July 28, 2019

2919 words 14 mins read

Paper Group ANR 280

Effective Image Differencing with ConvNets for Real-time Transient Hunting. Inducing Distant Supervision in Suggestion Mining through Part-of-Speech Embeddings. A Dual Sparse Decomposition Method for Image Denoising. HPatches: A benchmark and evaluation of handcrafted and learned local descriptors. Avoiding Your Teacher’s Mistakes: Training Neural …

Effective Image Differencing with ConvNets for Real-time Transient Hunting


Title	Effective Image Differencing with ConvNets for Real-time Transient Hunting
Authors	Nima Sedaghat, Ashish Mahabal
Abstract	Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying PSF, small brightness variations in many sources, as well as artifacts resulting from saturated stars, and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artifacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image subtraction pipeline – image registration, background subtraction, noise removal, psf matching, and subtraction – into a single real-time convolutional network. Once trained the method works lighteningly fast, and given that it does multiple steps at one go, the advantages for multi-CCD, fast surveys like ZTF and LSST are obvious.
Tasks	Image Registration
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01422v1
PDF	http://arxiv.org/pdf/1710.01422v1.pdf
PWC	https://paperswithcode.com/paper/effective-image-differencing-with-convnets
Repo
Framework

Inducing Distant Supervision in Suggestion Mining through Part-of-Speech Embeddings


Title	Inducing Distant Supervision in Suggestion Mining through Part-of-Speech Embeddings
Authors	Sapna Negi, Paul Buitelaar
Abstract	Mining suggestion expressing sentences from a given text is a less investigated sentence classification task, and therefore lacks hand labeled benchmark datasets. In this work, we propose and evaluate two approaches for distant supervision in suggestion mining. The distant supervision is obtained through a large silver standard dataset, constructed using the text from wikiHow and Wikipedia. Both the approaches use a LSTM based neural network architecture to learn a classification model for suggestion mining, but vary in their method to use the silver standard dataset. The first approach directly trains the classifier using this dataset, while the second approach only learns word embeddings from this dataset. In the second approach, we also learn POS embeddings, which interestingly gives the best classification accuracy.
Tasks	Sentence Classification, Word Embeddings
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07403v2
PDF	http://arxiv.org/pdf/1709.07403v2.pdf
PWC	https://paperswithcode.com/paper/inducing-distant-supervision-in-suggestion
Repo
Framework

A Dual Sparse Decomposition Method for Image Denoising


Title	A Dual Sparse Decomposition Method for Image Denoising
Authors	Hong Sun, Chen-guang Liu, Cheng-wei Sang
Abstract	This article addresses the image denoising problem in the situations of strong noise. We propose a dual sparse decomposition method. This method makes a sub-dictionary decomposition on the over-complete dictionary in the sparse decomposition. The sub-dictionary decomposition makes use of a novel criterion based on the occurrence frequency of atoms of the over-complete dictionary over the data set. The experimental results demonstrate that the dual-sparse-decomposition method surpasses state-of-art denoising performance in terms of both peak-signal-to-noise ratio and structural-similarity-index-metric, and also at subjective visual quality.
Tasks	Denoising, Image Denoising
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07063v1
PDF	http://arxiv.org/pdf/1704.07063v1.pdf
PWC	https://paperswithcode.com/paper/a-dual-sparse-decomposition-method-for-image
Repo
Framework

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors


Title	HPatches: A benchmark and evaluation of handcrafted and learned local descriptors
Authors	Vassileios Balntas, Karel Lenc, Andrea Vedaldi, Krystian Mikolajczyk
Abstract	In this paper, we propose a novel benchmark for evaluating local image descriptors. We demonstrate that the existing datasets and evaluation protocols do not specify unambiguously all aspects of evaluation, leading to ambiguities and inconsistencies in results reported in the literature. Furthermore, these datasets are nearly saturated due to the recent improvements in local descriptors obtained by learning them from large annotated datasets. Therefore, we introduce a new large dataset suitable for training and testing modern descriptors, together with strictly defined evaluation protocols in several tasks such as matching, retrieval and classification. This allows for more realistic, and thus more reliable comparisons in different application scenarios. We evaluate the performance of several state-of-the-art descriptors and analyse their properties. We show that a simple normalisation of traditional hand-crafted descriptors can boost their performance to the level of deep learning based descriptors within a realistic benchmarks evaluation.
Tasks
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05939v1
PDF	http://arxiv.org/pdf/1704.05939v1.pdf
PWC	https://paperswithcode.com/paper/hpatches-a-benchmark-and-evaluation-of
Repo
Framework

Avoiding Your Teacher’s Mistakes: Training Neural Networks with Controlled Weak Supervision


Title	Avoiding Your Teacher’s Mistakes: Training Neural Networks with Controlled Weak Supervision
Authors	Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
Abstract	Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or user click-through data for training. In a semi-supervised setting, we can use a large set of data with weak labels to pretrain a neural network and then fine-tune the parameters with a small amount of data with true labels. This feels intuitively sub-optimal as these two independent stages leave the model unaware about the varying label quality. What if we could somehow inform the model about the label quality? In this paper, we propose a semi-supervised learning method where we train two neural networks in a multi-task fashion: a “target network” and a “confidence network”. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that are weakly annotated. We propose to weight the gradient updates to the target network using the scores provided by the second confidence network, which is trained on a small amount of supervised data. Thus we avoid that the weight updates computed from noisy labels harm the quality of the target network model. We evaluate our learning strategy on two different tasks: document ranking and sentiment classification. The results demonstrate that our approach not only enhances the performance compared to the baselines but also speeds up the learning process from weak labels.
Tasks	Document Ranking, Sentiment Analysis
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00313v2
PDF	http://arxiv.org/pdf/1711.00313v2.pdf
PWC	https://paperswithcode.com/paper/avoiding-your-teachers-mistakes-training
Repo
Framework

Continuous Semantic Topic Embedding Model Using Variational Autoencoder


Title	Continuous Semantic Topic Embedding Model Using Variational Autoencoder
Authors	Namkyu Jung, Hyeong In Choi
Abstract	This paper proposes the continuous semantic topic embedding model (CSTEM) which finds latent topic variables in documents using continuous semantic distance function between the topics and the words by means of the variational autoencoder(VAE). The semantic distance could be represented by any symmetric bell-shaped geometric distance function on the Euclidean space, for which the Mahalanobis distance is used in this paper. In order for the semantic distance to perform more properly, we newly introduce an additional model parameter for each word to take out the global factor from this distance indicating how likely it occurs regardless of its topic. It certainly improves the problem that the Gaussian distribution which is used in previous topic model with continuous word embedding could not explain the semantic relation correctly and helps to obtain the higher topic coherence. Through the experiments with the dataset of 20 Newsgroup, NIPS papers and CNN/Dailymail corpus, the performance of the recent state-of-the-art models is accomplished by our model as well as generating topic embedding vectors which makes possible to observe where the topic vectors are embedded with the word vectors in the real Euclidean space and how the topics are related each other semantically.
Tasks
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08870v1
PDF	http://arxiv.org/pdf/1711.08870v1.pdf
PWC	https://paperswithcode.com/paper/continuous-semantic-topic-embedding-model
Repo
Framework

Auxiliary Objectives for Neural Error Detection Models


Title	Auxiliary Objectives for Neural Error Detection Models
Authors	Marek Rei, Helen Yannakoudakis
Abstract	We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing. Auxiliary costs provide the model with additional linguistic information, allowing it to learn general-purpose compositional features that can then be exploited for other objectives. Our experiments show that a joint learning approach trained with parallel labels on in-domain data improves performance over the previous best error detection system. While the resulting model has the same number of parameters, the additional objectives allow it to be optimised more efficiently and achieve better performance.
Tasks	Grammatical Error Detection
Published	2017-07-17
URL	http://arxiv.org/abs/1707.05227v1
PDF	http://arxiv.org/pdf/1707.05227v1.pdf
PWC	https://paperswithcode.com/paper/auxiliary-objectives-for-neural-error
Repo
Framework

Why we have switched from building full-fledged taxonomies to simply detecting hypernymy relations


Title	Why we have switched from building full-fledged taxonomies to simply detecting hypernymy relations
Authors	Jose Camacho-Collados
Abstract	The study of taxonomies and hypernymy relations has been extensive on the Natural Language Processing (NLP) literature. However, the evaluation of taxonomy learning approaches has been traditionally troublesome, as it mainly relies on ad-hoc experiments which are hardly reproducible and manually expensive. Partly because of this, current research has been lately focusing on the hypernymy detection task. In this paper we reflect on this trend, analyzing issues related to current evaluation procedures. Finally, we propose three potential avenues for future work so that is-a relations and resources based on them play a more important role in downstream NLP applications.
Tasks
Published	2017-03-12
URL	http://arxiv.org/abs/1703.04178v2
PDF	http://arxiv.org/pdf/1703.04178v2.pdf
PWC	https://paperswithcode.com/paper/why-we-have-switched-from-building-full
Repo
Framework

Learning and Evaluating Musical Features with Deep Autoencoders


Title	Learning and Evaluating Musical Features with Deep Autoencoders
Authors	Mason Bretan, Sageev Oore, Doug Eck, Larry Heck
Abstract	In this work we describe and evaluate methods to learn musical embeddings. Each embedding is a vector that represents four contiguous beats of music and is derived from a symbolic representation. We consider autoencoding-based methods including denoising autoencoders, and context reconstruction, and evaluate the resulting embeddings on a forward prediction and a classification task.
Tasks	Denoising
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04486v2
PDF	http://arxiv.org/pdf/1706.04486v2.pdf
PWC	https://paperswithcode.com/paper/learning-and-evaluating-musical-features-with
Repo
Framework

Probing for sparse and fast variable selection with model-based boosting


Title	Probing for sparse and fast variable selection with model-based boosting
Authors	Janek Thomas, Tobias Hepp, Andreas Mayr, Bernd Bischl
Abstract	We present a new variable selection method based on model-based gradient boosting and randomly permuted variables. Model-based boosting is a tool to fit a statistical model while performing variable selection at the same time. A drawback of the fitting lies in the need of multiple model fits on slightly altered data (e.g. cross-validation or bootstrap) to find the optimal number of boosting iterations and prevent overfitting. In our proposed approach, we augment the data set with randomly permuted versions of the true variables, so called shadow variables, and stop the step-wise fitting as soon as such a variable would be added to the model. This allows variable selection in a single fit of the model without requiring further parameter tuning. We show that our probing approach can compete with state-of-the-art selection methods like stability selection in a high-dimensional classification benchmark and apply it on gene expression data for the estimation of riboflavin production of Bacillus subtilis.
Tasks
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04561v1
PDF	http://arxiv.org/pdf/1702.04561v1.pdf
PWC	https://paperswithcode.com/paper/probing-for-sparse-and-fast-variable
Repo
Framework

Syntax-Preserving Belief Change Operators for Logic Programs


Title	Syntax-Preserving Belief Change Operators for Logic Programs
Authors	Sebastian Binnewies, Zhiqiang Zhuang, Kewen Wang, Bela Stantic
Abstract	Recent methods have adapted the well-established AGM and belief base frameworks for belief change to cover belief revision in logic programs. In this study here, we present two new sets of belief change operators for logic programs. They focus on preserving the explicit relationships expressed in the rules of a program, a feature that is missing in purely semantic approaches that consider programs only in their entirety. In particular, operators of the latter class fail to satisfy preservation and support, two important properties for belief change in logic programs required to ensure intuitive results. We address this shortcoming of existing approaches by introducing partial meet and ensconcement constructions for logic program belief change, which allow us to define syntax-preserving operators that satisfy preservation and support. Our work is novel in that our constructions not only preserve more information from a logic program during a change operation than existing ones, but they also facilitate natural definitions of contraction operators, the first in the field to the best of our knowledge. In order to evaluate the rationality of our operators, we translate the revision and contraction postulates from the AGM and belief base frameworks to the logic programming setting. We show that our operators fully comply with the belief base framework and formally state the interdefinability between our operators. We further propose an algorithm that is based on modularising a logic program to reduce partial meet and ensconcement revisions or contractions to performing the operation only on the relevant modules of that program. Finally, we compare our approach to two state-of-the-art logic program revision methods and demonstrate that our operators address the shortcomings of one and generalise the other method.
Tasks
Published	2017-03-15
URL	http://arxiv.org/abs/1703.04912v2
PDF	http://arxiv.org/pdf/1703.04912v2.pdf
PWC	https://paperswithcode.com/paper/syntax-preserving-belief-change-operators-for
Repo
Framework

Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses


Title	Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses
Authors	Chandrasekhar Bhagavatula, Chenchen Zhu, Khoa Luu, Marios Savvides
Abstract	Facial alignment involves finding a set of landmark points on an image with a known semantic meaning. However, this semantic meaning of landmark points is often lost in 2D approaches where landmarks are either moved to visible boundaries or ignored as the pose of the face changes. In order to extract consistent alignment points across large poses, the 3D structure of the face must be considered in the alignment step. However, extracting a 3D structure from a single 2D image usually requires alignment in the first place. We present our novel approach to simultaneously extract the 3D shape of the face and the semantically consistent 2D alignment through a 3D Spatial Transformer Network (3DSTN) to model both the camera projection matrix and the warping parameters of a 3D model. By utilizing a generic 3D model and a Thin Plate Spline (TPS) warping function, we are able to generate subject specific 3D shapes without the need for a large 3D shape basis. In addition, our proposed network can be trained in an end-to-end framework on entirely synthetic data from the 300W-LP dataset. Unlike other 3D methods, our approach only requires one pass through the network resulting in a faster than real-time alignment. Evaluations of our model on the Annotated Facial Landmarks in the Wild (AFLW) and AFLW2000-3D datasets show our method achieves state-of-the-art performance over other 3D approaches to alignment.
Tasks	Face Alignment
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05653v2
PDF	http://arxiv.org/pdf/1707.05653v2.pdf
PWC	https://paperswithcode.com/paper/faster-than-real-time-facial-alignment-a-3d
Repo
Framework

Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation


Title	Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation
Authors	Carolin Lawrence, Artem Sokolov, Stefan Riezler
Abstract	The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically log the most probable translation. The lack of sufficient exploration of the SMT output space seemingly contradicts the theoretical requirements for counterfactual learning. We show that counterfactual learning from deterministic bandit logs is possible nevertheless by smoothing out deterministic components in learning. This can be achieved by additive and multiplicative control variates that avoid degenerate behavior in empirical risk minimization. Our simulation experiments show improvements of up to 2 BLEU points by counterfactual learning from deterministic bandit feedback.
Tasks	Machine Translation
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09118v3
PDF	http://arxiv.org/pdf/1707.09118v3.pdf
PWC	https://paperswithcode.com/paper/counterfactual-learning-from-bandit-feedback
Repo
Framework

Elastic-net regularized High-dimensional Negative Binomial Regression: Consistency and Weak Signals Detection


Title	Elastic-net regularized High-dimensional Negative Binomial Regression: Consistency and Weak Signals Detection
Authors	Huiming Zhang, Jinzhu Jia
Abstract	We study sparse high-dimensional negative binomial regression problem for count data regression by showing non-asymptotic merits of the Elastic-net regularized estimator. With the KKT conditions, we derive two types of non-asymptotic oracle inequalities for the elastic net estimates of negative binomial regression by utilizing Compatibility factor and Stabil Condition, respectively. Based on oracle inequalities we proposed, we firstly show the sign consistency property of the Elastic-net estimators provided that the non-zero components in sparse true vector are large than a proper choice of the weakest signal detection threshold, and the second application is that we give an oracle inequality for bounding the grouping effect with high probability, thirdly, under some assumptions of design matrix, we can recover the true variable set with high probability if the weakest signal detection threshold is large than 3 times the value of turning parameter, at last, we briefly discuss the de-biased Elastic-net estimator.
Tasks
Published	2017-12-09
URL	http://arxiv.org/abs/1712.03412v2
PDF	http://arxiv.org/pdf/1712.03412v2.pdf
PWC	https://paperswithcode.com/paper/elastic-net-regularized-high-dimensional
Repo
Framework

Solving Non-parametric Inverse Problem in Continuous Markov Random Field using Loopy Belief Propagation


Title	Solving Non-parametric Inverse Problem in Continuous Markov Random Field using Loopy Belief Propagation
Authors	Muneki Yasuda, Shun Kataoka
Abstract	In this paper, we address the inverse problem, or the statistical machine learning problem, in Markov random fields with a non-parametric pair-wise energy function with continuous variables. The inverse problem is formulated by maximum likelihood estimation. The exact treatment of maximum likelihood estimation is intractable because of two problems: (1) it includes the evaluation of the partition function and (2) it is formulated in the form of functional optimization. We avoid Problem (1) by using Bethe approximation. Bethe approximation is an approximation technique equivalent to the loopy belief propagation. Problem (2) can be solved by using orthonormal function expansion. Orthonormal function expansion can reduce a functional optimization problem to a function optimization problem. Our method can provide an analytic form of the solution of the inverse problem within the framework of Bethe approximation.
Tasks
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09397v1
PDF	http://arxiv.org/pdf/1703.09397v1.pdf
PWC	https://paperswithcode.com/paper/solving-non-parametric-inverse-problem-in
Repo
Framework