April 2, 2020

3043 words 15 mins read

Paper Group ANR 247

Probabilistic Reasoning across the Causal Hierarchy. EDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation. Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network. Fashion Meets Computer Vision: A Survey. On Expert Behaviors and Question Types for Efficient Query-Based Ontol …

Probabilistic Reasoning across the Causal Hierarchy


Title	Probabilistic Reasoning across the Causal Hierarchy
Authors	Duligur Ibeling, Thomas Icard
Abstract	We propose a formalization of the three-tier causal hierarchy of association, intervention, and counterfactuals as a series of probabilistic logical languages. Our languages are of strictly increasing expressivity, the first capable of expressing quantitative probabilistic reasoning—including conditional independence and Bayesian inference—the second encoding do-calculus reasoning for causal effects, and the third capturing a fully expressive do-calculus for arbitrary counterfactual queries. We give a corresponding series of finitary axiomatizations complete over both structural causal models and probabilistic programs, and show that satisfiability and validity for each language are decidable in polynomial space.
Tasks	Bayesian Inference
Published	2020-01-09
URL	https://arxiv.org/abs/2001.02889v2
PDF	https://arxiv.org/pdf/2001.02889v2.pdf
PWC	https://paperswithcode.com/paper/probabilistic-reasoning-across-the-causal
Repo
Framework

EDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation


Title	EDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation
Authors	Somenath Kuiry, Nibaran Das, Alaka Das, Mita Nasipuri
Abstract	In the literature, many fusion techniques are registered for the segmentation of images, but they primarily focus on observed output or belief score or probability score of the output classes. In the present work, we have utilized inter source statistical dependency among different classifiers for ensembling of different deep learning techniques for semantic segmentation of images. For this purpose, in the present work, a class-wise Copula-based ensembling method is newly proposed for solving the multi-class segmentation problem. Experimentally, it is observed that the performance has improved more for semantic image segmentation using the proposed class-specific Copula function than the traditionally used single Copula function for the problem. The performance is also compared with three state-of-the-art ensembling methods.
Tasks	Semantic Segmentation
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05710v1
PDF	https://arxiv.org/pdf/2003.05710v1.pdf
PWC	https://paperswithcode.com/paper/edc3-ensemble-of-deep-classifiers-using-class
Repo
Framework

Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network


Title	Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network
Authors	Yuanyuan Jin, Wei Zhang, Xiangnan He, Xinyu Wang, Xiaoling Wang
Abstract	Herb recommendation plays a crucial role in the therapeutic process of Traditional Chinese Medicine(TCM), which aims to recommend a set of herbs to treat the symptoms of a patient. While several machine learning methods have been developed for herb recommendation, they are limited in modeling only the interactions between herbs and symptoms, and ignoring the intermediate process of syndrome induction. When performing TCM diagnostics, an experienced doctor typically induces syndromes from the patient’s symptoms and then suggests herbs based on the induced syndromes. As such, we believe the induction of syndromes, an overall description of the symptoms, is important for herb recommendation and should be properly handled. However, due to the ambiguity and complexity of syndrome induction, most prescriptions lack the explicit ground truth of syndromes. In this paper, we propose a new method that takes the implicit syndrome induction process into account for herb recommendation. Given a set of symptoms to treat, we aim to generate an overall syndrome representation by effectively fusing the embeddings of all the symptoms in the set, to mimic how a doctor induces the syndromes. Towards symptom embedding learning, we additionally construct a symptom-symptom graph from the input prescriptions for capturing the relations between symptoms; we then build graph convolution networks(GCNs) on both symptom-symptom and symptom-herb graphs to learn symptom embedding. Similarly, we construct a herb-herb graph and build GCNs on both herb-herb and symptom-herb graphs to learn herb embedding, which is finally interacted with the syndrome representation to predict the scores of herbs. In this way, more comprehensive representations can be obtained. We conduct extensive experiments on a public TCM dataset, showing significant improvements over state-of-the-art herb recommendation methods.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08575v1
PDF	https://arxiv.org/pdf/2002.08575v1.pdf
PWC	https://paperswithcode.com/paper/syndrome-aware-herb-recommendation-with-multi
Repo
Framework

Fashion Meets Computer Vision: A Survey


Title	Fashion Meets Computer Vision: A Survey
Authors	Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
Abstract	Fashion is the way we present ourselves to the world and has become one of the world’s largest industries. Fashion, mainly conveyed by vision, has thus attracted much attention from computer vision researchers in recent years. Given the rapid development, this paper provides a comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion: (1) Fashion detection includes landmark detection, fashion parsing, and item retrieval, (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction, (3) Fashion synthesis involves style transfer, pose transformation, and physical simulation, and (4) Fashion recommendation comprises fashion compatibility, outfit matching, and hairstyle suggestion. For each task, the benchmark datasets and the evaluation protocols are summarized. Furthermore, we highlight promising directions for future research.
Tasks	Style Transfer
Published	2020-03-31
URL	https://arxiv.org/abs/2003.13988v1
PDF	https://arxiv.org/pdf/2003.13988v1.pdf
PWC	https://paperswithcode.com/paper/fashion-meets-computer-vision-a-survey
Repo
Framework

On Expert Behaviors and Question Types for Efficient Query-Based Ontology Fault Localization


Title	On Expert Behaviors and Question Types for Efficient Query-Based Ontology Fault Localization
Authors	Patrick Rodler
Abstract	We challenge existing query-based ontology fault localization methods wrt. assumptions they make, criteria they optimize, and interaction means they use. We find that their efficiency depends largely on the behavior of the interacting expert, that performed calculations can be inefficient or imprecise, and that used optimization criteria are often not fully realistic. As a remedy, we suggest a novel (and simpler) interaction approach which overcomes all identified problems and, in comprehensive experiments on faulty real-world ontologies, enables a successful fault localization while requiring fewer expert interactions in 66 % of the cases, and always at least 80 % less expert waiting time, compared to existing methods.
Tasks
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05952v1
PDF	https://arxiv.org/pdf/2001.05952v1.pdf
PWC	https://paperswithcode.com/paper/on-expert-behaviors-and-question-types-for
Repo
Framework

A Generative Adversarial Network for AI-Aided Chair Design


Title	A Generative Adversarial Network for AI-Aided Chair Design
Authors	Zhibo Liu, Feng Gao, Yizhou Wang
Abstract	We present a method for improving human design of chairs. The goal of the method is generating enormous chair candidates in order to facilitate human designer by creating sketches and 3d models accordingly based on the generated chair design. It consists of an image synthesis module, which learns the underlying distribution of training dataset, a super-resolution module, which improve quality of generated image and human involvements. Finally, we manually pick one of the generated candidates to create a real life chair for illustration.
Tasks	Image Generation, Super-Resolution
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11715v1
PDF	https://arxiv.org/pdf/2001.11715v1.pdf
PWC	https://paperswithcode.com/paper/a-generative-adversarial-network-for-ai-aided
Repo
Framework

Estimation of Accurate and Calibrated Uncertainties in Deterministic models


Title	Estimation of Accurate and Calibrated Uncertainties in Deterministic models
Authors	Enrico Camporeale, Algo Carè
Abstract	In this paper we focus on the problem of assigning uncertainties to single-point predictions generated by a deterministic model that outputs a continuous variable. This problem applies to any state-of-the-art physics or engineering models that have a computational cost that does not readily allow to run ensembles and to estimate the uncertainty associated to single-point predictions. Essentially, we devise a method to easily transform a deterministic prediction into a probabilistic one. We show that for doing so, one has to compromise between the accuracy and the reliability (calibration) of such a probabilistic model. Hence, we introduce a cost function that encodes their trade-off. We use the Continuous Rank Probability Score to measure accuracy and we derive an analytic formula for the reliability, in the case of forecasts of continuous scalar variables expressed in terms of Gaussian distributions. The new Accuracy-Reliability cost function is then used to estimate the input-dependent variance, given a black-box mean function, by solving a two-objective optimization problem. The simple philosophy behind this strategy is that predictions based on the estimated variances should not only be accurate, but also reliable (i.e. statistical consistent with observations). Conversely, early works based on the minimization of classical cost functions, such as the negative log probability density, cannot simultaneously enforce both accuracy and reliability. We show several examples both with synthetic data, where the underlying hidden noise can accurately be recovered, and with large real-world datasets.
Tasks	Calibration
Published	2020-03-11
URL	https://arxiv.org/abs/2003.05103v1
PDF	https://arxiv.org/pdf/2003.05103v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-accurate-and-calibrated
Repo
Framework

Proximity Preserving Binary Code using Signed Graph-Cut


Title	Proximity Preserving Binary Code using Signed Graph-Cut
Authors	Inbal Lav, Shai Avidan, Yoram Singer, Yacov Hel-Or
Abstract	We introduce a binary embedding framework, called Proximity Preserving Code (PPC), which learns similarity and dissimilarity between data points to create a compact and affinity-preserving binary code. This code can be used to apply fast and memory-efficient approximation to nearest-neighbor searches. Our framework is flexible, enabling different proximity definitions between data points. In contrast to previous methods that extract binary codes based on unsigned graph partitioning, our system models the attractive and repulsive forces in the data by incorporating positive and negative graph weights. The proposed framework is shown to boil down to finding the minimal cut of a signed graph, a problem known to be NP-hard. We offer an efficient approximation and achieve superior results by constructing the code bit after bit. We show that the proposed approximation is superior to the commonly used spectral methods with respect to both accuracy and complexity. Thus, it is useful for many other problems that can be translated into signed graph cut.
Tasks	graph partitioning
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01793v1
PDF	https://arxiv.org/pdf/2002.01793v1.pdf
PWC	https://paperswithcode.com/paper/proximity-preserving-binary-code-using-signed
Repo
Framework

Structural Information Learning Machinery: Learning from Observing, Associating, Optimizing, Decoding, and Abstracting


Title	Structural Information Learning Machinery: Learning from Observing, Associating, Optimizing, Decoding, and Abstracting
Authors	Angsheng Li
Abstract	In the present paper, we propose the model of {\it structural information learning machines} (SiLeM for short), leading to a mathematical definition of learning by merging the theories of computation and information. Our model shows that the essence of learning is {\it to gain information}, that to gain information is {\it to eliminate uncertainty} embedded in a data space, and that to eliminate uncertainty of a data space can be reduced to an optimization problem, that is, an {\it information optimization problem}, which can be realized by a general {\it encoding tree method}. The principle and criterion of the structural information learning machines are maximization of {\it decoding information} from the data points observed together with the relationships among the data points, and semantical {\it interpretation} of syntactical {\it essential structure}, respectively. A SiLeM machine learns the laws or rules of nature. It observes the data points of real world, builds the {\it connections} among the observed data and constructs a {\it data space}, for which the principle is to choose the way of connections of data points so that the {\it decoding information} of the data space is maximized, finds the {\it encoding tree} of the data space that minimizes the dynamical uncertainty of the data space, in which the encoding tree is hence referred to as a {\it decoder}, due to the fact that it has already eliminated the maximum amount of uncertainty embedded in the data space, interprets the {\it semantics} of the decoder, an encoding tree, to form a {\it knowledge tree}, extracts the {\it remarkable common features} for both semantical and syntactical features of the modules decoded by a decoder to construct {\it trees of abstractions}, providing the foundations for {\it intuitive reasoning} in the learning when new data are observed.
Tasks
Published	2020-01-27
URL	https://arxiv.org/abs/2001.09637v1
PDF	https://arxiv.org/pdf/2001.09637v1.pdf
PWC	https://paperswithcode.com/paper/structural-information-learning-machinery
Repo
Framework

Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks


Title	Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks
Authors	Woojay Jeon, Leo Liu, Henry Mason
Abstract	We propose a method to reduce false voice triggers of a speech-enabled personal assistant by post-processing the hypothesis lattice of a server-side large-vocabulary continuous speech recognizer (LVCSR) via a neural network. We first discuss how an estimate of the posterior probability of the trigger phrase can be obtained from the hypothesis lattice using known techniques to perform detection, then investigate a statistical model that processes the lattice in a more explicitly data-driven, discriminative manner. We propose using a Bidirectional Lattice Recurrent Neural Network (LatticeRNN) for the task, and show that it can significantly improve detection accuracy over using the 1-best result or the posterior.
Tasks	Large Vocabulary Continuous Speech Recognition
Published	2020-02-29
URL	https://arxiv.org/abs/2003.00304v1
PDF	https://arxiv.org/pdf/2003.00304v1.pdf
PWC	https://paperswithcode.com/paper/voice-trigger-detection-from-lvcsr-hypothesis
Repo
Framework

Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs


Title	Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs
Authors	Anton Tsitsulin, Marina Munkhoeva, Bryan Perozzi
Abstract	Graph comparison is a fundamental operation in data mining and information retrieval. Due to the combinatorial nature of graphs, it is hard to balance the expressiveness of the similarity measure and its scalability. Spectral analysis provides quintessential tools for studying the multi-scale structure of graphs and is a well-suited foundation for reasoning about differences between graphs. However, computing full spectrum of large graphs is computationally prohibitive; thus, spectral graph comparison methods often rely on rough approximation techniques with weak error guarantees. In this work, we propose SLaQ, an efficient and effective approximation technique for computing spectral distances between graphs with billions of nodes and edges. We derive the corresponding error bounds and demonstrate that accurate computation is possible in time linear in the number of graph edges. In a thorough experimental evaluation, we show that SLaQ outperforms existing methods, oftentimes by several orders of magnitude in approximation accuracy, and maintains comparable performance, allowing to compare million-scale graphs in a matter of minutes on a single machine.
Tasks	Information Retrieval
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01282v1
PDF	https://arxiv.org/pdf/2003.01282v1.pdf
PWC	https://paperswithcode.com/paper/just-slaq-when-you-approximate-accurate
Repo
Framework

LIMP: Learning Latent Shape Representations with Metric Preservation Priors


Title	LIMP: Learning Latent Shape Representations with Metric Preservation Priors
Authors	Luca Cosmo, Antonio Norelli, Oshri Halimi, Ron Kimmel, Emanuele Rodolà
Abstract	In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes. Key to our construction is the introduction of a geometric distortion criterion, defined directly on the decoded shapes, translating the preservation of the metric on the decoding to the formation of linear paths in the underlying latent space. Our rationale lies in the observation that training samples alone are often insufficient to endow generative models with high fidelity, motivating the need for large training datasets. In contrast, metric preservation provides a rigorous way to control the amount of geometric distortion incurring in the construction of the latent space, leading in turn to synthetic samples of higher quality. We further demonstrate, for the first time, the adoption of differentiable intrinsic distances in the backpropagation of a geodesic loss. Our geometric priors are particularly relevant in the presence of scarce training data, where learning any meaningful latent structure can be especially challenging. The effectiveness and potential of our generative model is showcased in applications of style transfer, content generation, and shape completion.
Tasks	Style Transfer
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12283v1
PDF	https://arxiv.org/pdf/2003.12283v1.pdf
PWC	https://paperswithcode.com/paper/limp-learning-latent-shape-representations
Repo
Framework

Deformable Style Transfer


Title	Deformable Style Transfer
Authors	Sunnie S. Y. Kim, Nicholas Kolkin, Jason Salavon, Gregory Shakhnarovich
Abstract	Geometry and shape are fundamental aspects of visual style. Existing style transfer methods focus on texture-like components of style, ignoring geometry. We propose deformable style transfer (DST), an optimization-based approach that integrates texture and geometry style transfer. Our method is the first to allow geometry-aware stylization not restricted to any domain and not requiring training sets of matching style/content pairs. We demonstrate our method on a diverse set of content and style images including portraits, animals, objects, scenes, and paintings.
Tasks	Style Transfer
Published	2020-03-24
URL	https://arxiv.org/abs/2003.11038v1
PDF	https://arxiv.org/pdf/2003.11038v1.pdf
PWC	https://paperswithcode.com/paper/deformable-style-transfer
Repo
Framework

Toward Enabling a Reliable Quality Monitoring System for Additive Manufacturing Process using Deep Convolutional Neural Networks


Title	Toward Enabling a Reliable Quality Monitoring System for Additive Manufacturing Process using Deep Convolutional Neural Networks
Authors	Yaser Banadaki, Nariman Razaviarab, Hadi Fekrmandi, Safura Sharifi
Abstract	Additive Manufacturing (AM) is a crucial component of the smart industry. In this paper, we propose an automated quality grading system for the AM process using a deep convolutional neural network (CNN) model. The CNN model is trained offline using the images of the internal and surface defects in the layer-by-layer deposition of materials and tested online by studying the performance of detecting and classifying the failure in AM process at different extruder speeds and temperatures. The model demonstrates the accuracy of 94% and specificity of 96%, as well as above 75% in three classifier measures of the Fscore, the sensitivity, and precision for classifying the quality of the printing process in five grades in real-time. The proposed online model adds an automated, consistent, and non-contact quality control signal to the AM process that eliminates the manual inspection of parts after they are entirely built. The quality monitoring signal can also be used by the machine to suggest remedial actions by adjusting the parameters in real-time. The proposed quality predictive model serves as a proof-of-concept for any type of AM machines to produce reliable parts with fewer quality hiccups while limiting the waste of both time and materials.
Tasks
Published	2020-03-06
URL	https://arxiv.org/abs/2003.08749v1
PDF	https://arxiv.org/pdf/2003.08749v1.pdf
PWC	https://paperswithcode.com/paper/toward-enabling-a-reliable-quality-monitoring
Repo
Framework

Temporal Tensor Transformation Network for Multivariate Time Series Prediction


Title	Temporal Tensor Transformation Network for Multivariate Time Series Prediction
Authors	Yuya Jeremy Ong, Mu Qiao, Divyesh Jadav
Abstract	Multivariate time series prediction has applications in a wide variety of domains and is considered to be a very challenging task, especially when the variables have correlations and exhibit complex temporal patterns, such as seasonality and trend. Many existing methods suffer from strong statistical assumptions, numerical issues with high dimensionality, manual feature engineering efforts, and scalability. In this work, we present a novel deep learning architecture, known as Temporal Tensor Transformation Network, which transforms the original multivariate time series into a higher order of tensor through the proposed Temporal-Slicing Stack Transformation. This yields a new representation of the original multivariate time series, which enables the convolution kernel to extract complex and non-linear features as well as variable interactional signals from a relatively large temporal region. Experimental results show that Temporal Tensor Transformation Network outperforms several state-of-the-art methods on window-based predictions across various tasks. The proposed architecture also demonstrates robust prediction performance through an extensive sensitivity analysis.
Tasks	Feature Engineering, Time Series, Time Series Prediction
Published	2020-01-04
URL	https://arxiv.org/abs/2001.01051v1
PDF	https://arxiv.org/pdf/2001.01051v1.pdf
PWC	https://paperswithcode.com/paper/temporal-tensor-transformation-network-for
Repo
Framework