May 6, 2019

3002 words 15 mins read

Paper Group ANR 409

Scalable Linear Causal Inference for Irregularly Sampled Time Series with Long Range Dependencies. Sampled Image Tagging and Retrieval Methods on User Generated Content. DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns. Adaptive mixed norm optical flow estimation. DeepText: A Unified Framework for Text Proposal Generation and Text …

Scalable Linear Causal Inference for Irregularly Sampled Time Series with Long Range Dependencies


Title	Scalable Linear Causal Inference for Irregularly Sampled Time Series with Long Range Dependencies
Authors	Francois W. Belletti, Evan R. Sparks, Michael J. Franklin, Alexandre M. Bayen, Joseph E. Gonzalez
Abstract	Linear causal analysis is central to a wide range of important application spanning finance, the physical sciences, and engineering. Much of the existing literature in linear causal analysis operates in the time domain. Unfortunately, the direct application of time domain linear causal analysis to many real-world time series presents three critical challenges: irregular temporal sampling, long range dependencies, and scale. Moreover, real-world data is often collected at irregular time intervals across vast arrays of decentralized sensors and with long range dependencies which make naive time domain correlation estimators spurious. In this paper we present a frequency domain based estimation framework which naturally handles irregularly sampled data and long range dependencies while enabled memory and communication efficient distributed processing of time series data. By operating in the frequency domain we eliminate the need to interpolate and help mitigate the effects of long range dependencies. We implement and evaluate our new work-flow in the distributed setting using Apache Spark and demonstrate on both Monte Carlo simulations and high-frequency financial trading that we can accurately recover causal structure at scale.
Tasks	Causal Inference, Time Series
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03336v1
PDF	http://arxiv.org/pdf/1603.03336v1.pdf
PWC	https://paperswithcode.com/paper/scalable-linear-causal-inference-for
Repo
Framework

Sampled Image Tagging and Retrieval Methods on User Generated Content


Title	Sampled Image Tagging and Retrieval Methods on User Generated Content
Authors	Karl Ni, Kyle Zaragoza, Charles Foster, Carmen Carrano, Barry Chen, Yonas Tesfaye, Alex Gude
Abstract	Traditional image tagging and retrieval algorithms have limited value as a result of being trained with heavily curated datasets. These limitations are most evident when arbitrary search words are used that do not intersect with training set labels. Weak labels from user generated content (UGC) found in the wild (e.g., Google Photos, FlickR, etc.) have an almost unlimited number of unique words in the metadata tags. Prior work on word embeddings successfully leveraged unstructured text with large vocabularies, and our proposed method seeks to apply similar cost functions to open source imagery. Specifically, we train a deep learning image tagging and retrieval system on large scale, user generated content (UGC) using sampling methods and joint optimization of word embeddings. By using the Yahoo! FlickR Creative Commons (YFCC100M) dataset, such an approach builds robustness to common unstructured data issues that include but are not limited to irrelevant tags, misspellings, multiple languages, polysemy, and tag imbalance. As a result, the final proposed algorithm will not only yield comparable results to state of the art in conventional image tagging, but will enable new capability to train algorithms on large, scale unstructured text in the YFCC100M dataset and outperform cited work in zero-shot capability.
Tasks	Word Embeddings
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06962v3
PDF	http://arxiv.org/pdf/1611.06962v3.pdf
PWC	https://paperswithcode.com/paper/sampled-image-tagging-and-retrieval-methods
Repo
Framework

DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns


Title	DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
Authors	Ali Diba, Ali Mohammad Pazandeh, Hamed Pirsiavash, Luc Van Gool
Abstract	The recognition of human actions and the determination of human attributes are two tasks that call for fine-grained classification. Indeed, often rather small and inconspicuous objects and features have to be detected to tell their classes apart. In order to deal with this challenge, we propose a novel convolutional neural network that mines mid-level image patches that are sufficiently dedicated to resolve the corresponding subtleties. In particular, we train a newly de- signed CNN (DeepPattern) that learns discriminative patch groups. There are two innovative aspects to this. On the one hand we pay attention to contextual information in an origi- nal fashion. On the other hand, we let an iteration of feature learning and patch clustering purify the set of dedicated patches that we use. We validate our method for action clas- sification on two challenging datasets: PASCAL VOC 2012 Action and Stanford 40 Actions, and for attribute recogni- tion we use the Berkeley Attributes of People dataset. Our discriminative mid-level mining CNN obtains state-of-the- art results on these datasets, without a need for annotations about parts and poses.
Tasks
Published	2016-08-10
URL	http://arxiv.org/abs/1608.03217v1
PDF	http://arxiv.org/pdf/1608.03217v1.pdf
PWC	https://paperswithcode.com/paper/deepcamp-deep-convolutional-action-attribute
Repo
Framework

Adaptive mixed norm optical flow estimation


Title	Adaptive mixed norm optical flow estimation
Authors	Vania V. Estrela, Matthias O. Franz, Ricardo T. Lopes, G. P. De Araujo
Abstract	The pel-recursive computation of 2-D optical flow has been extensively studied in computer vision to estimate motion from image sequences, but it still raises a wealth of issues, such as the treatment of outliers, motion discontinuities and occlusion. It relies on spatio-temporal brightness variations due to motion. Our proposed adaptive regularized approach deals with these issues within a common framework. It relies on the use of a data-driven technique called Mixed Norm (MN) to estimate the best motion vector for a given pixel. In our model, various types of noise can be handled, representing different sources of error. The motion vector estimation takes into consideration local image properties and it results from the minimization of a mixed norm functional with a regularization parameter depending on the kurtosis. This parameter determines the relative importance of the fourth norm and makes the functional convex. The main advantage of the developed procedure is that no knowledge of the noise distribution is necessary. Experiments indicate that this approach provides robust estimates of the optical flow.
Tasks	Optical Flow Estimation
Published	2016-11-03
URL	http://arxiv.org/abs/1611.00960v1
PDF	http://arxiv.org/pdf/1611.00960v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-mixed-norm-optical-flow-estimation
Repo
Framework

DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images


Title	DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
Authors	Zhuoyao Zhong, Lianwen Jin, Shuye Zhang, Ziyong Feng
Abstract	In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN). First, we propose the inception region proposal network (Inception-RPN) and design a set of text characteristic prior bounding boxes to achieve high word recall with only hundred level candidate proposals. Next, we present a powerful textdetection network that embeds ambiguous text category (ATC) information and multilevel region-of-interest pooling (MLRP) for text and non-text classification and accurate localization. Finally, we apply an iterative bounding box voting scheme to pursue high recall in a complementary manner and introduce a filtering algorithm to retain the most suitable bounding box, while removing redundant inner and outer boxes for each text instance. Our approach achieves an F-measure of 0.83 and 0.85 on the ICDAR 2011 and 2013 robust text detection benchmarks, outperforming previous state-of-the-art results.
Tasks	Text Classification
Published	2016-05-24
URL	http://arxiv.org/abs/1605.07314v1
PDF	http://arxiv.org/pdf/1605.07314v1.pdf
PWC	https://paperswithcode.com/paper/deeptext-a-unified-framework-for-text
Repo
Framework

MDL-motivated compression of GLM ensembles increases interpretability and retains predictive power


Title	MDL-motivated compression of GLM ensembles increases interpretability and retains predictive power
Authors	Boris Hayete, Matthew Valko, Alex Greenfield, Raymond Yan
Abstract	Over the years, ensemble methods have become a staple of machine learning. Similarly, generalized linear models (GLMs) have become very popular for a wide variety of statistical inference tasks. The former have been shown to enhance out- of-sample predictive power and the latter possess easy interpretability. Recently, ensembles of GLMs have been proposed as a possibility. On the downside, this approach loses the interpretability that GLMs possess. We show that minimum description length (MDL)-motivated compression of the inferred ensembles can be used to recover interpretability without much, if any, downside to performance and illustrate on a number of standard classification data sets.
Tasks
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06800v1
PDF	http://arxiv.org/pdf/1611.06800v1.pdf
PWC	https://paperswithcode.com/paper/mdl-motivated-compression-of-glm-ensembles
Repo
Framework

Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangian


Title	Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangian
Authors	Victor Picheny, Robert B. Gramacy, Stefan M. Wild, Sebastien Le Digabel
Abstract	An augmented Lagrangian (AL) can convert a constrained optimization problem into a sequence of simpler (e.g., unconstrained) problems, which are then usually solved with local solvers. Recently, surrogate-based Bayesian optimization (BO) sub-solvers have been successfully deployed in the AL framework for a more global search in the presence of inequality constraints; however, a drawback was that expected improvement (EI) evaluations relied on Monte Carlo. Here we introduce an alternative slack variable AL, and show that in this formulation the EI may be evaluated with library routines. The slack variables furthermore facilitate equality as well as inequality constraints, and mixtures thereof. We show how our new slack “ALBO” compares favorably to the original. Its superiority over conventional alternatives is reinforced on several mixed constraint examples.
Tasks
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09466v1
PDF	http://arxiv.org/pdf/1605.09466v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-under-mixed-constraints
Repo
Framework

Image Captioning and Visual Question Answering Based on Attributes and External Knowledge


Title	Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
Authors	Qi Wu, Chunhua Shen, Anton van den Hengel, Peng Wang, Anthony Dick
Abstract	Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism can be used to incorporate external knowledge, which is critically important for answering high level visual questions. Specifically, we design a visual question answering model that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain a complete answer. Our final model achieves the best reported results on both image captioning and visual question answering on several benchmark datasets.
Tasks	Image Captioning, Question Answering, Visual Question Answering
Published	2016-03-09
URL	http://arxiv.org/abs/1603.02814v2
PDF	http://arxiv.org/pdf/1603.02814v2.pdf
PWC	https://paperswithcode.com/paper/image-captioning-and-visual-question
Repo
Framework

Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation


Title	Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation
Authors	Mehran Javanmardi, Mehdi Sajjadi, Ting Liu, Tolga Tasdizen
Abstract	We introduce a novel unsupervised loss function for learning semantic segmentation with deep convolutional neural nets (ConvNet) when densely labeled training images are not available. More specifically, the proposed loss function penalizes the L1-norm of the gradient of the label probability vector image , i.e. total variation, produced by the ConvNet. This can be seen as a regularization term that promotes piecewise smoothness of the label probability vector image produced by the ConvNet during learning. The unsupervised loss function is combined with a supervised loss in a semi-supervised setting to learn ConvNets that can achieve high semantic segmentation accuracy even when only a tiny percentage of the pixels in the training images are labeled. We demonstrate significant improvements over the purely supervised setting in the Weizmann horse, Stanford background and Sift Flow datasets. Furthermore, we show that using the proposed piecewise smoothness constraint in the learning phase significantly outperforms post-processing results from a purely supervised approach with Markov Random Fields (MRF). Finally, we note that the framework we introduce is general and can be used to learn to label other types of structures such as curvilinear structures by modifying the unsupervised loss function accordingly.
Tasks	Semantic Segmentation
Published	2016-05-04
URL	http://arxiv.org/abs/1605.01368v3
PDF	http://arxiv.org/pdf/1605.01368v3.pdf
PWC	https://paperswithcode.com/paper/unsupervised-total-variation-loss-for-semi
Repo
Framework

A Web-based Tool for Identifying Strategic Intervention Points in Complex Systems


Title	A Web-based Tool for Identifying Strategic Intervention Points in Complex Systems
Authors	Sotiris Moschoyiannis, Nicholas Elia, Alexandra S. Penn, David J. B. Lloyd, Chris Knight
Abstract	Steering a complex system towards a desired outcome is a challenging task. The lack of clarity on the system’s exact architecture and the often scarce scientific data upon which to base the operationalisation of the dynamic rules that underpin the interactions between participant entities are two contributing factors. We describe an analytical approach that builds on Fuzzy Cognitive Mapping (FCM) to address the latter and represent the system as a complex network. We apply results from network controllability to address the former and determine minimal control configurations - subsets of factors, or system levers, which comprise points for strategic intervention in steering the system. We have implemented the combination of these techniques in an analytical tool that runs in the browser, and generates all minimal control configurations of a complex network. We demonstrate our approach by reporting on our experience of working alongside industrial, local-government, and NGO stakeholders in the Humber region, UK. Our results are applied to the decision-making process involved in the transition of the region to a bio-based economy.
Tasks	Decision Making
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00655v1
PDF	http://arxiv.org/pdf/1608.00655v1.pdf
PWC	https://paperswithcode.com/paper/a-web-based-tool-for-identifying-strategic
Repo
Framework

Topic Browsing for Research Papers with Hierarchical Latent Tree Analysis


Title	Topic Browsing for Research Papers with Hierarchical Latent Tree Analysis
Authors	Leonard K. M. Poon, Nevin L. Zhang
Abstract	Academic researchers often need to face with a large collection of research papers in the literature. This problem may be even worse for postgraduate students who are new to a field and may not know where to start. To address this problem, we have developed an online catalog of research papers where the papers have been automatically categorized by a topic model. The catalog contains 7719 papers from the proceedings of two artificial intelligence conferences from 2000 to 2015. Rather than the commonly used Latent Dirichlet Allocation, we use a recently proposed method called hierarchical latent tree analysis for topic modeling. The resulting topic model contains a hierarchy of topics so that users can browse the topics from the top level to the bottom level. The topic model contains a manageable number of general topics at the top level and allows thousands of fine-grained topics at the bottom level. It also can detect topics that have emerged recently.
Tasks
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09188v1
PDF	http://arxiv.org/pdf/1609.09188v1.pdf
PWC	https://paperswithcode.com/paper/topic-browsing-for-research-papers-with
Repo
Framework

hdm: High-Dimensional Metrics


Title	hdm: High-Dimensional Metrics
Authors	Victor Chernozhukov, Chris Hansen, Martin Spindler
Abstract	In this article the package High-dimensional Metrics (\texttt{hdm}) is introduced. It is a collection of statistical methods for estimation and quantification of uncertainty in high-dimensional approximately sparse models. It focuses on providing confidence intervals and significance testing for (possibly many) low-dimensional subcomponents of the high-dimensional parameter vector. Efficient estimators and uniformly valid confidence intervals for regression coefficients on target variables (e.g., treatment or policy variable) in a high-dimensional approximately sparse regression model, for average treatment effect (ATE) and average treatment effect for the treated (ATET), as well for extensions of these parameters to the endogenous setting are provided. Theory grounded, data-driven methods for selecting the penalization parameter in Lasso regressions under heteroscedastic and non-Gaussian errors are implemented. Moreover, joint/ simultaneous confidence intervals for regression coefficients of a high-dimensional sparse regression are implemented. Data sets which have been used in the literature and might be useful for classroom demonstration and for testing new estimators are included.
Tasks
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00354v1
PDF	http://arxiv.org/pdf/1608.00354v1.pdf
PWC	https://paperswithcode.com/paper/hdm-high-dimensional-metrics
Repo
Framework

Semantic Segmentation using Adversarial Networks


Title	Semantic Segmentation using Adversarial Networks
Authors	Pauline Luc, Camille Couprie, Soumith Chintala, Jakob Verbeek
Abstract	Adversarial training has been shown to produce state of the art results for generative image modeling. In this paper we propose an adversarial training approach to train semantic segmentation models. We train a convolutional semantic segmentation network along with an adversarial network that discriminates segmentation maps coming either from the ground truth or from the segmentation network. The motivation for our approach is that it can detect and correct higher-order inconsistencies between ground truth segmentation maps and the ones produced by the segmentation net. Our experiments show that our adversarial training approach leads to improved accuracy on the Stanford Background and PASCAL VOC 2012 datasets.
Tasks	Semantic Segmentation
Published	2016-11-25
URL	http://arxiv.org/abs/1611.08408v1
PDF	http://arxiv.org/pdf/1611.08408v1.pdf
PWC	https://paperswithcode.com/paper/semantic-segmentation-using-adversarial
Repo
Framework

Lifted Message Passing for the Generalized Belief Propagation


Title	Lifted Message Passing for the Generalized Belief Propagation
Authors	Udi Apsel
Abstract	We introduce the lifted Generalized Belief Propagation (GBP) message passing algorithm, for the computation of sum-product queries in Probabilistic Relational Models (e.g. Markov logic network). The algorithm forms a compact region graph and establishes a modified version of message passing, which mimics the GBP behavior in a corresponding ground model. The compact graph is obtained by exploiting a graphical representation of clusters, which reduces cluster symmetry detection to isomorphism tests on small local graphs. The framework is thus capable of handling complex models, while remaining domain-size independent.
Tasks
Published	2016-10-05
URL	http://arxiv.org/abs/1610.01525v1
PDF	http://arxiv.org/pdf/1610.01525v1.pdf
PWC	https://paperswithcode.com/paper/lifted-message-passing-for-the-generalized
Repo
Framework

Decision making via semi-supervised machine learning techniques


Title	Decision making via semi-supervised machine learning techniques
Authors	Eftychios Protopapadakis
Abstract	Semi-supervised learning (SSL) is a class of supervised learning tasks and techniques that also exploits the unlabeled data for training. SSL significantly reduces labeling related costs and is able to handle large data sets. The primary objective is the extraction of robust inference rules. Decision support systems (DSSs) who utilize SSL have significant advantages. Only a small amount of labelled data is required for the initialization. Then, new (unlabeled) data can be utilized and improve system’s performance. Thus, the DSS is continuously adopted to new conditions, with minimum effort. Techniques which are cost effective and easily adopted to dynamic systems, can be beneficial for many practical applications. Such applications fields are: (a) industrial assembly lines monitoring, (b) sea border surveillance, (c) elders’ falls detection, (d) transportation tunnels inspection, (e) concrete foundation piles defect recognition, (f) commercial sector companies financial assessment and (g) image advanced filtering for cultural heritage applications.
Tasks	Decision Making
Published	2016-06-29
URL	http://arxiv.org/abs/1606.09022v1
PDF	http://arxiv.org/pdf/1606.09022v1.pdf
PWC	https://paperswithcode.com/paper/decision-making-via-semi-supervised-machine
Repo
Framework