for modeling continuous-time stochastic processes on networks. This makes them particularly attractive for learning the directed structures among interacting entities. However, if the available data is incomplete, one needs to simulate the prohibitively complex CTBN dynamics. Existing approximation techniques, such as sampling and low-order variational methods, either scale unfavorably in system size, or are unsatisfactory in terms of accuracy. Inspired by recent advances in statistical physics, we present a new approximation scheme based on cluster-variational methods significantly improving upon existing variational approximations. We can analytically marginalize the parameters of the approximate CTBN, as these are of secondary importance for structure learning. This recovers a scalable scheme for direct structure learning from incomplete and noisy time-series data. Our approach outperforms existing methods in terms of scalability. |
| Tasks | Time Series |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04294v4 |
| http://arxiv.org/pdf/1809.04294v4.pdf | |
| PWC | https://paperswithcode.com/paper/cluster-variational-approximations-for |
| Repo | |
| Framework | |
Community structure: A comparative evaluation of community detection methods
| Title | Community structure: A comparative evaluation of community detection methods |
| Authors | Vinh-Loc Dao, Cécile Bothorel, Philippe Lenca |
| Abstract | Discovering community structure in complex networks is a mature field since a tremendous number of community detection methods have been introduced in the literature. Nevertheless, it is still very challenging for practioners to determine which method would be suitable to get insights into the structural information of the networks they study. Many recent efforts have been devoted to investigating various quality scores of the community structure, but the problem of distinguishing between different types of communities is still open. In this paper, we propose a comparative, extensive and empirical study to investigate what types of communities many state-of-the-art and well-known community detection methods are producing. Specifically, we provide comprehensive analyses on computation time, community size distribution, a comparative evaluation of methods according to their optimisation schemes as well as a comparison of their partioning strategy through validation metrics. We process our analyses on a very large corpus of hundreds of networks from five different network categories and propose ways to classify community detection methods, helping a potential user to navigate the complex landscape of community detection. |
| Tasks | Community Detection |
| Published | 2018-12-14 |
| URL | https://arxiv.org/abs/1812.06598v4 |
| https://arxiv.org/pdf/1812.06598v4.pdf | |
| PWC | https://paperswithcode.com/paper/community-structure-a-comparative-evaluation |
| Repo | |
| Framework | |
Non-linear process convolutions for multi-output Gaussian processes
| Title | Non-linear process convolutions for multi-output Gaussian processes |
| Authors | Mauricio A. Álvarez, Wil O. C. Ward, Cristian Guarnizo |
| Abstract | The paper introduces a non-linear version of the process convolution formalism for building covariance functions for multi-output Gaussian processes. The non-linearity is introduced via Volterra series, one series per each output. We provide closed-form expressions for the mean function and the covariance function of the approximated Gaussian process at the output of the Volterra series. The mean function and covariance function for the joint Gaussian process are derived using formulae for the product moments of Gaussian variables. We compare the performance of the non-linear model against the classical process convolution approach in one synthetic dataset and two real datasets. |
| Tasks | Gaussian Processes |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.04632v2 |
| http://arxiv.org/pdf/1810.04632v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-linear-process-convolutions-for-multi |
| Repo | |
| Framework | |
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning
| Title | From Word to Sense Embeddings: A Survey on Vector Representations of Meaning |
| Authors | Jose Camacho-Collados, Mohammad Taher Pilehvar |
| Abstract | Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey focuses on the representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their major limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from the word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and applications for this type of representation, and provides an analysis of four of its important aspects: interpretability, sense granularity, adaptability to different domains and compositionality. |
| Tasks | |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.04032v3 |
| http://arxiv.org/pdf/1805.04032v3.pdf | |
| PWC | https://paperswithcode.com/paper/from-word-to-sense-embeddings-a-survey-on |
| Repo | |
| Framework | |
Energy Spatio-Temporal Pattern Prediction for Electric Vehicle Networks
| Title | Energy Spatio-Temporal Pattern Prediction for Electric Vehicle Networks |
| Authors | Qinglong Wang |
| Abstract | Information about the spatio-temporal pattern of electricity energy carried by EVs, instead of EVs themselves, is crucial for EVs to establish more effective and intelligent interactions with the smart grid. In this paper, we propose a framework for predicting the amount of the electricity energy stored by a large number of EVs aggregated within different city-scale regions, based on spatio-temporal pattern of the electricity energy. The spatial pattern is modeled via using a neural network based spatial predictor, while the temporal pattern is captured via using a linear-chain conditional random field (CRF) based temporal predictor. Two predictors are fed with spatial and temporal features respectively, which are extracted based on real trajectories data recorded in Beijing. Furthermore, we combine both predictors to build the spatio-temporal predictor, by using an optimal combination coefficient which minimizes the normalized mean square error (NMSE) of the predictions. The prediction performance is evaluated based on extensive experiments covering both spatial and temporal predictions, and the improvement achieved by the combined spatio-temporal predictor. The experiment results show that the NMSE of the spatio-temporal predictor is maintained below 0.1 for all investigate regions of Beijing. We further visualize the prediction and discuss the potential benefits can be brought to smart grid scheduling and EV charging by utilizing the proposed framework. |
| Tasks | |
| Published | 2018-02-14 |
| URL | http://arxiv.org/abs/1802.04931v1 |
| http://arxiv.org/pdf/1802.04931v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-spatio-temporal-pattern-prediction-for |
| Repo | |
| Framework | |
