October 15, 2019

2593 words 13 mins read

Paper Group NANR 230

Paper Group NANR 230

Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading. Bilevel Distance Metric Learning for Robust Image Recognition. Differentially Private Uniformly Most Powerful Tests for Binomial Data. Large Scale Urban Scene Modeling from MVS Meshes. Deep Models for Arabic Dialect Identification on Benchmarked Dat …

Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading

Title Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading
Authors Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers
Abstract We put forward a principled variational approach for up-sampling a single depth map to the resolution of the companion color image provided by an RGB-D sensor. We combine heterogeneous depth and color data in order to jointly solve the ill-posed depth super-resolution and shape-from-shading problems. The low-frequency geometric information necessary to disambiguate shape-from-shading is extracted from the low-resolution depth measurements and, symmetrically, the high-resolution photometric clues in the RGB image provide the high-frequency information required to disambiguate depth super-resolution.
Tasks Super-Resolution
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Haefner_Fight_Ill-Posedness_With_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Haefner_Fight_Ill-Posedness_With_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/fight-ill-posedness-with-ill-posedness-single
Repo
Framework

Bilevel Distance Metric Learning for Robust Image Recognition

Title Bilevel Distance Metric Learning for Robust Image Recognition
Authors Jie Xu, Lei Luo, Cheng Deng, Heng Huang
Abstract Metric learning, aiming to learn a discriminative Mahalanobis distance matrix M that can effectively reflect the similarity between data samples, has been widely studied in various image recognition problems. Most of the existing metric learning methods input the features extracted directly from the original data in the preprocess phase. What’s worse, these features usually take no consideration of the local geometrical structure of the data and the noise existed in the data, thus they may not be optimal for the subsequent metric learning task. In this paper, we integrate both feature extraction and metric learning into one joint optimization framework and propose a new bilevel distance metric learning model. Specifically, the lower level characterizes the intrinsic data structure using graph regularized sparse coefficients, while the upper level forces the data samples from the same class to be close to each other and pushes those from different classes far away. In addition, leveraging the KKT conditions and the alternating direction method (ADM), we derive an efficient algorithm to solve the proposed new model. Extensive experiments on various occluded datasets demonstrate the effectiveness and robustness of our method.
Tasks Metric Learning
Published 2018-12-01
URL http://papers.nips.cc/paper/7674-bilevel-distance-metric-learning-for-robust-image-recognition
PDF http://papers.nips.cc/paper/7674-bilevel-distance-metric-learning-for-robust-image-recognition.pdf
PWC https://paperswithcode.com/paper/bilevel-distance-metric-learning-for-robust
Repo
Framework

Differentially Private Uniformly Most Powerful Tests for Binomial Data

Title Differentially Private Uniformly Most Powerful Tests for Binomial Data
Authors Jordan Awan, Aleksandra Slavković
Abstract We derive uniformly most powerful (UMP) tests for simple and one-sided hypotheses for a population proportion within the framework of Differential Privacy (DP), optimizing finite sample performance. We show that in general, DP hypothesis tests can be written in terms of linear constraints, and for exchangeable data can always be expressed as a function of the empirical distribution. Using this structure, we prove a ‘Neyman-Pearson lemma’ for binomial data under DP, where the DP-UMP only depends on the sample sum. Our tests can also be stated as a post-processing of a random variable, whose distribution we coin “Truncated-Uniform-Laplace” (Tulap), a generalization of the Staircase and discrete Laplace distributions. Furthermore, we obtain exact p-values, which are easily computed in terms of the Tulap random variable. We show that our results also apply to distribution-free hypothesis tests for continuous data. Our simulation results demonstrate that our tests have exact type I error, and are more powerful than current techniques.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7675-differentially-private-uniformly-most-powerful-tests-for-binomial-data
PDF http://papers.nips.cc/paper/7675-differentially-private-uniformly-most-powerful-tests-for-binomial-data.pdf
PWC https://paperswithcode.com/paper/differentially-private-uniformly-most
Repo
Framework

Large Scale Urban Scene Modeling from MVS Meshes

Title Large Scale Urban Scene Modeling from MVS Meshes
Authors Lingjie Zhu, Shuhan Shen, Xiang Gao, Zhanyi Hu
Abstract In this paper we present an effcient modeling framework for large scale urban scenes. Taking surface meshes derived from multi- view-stereo systems as input, our algorithm outputs simplied models with semantics at different levels of detail (LODs). Our key observation is that urban building is usually composed of planar roof tops connected with vertical walls. There are two major steps in our framework: segmentation and building modeling. The scene is first segmented into four classes with a Markov random field combining height and image features. In the following modeling step, various 2D line segments sketching the roof boundaries are detected and slice the plane into faces. Through assigning each face with a roof plane, the final model is constructed by extruding the faces to the corresponding planes. By combining geometric and appearance cues together, the proposed method is robust and fast compared to the state-of-the-art algorithms.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Lingjie_Zhu_Large_Scale_Urban_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Lingjie_Zhu_Large_Scale_Urban_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/large-scale-urban-scene-modeling-from-mvs
Repo
Framework

Deep Models for Arabic Dialect Identification on Benchmarked Data

Title Deep Models for Arabic Dialect Identification on Benchmarked Data
Authors Mohamed Elaraby, Muhammad Abdul-Mageed
Abstract The Arabic Online Commentary (AOC) (Zaidan and Callison-Burch, 2011) is a large-scale repos-itory of Arabic dialects with manual labels for4varieties of the language. Existing dialect iden-tification models exploiting the dataset pre-date the recent boost deep learning brought to NLPand hence the data are not benchmarked for use with deep learning, nor is it clear how much neural networks can help tease the categories in the data apart. We treat these two limitations:We (1) benchmark the data, and (2) empirically test6different deep learning methods on thetask, comparing peformance to several classical machine learning models under different condi-tions (i.e., both binary and multi-way classification). Our experimental results show that variantsof (attention-based) bidirectional recurrent neural networks achieve best accuracy (acc) on thetask, significantly outperforming all competitive baselines. On blind test data, our models reach87.65{%}acc on the binary task (MSA vs. dialects),87.4{%}acc on the 3-way dialect task (Egyptianvs. Gulf vs. Levantine), and82.45{%}acc on the 4-way variants task (MSA vs. Egyptian vs. Gulfvs. Levantine). We release our benchmark for future work on the dataset
Tasks Language Identification, Machine Translation
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-3930/
PDF https://www.aclweb.org/anthology/W18-3930
PWC https://paperswithcode.com/paper/deep-models-for-arabic-dialect-identification
Repo
Framework

Learning Graph Convolution Filters from Data Manifold

Title Learning Graph Convolution Filters from Data Manifold
Authors Guokun Lai, Hanxiao Liu, Yiming Yang
Abstract Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending CNNs to the general spatial domain. Although various types of graph convolution and geometric convolution methods have been proposed, their connections to traditional 2D-convolution are not well-understood. In this paper, we show that depthwise separable convolution is a path to unify the two kinds of convolution methods in one mathematical view, based on which we derive a novel Depthwise Separable Graph Convolution that subsumes existing graph convolution methods as special cases of our formulation. Experiments show that the proposed approach consistently outperforms other graph convolution and geometric convolution baselines on benchmark datasets in multiple domains.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=H139Q_gAW
PDF https://openreview.net/pdf?id=H139Q_gAW
PWC https://paperswithcode.com/paper/learning-graph-convolution-filters-from-data
Repo
Framework

Graininess-Aware Deep Feature Learning for Pedestrian Detection

Title Graininess-Aware Deep Feature Learning for Pedestrian Detection
Authors Chunze Lin, Jiwen Lu, Gang Wang, Jie Zhou
Abstract In this paper, we propose a graininess-aware deep feature learning method for pedestrian detection. Unlike most existing pedestrian detection methods which only consider low resolution feature maps, we incorporate fine-grained information into convolutional features to make them more discriminative for human body parts. Specifically, we propose a pedestrian attention mechanism which efficiently identifies pedestrian regions. Our method encodes fine-grained attention masks into convolutional feature maps, which significantly suppresses background interference and highlights pedestrians. Hence, our graininess-aware features become more focused on pedestrians, in particular those of small size and with occlusion. We further introduce a zoom-in-zoom-out module, which enhances the features by incorporating local details and context information. We integrate these two modules into a deep neural network, forming an end-to-end trainable pedestrian detector. Comprehensive experimental results on four challenging pedestrian benchmarks demonstrate the effectiveness of the proposed approach.
Tasks Pedestrian Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Chunze_Lin_Graininess-Aware_Deep_Feature_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Chunze_Lin_Graininess-Aware_Deep_Feature_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/graininess-aware-deep-feature-learning-for
Repo
Framework

Incorporating Context into Language Encoding Models for fMRI

Title Incorporating Context into Language Encoding Models for fMRI
Authors Shailee Jain, Alexander Huth
Abstract Language encoding models help explain language processing in the human brain by learning functions that predict brain responses from the language stimuli that elicited them. Current word embedding-based approaches treat each stimulus word independently and thus ignore the influence of context on language understanding. In this work we instead build encoding models using rich contextual representations derived from an LSTM language model. Our models show a significant improvement in encoding performance relative to state-of-the-art embeddings in nearly every brain area. By varying the amount of context used in the models and providing the models with distorted context, we show that this improvement is due to a combination of better word embeddings learned by the LSTM language model and contextual information. We are also able to use our models to map context sensitivity across the cortex. These results suggest that LSTM language models learn high-level representations that are related to representations in the human brain.
Tasks Language Modelling, Word Embeddings
Published 2018-12-01
URL http://papers.nips.cc/paper/7897-incorporating-context-into-language-encoding-models-for-fmri
PDF http://papers.nips.cc/paper/7897-incorporating-context-into-language-encoding-models-for-fmri.pdf
PWC https://paperswithcode.com/paper/incorporating-context-into-language-encoding
Repo
Framework

Generating a Gold Standard for a Swedish Sentiment Lexicon

Title Generating a Gold Standard for a Swedish Sentiment Lexicon
Authors Jacobo Rouces, Nina Tahmasebi, Lars Borin, Stian R{\o}dven Eide
Abstract
Tasks Lemmatization, Machine Translation, Morphological Analysis, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1426/
PDF https://www.aclweb.org/anthology/L18-1426
PWC https://paperswithcode.com/paper/generating-a-gold-standard-for-a-swedish
Repo
Framework

Retrieval of the Best Counterargument without Prior Topic Knowledge

Title Retrieval of the Best Counterargument without Prior Topic Knowledge
Authors Henning Wachsmuth, Shahbaz Syed, Benno Stein
Abstract Given any argument on any controversial topic, how to counter it? This question implies the challenging retrieval task of finding the best counterargument. Since prior knowledge of a topic cannot be expected in general, we hypothesize the best counterargument to invoke the same aspects as the argument while having the opposite stance. To operationalize our hypothesis, we simultaneously model the similarity and dissimilarity of pairs of arguments, based on the words and embeddings of the arguments{'} premises and conclusions. A salient property of our model is its independence from the topic at hand, i.e., it applies to arbitrary arguments. We evaluate different model variations on millions of argument pairs derived from the web portal idebate.org. Systematic ranking experiments suggest that our hypothesis is true for many arguments: For 7.6 candidates with opposing stance on average, we rank the best counterargument highest with 60{%} accuracy. Even among all 2801 test set pairs as candidates, we still find the best one about every third time.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1023/
PDF https://www.aclweb.org/anthology/P18-1023
PWC https://paperswithcode.com/paper/retrieval-of-the-best-counterargument-without
Repo
Framework

Analysis of Rhythmic Phrasing: Feature Engineering vs. Representation Learning for Classifying Readout Poetry

Title Analysis of Rhythmic Phrasing: Feature Engineering vs. Representation Learning for Classifying Readout Poetry
Authors Timo Baumann, Hussein Hussein, Burkhard Meyer-Sickendiek
Abstract We show how to classify the phrasing of readout poems with the help of machine learning algorithms that use manually engineered features or automatically learn representations. We investigate modern and postmodern poems from the webpage lyrikline, and focus on two exemplary rhythmical patterns in order to detect the rhythmic phrasing: The Parlando and the Variable Foot. These rhythmical patterns have been compared by using two important theoretical works: The Generative Theory of Tonal Music and the Rhythmic Phrasing in English Verse. Using both, we focus on a combination of four different features: The grouping structure, the metrical structure, the time-span-variation, and the prolongation in order to detect the rhythmic phrasing in the two rhythmical types. We use manually engineered features based on text-speech alignment and parsing for classification. We also train a neural network to learn its own representation based on text, speech and audio during pauses. The neural network outperforms manual feature engineering, reaching an f-measure of 0.85.
Tasks Feature Engineering, Representation Learning
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4505/
PDF https://www.aclweb.org/anthology/W18-4505
PWC https://paperswithcode.com/paper/analysis-of-rhythmic-phrasing-feature
Repo
Framework

Resource Creation Towards Automated Sentiment Analysis in Telugu (a low resource language) and Integrating Multiple Domain Sources to Enhance Sentiment Prediction

Title Resource Creation Towards Automated Sentiment Analysis in Telugu (a low resource language) and Integrating Multiple Domain Sources to Enhance Sentiment Prediction
Authors Rama Rohit Reddy Gangula, Radhika Mamidi
Abstract
Tasks Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1100/
PDF https://www.aclweb.org/anthology/L18-1100
PWC https://paperswithcode.com/paper/resource-creation-towards-automated-sentiment
Repo
Framework

YNU-HPCC at SemEval-2018 Task 2: Multi-ensemble Bi-GRU Model with Attention Mechanism for Multilingual Emoji Prediction

Title YNU-HPCC at SemEval-2018 Task 2: Multi-ensemble Bi-GRU Model with Attention Mechanism for Multilingual Emoji Prediction
Authors Nan Wang, Jin Wang, Xuejie Zhang
Abstract This paper describes our approach to SemEval-2018 Task 2, which aims to predict the most likely associated emoji, given a tweet in English or Spanish. We normalized text-based tweets during pre-processing, following which we utilized a bi-directional gated recurrent unit with an attention mechanism to build our base model. Multi-models with or without class weights were trained for the ensemble methods. We boosted models without class weights, and only strong boost classifiers were identified. In our system, not only was a boosting method used, but we also took advantage of the voting ensemble method to enhance our final system result. Our method demonstrated an obvious improvement of approximately 3{%} of the macro F1 score in English and 2{%} in Spanish.
Tasks Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1073/
PDF https://www.aclweb.org/anthology/S18-1073
PWC https://paperswithcode.com/paper/ynu-hpcc-at-semeval-2018-task-2-multi
Repo
Framework

A Tensor Analysis on Dense Connectivity via Convolutional Arithmetic Circuits

Title A Tensor Analysis on Dense Connectivity via Convolutional Arithmetic Circuits
Authors Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
Abstract Several state of the art convolutional networks rely on inter-connecting different layers to ease the flow of information and gradient between their input and output layers. These techniques have enabled practitioners to successfully train deep convolutional networks with hundreds of layers. Particularly, a novel way of interconnecting layers was introduced as the Dense Convolutional Network (DenseNet) and has achieved state of the art performance on relevant image recognition tasks. Despite their notable empirical success, their theoretical understanding is still limited. In this work, we address this problem by analyzing the effect of layer interconnection on the overall expressive power of a convolutional network. In particular, the connections used in DenseNet are compared with other types of inter-layer connectivity. We carry out a tensor analysis on the expressive power inter-connections on convolutional arithmetic circuits (ConvACs) and relate our results to standard convolutional networks. The analysis leads to performance bounds and practical guidelines for design of ConvACs. The generalization of these results are discussed for other kinds of convolutional networks via generalized tensor decompositions.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=Byj54-bAW
PDF https://openreview.net/pdf?id=Byj54-bAW
PWC https://paperswithcode.com/paper/a-tensor-analysis-on-dense-connectivity-via
Repo
Framework

Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting With a Single Convolutional Net

Title Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting With a Single Convolutional Net
Authors Wenjie Luo, Bin Yang, Raquel Urtasun
Abstract In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is more robust to occlusion as well as sparse data at range. Our approach performs 3D convolutions across space and time over a bird’s eye view representation of the 3D world, which is very efficient in terms of both memory and computation. Our experiments on a new very large scale dataset captured in several north american cities, show that we can outperform the state-of-the-art by a large margin. Importantly, by sharing computation we can perform all tasks in as little as 30 ms.
Tasks Motion Forecasting
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Luo_Fast_and_Furious_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Luo_Fast_and_Furious_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/fast-and-furious-real-time-end-to-end-3d
Repo
Framework
comments powered by Disqus